This document discusses opportunities and challenges for machine learning in investing in the data economy. It outlines how machine learning approaches could enable regime-aware investing by overcoming limitations like catastrophic forgetting. However, finance poses unique challenges for machine learning due to its sequential nature and short history of clean explanatory data. The document suggests scientists focus research on scalable approaches for regime-aware investing, like using shallow and deep networks to separately predict returns and market conditions.
"Applying Deep Learning Techniques to Financial Time Series" by Scott Treloar...Quantopian
Presented at QuantCon Singapore 2016, Quantopian's quantitative finance and algorithmic trading conference, November 11th.
Deep learning is a subset of machine learning that draws on fields including applied mathematics, statistics, computer science and neuroscience. Currently it is experiencing tremendous growth due to the confluence of larger datasets, massive computational power and the development of new algorithms. While there is a lot of work on static data and some work on sequential data (such as text-based learning), less attention has been paid to (dynamic) time series data. In finance we are often interested in problems of prediction and classification, based on time series data.
In this talk, we introduce deep learning models and discuss their application to time series data. We do this in the context of using a trained model to make predictions from new data. After introducing the framework, we work through the application of deep learning to a number of areas in finance.
Empowering Quants in the Data Economy by Napoleon Hernandez at QuantCon 2016Quantopian
The proliferation of novel data sources has awoken quantitative investors to the promise of “Big Data”. Billions of venture capital funding has created an ecosystem of companies to help investors extract information out of unstructured text, sensors, etc. A “Vision for Quants in the Data Economy” is nice, but what does it take to turn that vision into reality? Join Data Capital Management as we discuss some of the breakthroughs by companies like Twitter, Google and Facebook that are empowering quantitative investors to extract alpha from “Big Data."
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...Quantopian
From QuantCon Singapore 2017: The vast proliferation of data related to the financial industry introduces both new opportunities and challenges to quantitative investors. These challenges are often due to the nature of big data and include: volume, variety, and velocity.
In this talk, Dr. Cheng will take the audience on a tour of the “big-data production line” in InfoTrie and show how the financial news collected from various and customizable sources are transformed into quantitative signals in a real-time manner. The talk will touch on various kind of topics like sentiment analysis, entity detection, topic classification, and big-data tools.
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle AlphaQuantopian
From QuantCon 2017: At J.P. Morgan's annual quantitative conference 93% of investors said alternative data will change the investment landscape.
In this presentation, Emmett will discuss the rapidly increasing adoption of alternative data, give a detailed overview of the 24 different types of alternative data, outline the applications of alternative data for quantitative funds, discuss interesting datasets that are available (including Asian datasets) and present case studies that evidence value in alternative datasets.
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...Quantopian
SEC filings provide a window into the health of the company and are immensely important for investors. Historically, the only feasible way to read and interpret filings has been manually, where domain experts interpret filings and provide guidance to public. However, advances in big data technologies and Natural Language processing have enabled its automation. Sameena will discuss how her team created predictive models from text in filings and social media.
This presentation was part of QuantCon 2015 hosted by Quantopian. Visit us at: www.quantopian.com.
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016Quantopian
The huge uptake of Python and R as first-class programming languages within quantitative trading has lead to an abundance of backtesting libraries becoming widely available. It can take months, if not years, to develop a robust backtesting and trading infrastructure from scratch and many of the vendors (both commercial and open source) have a huge head start. Given such prevalence and maturity of the available software, as well as the time investment needed for development, is there any benefit to building your own?
In this talk, Mike will argue the advantages and disadvantages of building your own infrastructure, how to develop and improve your first backtesting system and how to make it robust to internal and external risk events. The talk will be of interest whether you are a retail quant trader managing your own capital or are forming a start-up quant fund with initial seed funding.
"Applying Deep Learning Techniques to Financial Time Series" by Scott Treloar...Quantopian
Presented at QuantCon Singapore 2016, Quantopian's quantitative finance and algorithmic trading conference, November 11th.
Deep learning is a subset of machine learning that draws on fields including applied mathematics, statistics, computer science and neuroscience. Currently it is experiencing tremendous growth due to the confluence of larger datasets, massive computational power and the development of new algorithms. While there is a lot of work on static data and some work on sequential data (such as text-based learning), less attention has been paid to (dynamic) time series data. In finance we are often interested in problems of prediction and classification, based on time series data.
In this talk, we introduce deep learning models and discuss their application to time series data. We do this in the context of using a trained model to make predictions from new data. After introducing the framework, we work through the application of deep learning to a number of areas in finance.
Empowering Quants in the Data Economy by Napoleon Hernandez at QuantCon 2016Quantopian
The proliferation of novel data sources has awoken quantitative investors to the promise of “Big Data”. Billions of venture capital funding has created an ecosystem of companies to help investors extract information out of unstructured text, sensors, etc. A “Vision for Quants in the Data Economy” is nice, but what does it take to turn that vision into reality? Join Data Capital Management as we discuss some of the breakthroughs by companies like Twitter, Google and Facebook that are empowering quantitative investors to extract alpha from “Big Data."
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...Quantopian
From QuantCon Singapore 2017: The vast proliferation of data related to the financial industry introduces both new opportunities and challenges to quantitative investors. These challenges are often due to the nature of big data and include: volume, variety, and velocity.
In this talk, Dr. Cheng will take the audience on a tour of the “big-data production line” in InfoTrie and show how the financial news collected from various and customizable sources are transformed into quantitative signals in a real-time manner. The talk will touch on various kind of topics like sentiment analysis, entity detection, topic classification, and big-data tools.
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle AlphaQuantopian
From QuantCon 2017: At J.P. Morgan's annual quantitative conference 93% of investors said alternative data will change the investment landscape.
In this presentation, Emmett will discuss the rapidly increasing adoption of alternative data, give a detailed overview of the 24 different types of alternative data, outline the applications of alternative data for quantitative funds, discuss interesting datasets that are available (including Asian datasets) and present case studies that evidence value in alternative datasets.
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...Quantopian
SEC filings provide a window into the health of the company and are immensely important for investors. Historically, the only feasible way to read and interpret filings has been manually, where domain experts interpret filings and provide guidance to public. However, advances in big data technologies and Natural Language processing have enabled its automation. Sameena will discuss how her team created predictive models from text in filings and social media.
This presentation was part of QuantCon 2015 hosted by Quantopian. Visit us at: www.quantopian.com.
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016Quantopian
The huge uptake of Python and R as first-class programming languages within quantitative trading has lead to an abundance of backtesting libraries becoming widely available. It can take months, if not years, to develop a robust backtesting and trading infrastructure from scratch and many of the vendors (both commercial and open source) have a huge head start. Given such prevalence and maturity of the available software, as well as the time investment needed for development, is there any benefit to building your own?
In this talk, Mike will argue the advantages and disadvantages of building your own infrastructure, how to develop and improve your first backtesting system and how to make it robust to internal and external risk events. The talk will be of interest whether you are a retail quant trader managing your own capital or are forming a start-up quant fund with initial seed funding.
Overview of Quantopian: where we are and where we are headed.
Quantopian provides this presentation to help people write trading algorithms - it is not intended to provide investment advice.
More specifically, the material is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory or other services by Quantopian.
In addition, the content neither constitutes investment advice nor offers any opinion with respect to the suitability of any security or any specific investment. Quantopian makes no guarantees as to accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...Quantopian
Presented at QuantCon Singapore 2016, Quantopian's quantitative finance and algorithmic trading conference, November 11th.
The vast proliferation of data related to the financial industry introduces both new opportunities and challenges to quantitative investors. These challenges are often due to the nature of big data and include: volume, variety, and velocity.
In this talk, Dr. Cheng will take the audience on a tour of the “big-data production line” in InfoTrie and show how the financial news collected from various and customizable sources are transformed into quantitative signals in a real-time manner. The talk will touch on various kind of topics like sentiment analysis, entity detection, topic classification, and big-data tools.
Crowd-sourced Alpha: The Search for the Holy Grail of InvestingQuantopian
It has been said that diversification is the only free lunch. Join Dr. Jess Stauth, vice president of quant strategy at Quantopian, and learn about the criteria we are using to select crowd-sourced algorithms with uncorrelated returns streams to achieve consistent market outperformance.
Quantopian provides this presentation to help people write trading algorithms - it is not intended to provide investment advice.
More specifically, the material is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory or other services by Quantopian.
In addition, the content neither constitutes investment advice nor offers any opinion with respect to the suitability of any security or any specific investment. Quantopian makes no guarantees as to accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...Quantopian
Supply chains and network effects are becoming increasingly important and increasingly transparent in the global economy. However, conventional techniques are poorly equipped to handle relational data, and new techniques are required to decode the meaning of supply chain effects. We explore a novel technique for modelling and forecasting the diffusion of earnings revisions, known as a diffusion graph kernel support vector machine.
My Professional Journey in digitalization of seven industries as Educational intelligence. Data intelligence into Fintech insights, actions, solutions. Practical Reference: 7 Machine Learning Algorithms.
Examples for the build-out of the data and analytic architecture from my personal experience in seven industries
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...Quantopian
Over the last 10 years, the world of economics has been playing a catching up game and many economists have been struggling to explain their theories. The world has adopted technology in nearly every aspect of life, from phones to cars; however, good, reliable and quality data in economics is still elusive.
There is over reliance on macroeconomic principles in comparison to the quality of data available. Macro-economic figures move markets, only to get revised one, two or three times in the following months. Some fields of economic study are exceptions, such as analysing trade data. Trade data, with the support of technology, has become readily available and can now be analysed in depth, providing actual numbers indicating the health and state of economies.
Trade data, which is export and import information of all the goods and services from one country to another, can be seen as an inseparable marker of real economic activity. It can be used to predict various market indicators exhibiting high correlations, from currencies to commodities to equities to macroeconomic data, with varying degree of certainties. Trade data, at an in-depth level, acts like a compilation of millions of real life mathematical functions.
This presentation explores this new economic area of trade data as a quantitative tool, its intense big data analysis and its applications in trading markets.
The Datafication of HR: Graduating from Metrics to AnalyticsVisier
Datafication is a new term used to describe the process of turning an existing business into a “data business.” In HR it refers to our increasing ability to use Talent Analytics to understand more and more about our people, HR practices and processes, and external demographics.
Global competition for talent, outsourcing labor, compliance legislation, remote workers, aging populations – these are just a few of the daunting challenges faced by HR organizations today. Yet the most commonly monitored workforce metrics do very little to deliver true insight into these topics. Leaders need to graduate from metrics to analytics, surfacing the important connections and patterns in their data to make better workforce decisions.
Learn the difference between metrics and analytics, as well as key analytics and their values in these core areas:
Recruiting Effectiveness
Performance
Talent Retention
Employee Movement
Total Rewards
The challenges in today’s business environment require new approaches to remain competitive in an ever-shrinking world of global competition. By graduating from metrics to analytics, HR professionals and leaders can better understand the contributing factors that are impacting their organization, and take the right actions to implement programs that will provide a true competitive advantage.
View the full webinar recording here:
http://www.visier.com/lp/the-datafication-of-hr-graduating-from-metrics-to-analytics/
Download the companion white paper here:
http://www.visier.com/lp/wp-datafication-of-hr/
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...Quantopian
Quantitative Investors have long been charged with an exhilarating challenge - to derive insight from data. To support this ardor, a plethora of traditional data and technology vendors have entrenched themselves as critical partners in our pursuit of Alpha.
Over the last decade, a new partner in the pursuit of “automated truth from data” has emerged. Billions of dollars in Venture Capital funding have created an ecosystem of “Big Data”, “Cognitive Intelligence”, “Cloud Technology”, etc. companies seeking to extract information from anything and everything (e.g. unstructured text, sensors, satellites, etc.). This “Data Revolution” began in California and is now blossoming globally.
As “Silicon Alley” brings financial technology to the mainstream, what new opportunities await the ambitious? What disruptions threaten the complacent? And which historical analogs best illuminate the path forward for Quantitative Investors in the “Data Economy”?
A focus on 4 key issues related to HR technology.
1. Cloud computing & SaaS
2. Integration between SaaS & on-premises
3. Social media impacts
4. Gamification of HR
New Industrial Revolution and Digital Business ModelsRobin Teigland
An extended version of my presentation on digital business models for Chairmen and CXOs of some of Sweden's largest multinationals (primarily B2B) in January 2017.
Data analysis is becoming the most significant core for the digital corporation. This talk provides information about how time to develop software and deploy apps in data centers has declined by orders of magnitude. It focuses on cases from Adidas, BlackRock, and BristolMyersSquibb to illustrate data -driven digital firms. It highlights how the growth of AutoML will speed the move to data analysis and faster creation of algorithms. It also explores the impact of these changes on jobs.
The customer journey could essentially be divided into 7 elements. We’ll touch upon the issue of ‘Privacy’ and how one balance social and commercial value. Practical examples of
customer analytics at its best will be discussed as well as the importance of the eco-system.
Scaling the mirrorworld with knowledge graphsAlan Morrison
After registration at https://www.brighttalk.com/webcast/9273/364148, you can view the full recording, which begins with Scott Abel's intro for a few minutes, then my talk for 20 minutes, and then Sebastian Gabler's. First presented on October 23 at an SWC webinar.
Conclusions:
(1) The mirrorworld (a world of digital twins, which will be 25 years in the making, according to Kevin Kelly) will require semantic knowledge graphs for interaction and interoperability.
(2) This fact implies massive future demand for knowledge graph technology and other new data infrastructure innovations, comparable to the scale of oil & gas industry infrastructure development over 150 years.
(3) Conceivably, knowledge graphs could be used to address a $205 billion market demand by 2021 for graph databases, information management, digital twins, conversational AI, virtual assistants and as knowledge bases/accelerated training for deep learning, etc. but the problem is that awareness of the tech is low, and the semantics community that understands the tech is still quite small.
(4) Over the next decades, knowledge graphs promise both scalability and substantial efficiencies in enterprises. But lack of awareness of its potential and how to harness it will continue to be stumbling blocks to adoption.
Overview of Quantopian: where we are and where we are headed.
Quantopian provides this presentation to help people write trading algorithms - it is not intended to provide investment advice.
More specifically, the material is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory or other services by Quantopian.
In addition, the content neither constitutes investment advice nor offers any opinion with respect to the suitability of any security or any specific investment. Quantopian makes no guarantees as to accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...Quantopian
Presented at QuantCon Singapore 2016, Quantopian's quantitative finance and algorithmic trading conference, November 11th.
The vast proliferation of data related to the financial industry introduces both new opportunities and challenges to quantitative investors. These challenges are often due to the nature of big data and include: volume, variety, and velocity.
In this talk, Dr. Cheng will take the audience on a tour of the “big-data production line” in InfoTrie and show how the financial news collected from various and customizable sources are transformed into quantitative signals in a real-time manner. The talk will touch on various kind of topics like sentiment analysis, entity detection, topic classification, and big-data tools.
Crowd-sourced Alpha: The Search for the Holy Grail of InvestingQuantopian
It has been said that diversification is the only free lunch. Join Dr. Jess Stauth, vice president of quant strategy at Quantopian, and learn about the criteria we are using to select crowd-sourced algorithms with uncorrelated returns streams to achieve consistent market outperformance.
Quantopian provides this presentation to help people write trading algorithms - it is not intended to provide investment advice.
More specifically, the material is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory or other services by Quantopian.
In addition, the content neither constitutes investment advice nor offers any opinion with respect to the suitability of any security or any specific investment. Quantopian makes no guarantees as to accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...Quantopian
Supply chains and network effects are becoming increasingly important and increasingly transparent in the global economy. However, conventional techniques are poorly equipped to handle relational data, and new techniques are required to decode the meaning of supply chain effects. We explore a novel technique for modelling and forecasting the diffusion of earnings revisions, known as a diffusion graph kernel support vector machine.
My Professional Journey in digitalization of seven industries as Educational intelligence. Data intelligence into Fintech insights, actions, solutions. Practical Reference: 7 Machine Learning Algorithms.
Examples for the build-out of the data and analytic architecture from my personal experience in seven industries
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...Quantopian
Over the last 10 years, the world of economics has been playing a catching up game and many economists have been struggling to explain their theories. The world has adopted technology in nearly every aspect of life, from phones to cars; however, good, reliable and quality data in economics is still elusive.
There is over reliance on macroeconomic principles in comparison to the quality of data available. Macro-economic figures move markets, only to get revised one, two or three times in the following months. Some fields of economic study are exceptions, such as analysing trade data. Trade data, with the support of technology, has become readily available and can now be analysed in depth, providing actual numbers indicating the health and state of economies.
Trade data, which is export and import information of all the goods and services from one country to another, can be seen as an inseparable marker of real economic activity. It can be used to predict various market indicators exhibiting high correlations, from currencies to commodities to equities to macroeconomic data, with varying degree of certainties. Trade data, at an in-depth level, acts like a compilation of millions of real life mathematical functions.
This presentation explores this new economic area of trade data as a quantitative tool, its intense big data analysis and its applications in trading markets.
The Datafication of HR: Graduating from Metrics to AnalyticsVisier
Datafication is a new term used to describe the process of turning an existing business into a “data business.” In HR it refers to our increasing ability to use Talent Analytics to understand more and more about our people, HR practices and processes, and external demographics.
Global competition for talent, outsourcing labor, compliance legislation, remote workers, aging populations – these are just a few of the daunting challenges faced by HR organizations today. Yet the most commonly monitored workforce metrics do very little to deliver true insight into these topics. Leaders need to graduate from metrics to analytics, surfacing the important connections and patterns in their data to make better workforce decisions.
Learn the difference between metrics and analytics, as well as key analytics and their values in these core areas:
Recruiting Effectiveness
Performance
Talent Retention
Employee Movement
Total Rewards
The challenges in today’s business environment require new approaches to remain competitive in an ever-shrinking world of global competition. By graduating from metrics to analytics, HR professionals and leaders can better understand the contributing factors that are impacting their organization, and take the right actions to implement programs that will provide a true competitive advantage.
View the full webinar recording here:
http://www.visier.com/lp/the-datafication-of-hr-graduating-from-metrics-to-analytics/
Download the companion white paper here:
http://www.visier.com/lp/wp-datafication-of-hr/
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...Quantopian
Quantitative Investors have long been charged with an exhilarating challenge - to derive insight from data. To support this ardor, a plethora of traditional data and technology vendors have entrenched themselves as critical partners in our pursuit of Alpha.
Over the last decade, a new partner in the pursuit of “automated truth from data” has emerged. Billions of dollars in Venture Capital funding have created an ecosystem of “Big Data”, “Cognitive Intelligence”, “Cloud Technology”, etc. companies seeking to extract information from anything and everything (e.g. unstructured text, sensors, satellites, etc.). This “Data Revolution” began in California and is now blossoming globally.
As “Silicon Alley” brings financial technology to the mainstream, what new opportunities await the ambitious? What disruptions threaten the complacent? And which historical analogs best illuminate the path forward for Quantitative Investors in the “Data Economy”?
A focus on 4 key issues related to HR technology.
1. Cloud computing & SaaS
2. Integration between SaaS & on-premises
3. Social media impacts
4. Gamification of HR
New Industrial Revolution and Digital Business ModelsRobin Teigland
An extended version of my presentation on digital business models for Chairmen and CXOs of some of Sweden's largest multinationals (primarily B2B) in January 2017.
Data analysis is becoming the most significant core for the digital corporation. This talk provides information about how time to develop software and deploy apps in data centers has declined by orders of magnitude. It focuses on cases from Adidas, BlackRock, and BristolMyersSquibb to illustrate data -driven digital firms. It highlights how the growth of AutoML will speed the move to data analysis and faster creation of algorithms. It also explores the impact of these changes on jobs.
The customer journey could essentially be divided into 7 elements. We’ll touch upon the issue of ‘Privacy’ and how one balance social and commercial value. Practical examples of
customer analytics at its best will be discussed as well as the importance of the eco-system.
Scaling the mirrorworld with knowledge graphsAlan Morrison
After registration at https://www.brighttalk.com/webcast/9273/364148, you can view the full recording, which begins with Scott Abel's intro for a few minutes, then my talk for 20 minutes, and then Sebastian Gabler's. First presented on October 23 at an SWC webinar.
Conclusions:
(1) The mirrorworld (a world of digital twins, which will be 25 years in the making, according to Kevin Kelly) will require semantic knowledge graphs for interaction and interoperability.
(2) This fact implies massive future demand for knowledge graph technology and other new data infrastructure innovations, comparable to the scale of oil & gas industry infrastructure development over 150 years.
(3) Conceivably, knowledge graphs could be used to address a $205 billion market demand by 2021 for graph databases, information management, digital twins, conversational AI, virtual assistants and as knowledge bases/accelerated training for deep learning, etc. but the problem is that awareness of the tech is low, and the semantics community that understands the tech is still quite small.
(4) Over the next decades, knowledge graphs promise both scalability and substantial efficiencies in enterprises. But lack of awareness of its potential and how to harness it will continue to be stumbling blocks to adoption.
Digital transformation for the next decadeSudipta Lahiri
In this talk, I cover the Digital Transformation trends that we will see in the next decade in the context of the changes that we can expect to see in the environment around us. We then talk about how do organizations need to prepare to be able to take advantage of these trends.
LinkedIn Executive Summit in Munich: Digital Transformation @ ScaleLinkedIn D-A-CH
presented by Karel Dörner (McKinsey) at the LinkedIn Executive Summit in Munich, Sept 8. Fur further questions please reach out via http://bit.ly/KontaktLNKD. Thank you and we are looking forward to seeing you soon again.
Linked Data and examples, why they matter. Data driven strategies. Data mining: laws and applications. Data aggregation and fundamentals of data representation (table, bar chart, histogram, pie chart, line graph, scatter plot). Data science definition and job roles (who does what).
Data2030 Summit Data Megatrends Turner Sept 2022.pptxMatt Turner
The next challenge in data is rapidly becoming clear: how can we scale data value and bring data driven decision making to everyone? We’ve made tremendous progress in bringing data together. The megatrends in data - data mesh, data fabric, modern data stack - are all about crossing the last mile to get data to everyone, not just the data experts. How can we empower everyone to better use data? Are the megatrends the road to actually scaling data value? And what does that mean for the data teams and data engineers creating systems and delivering dataops?
BIG DATA is having an enormous impact on the profile of workforces around the world. If you've ever seen the technology and experienced the impact it has on the pace of innovation in a business then the predictations made by McKinsey Global Institute will come as no surprise ( and just in case you've been on holiday for around two years, McKinsey is suggesting that by 2018 the US will face a shortfall of close to 200,000 analysts and 1.5 million managers with the right skills. In this presentation I outline the impact of BIG DATA on workforce design. I hope you find it informative and fun to read. Ian.
Similar to "Machine Learning Approaches to Regime-aware Portfolio Management" by Michael M. Beal, Managing Member & CEO of Data Capital Management (20)
Being open (source) in the traditionally secretive field of quant finance.Quantopian
The field of quantitative finance is intensely competitive and maniacally secretive as a rule. The tendency toward secrecy is perhaps unsurprising given that the smallest of competitive advantages can translate to substantial profits. Indeed, over the past decade a growing list of legal prosecutions for alleged code theft or misuse have underscored how high the stakes can be for developers looking to leverage and contribute to open source projects. Notable exceptions to this approach include work from Wes McKinney and Travis Oliphant, whose work on open source projects like pandas and numpy, which have gained widespread adoption. In this talk we will review some of the costs and benefits of engaging with open source as a “two way street” and frame the modern quant workflow as a mosaic of open sourced, third party, and proprietary components.
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Quantopian
Data Modeling the Stock Market Today - Common Pitfalls to Avoid
The lure of creating models to predict the stock market has drawn talent from fields beyond finance and economics, reaching into disciplines such as physics, computational chemistry, applied mathematics, electrical engineering and perhaps most recently statistics and what we now refer to as data science. The attraction is clear - the stock market (and the economy/internet at large) throws off massive and ever increasing reams of data from garden variety time-series to complex structured data sets like quarterly financials, to unstructured data sets like conference call transcripts, news articles and of course — tweets! While all this data holds promise - it also holds traps and blind alleys that can be deceptively tricky to avoid. In this session we’ll review some of the common (but not easy!) pitfalls to avoid in creating models for predicting stock returns; overfitting & exploding model complexity, non-stationary processes, time-travel illusions, under-estimation of real-world costs, and as many more as we have time to cover.
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...Quantopian
From QuantCon 2017: Lookahead bias and stale data when used in an algorithm are generally categorized as "incorrect data". In fact, the issue does not lie with the data itself, but instead is an issue of perspective. This talk will examine how data is typically viewed through the lens of time, and why, on the whole, that approach is wrong.
At Quantopian, we've tried several ways of handling data with regards to time, and we'll talk about lessons learned along the way. We'll also discuss what multidimensionality means for financial data specifically, and how we can apply this to get better results in backtesting.
Additionally, we'll touch on how to apply multidimensionality to more general data, and why it's important for anyone working with applied data to take this approach.
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...Quantopian
We generally assume the past is a good guide to the future, but well do we even know the past? What effect does this uncertainty when estimating inputs have on the notoriously unstable algorithms for portfolio optimization?
I explore this issue, look at some commonly used solutions, and also introduce some alternative methods.
"Quant Trading for a Living – Lessons from a Life in the Trenches" by Andreas...Quantopian
It takes hard work, skill and time to develop robust trading models, but that is just the beginning of the journey. The question then is what you can do with it, and how to go about building a career in quant finance.
If your plan is to move beyond hobby trading and build a career in in the professional quant trading field, the work is not over once you have a great model.
This presentation will discuss how to leverage your trading models into building a successful career in quant trading. We will look at the various options available, and their respective merits and faults. Whether you want to trade your own money for a living, find a job in the industry or build your own business, your model design will have to be adapted to your aim. We will discuss what type of models and results there is a market for, how to go about finding investors for your trading, and how the real economics of the business look.
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...Quantopian
From QuantCon Singapore 2017: In this presentation, Olivier d’Assier, Managing Director of APAC Applied Research, will discuss the major drivers of the change in risk year-to-date and how the risk environment is affecting investor’s portfolios. This talk will look at global markets with a focus on the Asian region and how it compares to others with regards to its risk footprint.
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...Quantopian
Factor modeling and style premia are historically well documented and extensively researched in generating abnormal returns. Despite the large amount of research around factors, there is less clarity around effectively capturing and extracting this alpha from a given universe. In this presentation, Cheng will demonstrate different techniques for combining multiple factors, and the rationale behind maximizing alpha while maintaining scalability.
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...Quantopian
From QuantCon 2017: Running a quantitative trading business in China used to be very difficult and require strong IT skills, however it's getting much easier nowadays, when traders with no professional IT training can also do all the tasks in quantitative trading using Python.
In this sharing session, Xiaoyou will share his experience in using Python for data collection, strategy development and automated trading. He will also introduce some related open source projects including TuShare, quantOS, vn.py and so on.
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlphaQuantopian
From QuantCon 2017:
Fundamental and quantitative stock selection research has long focused on creating accurate forecasts of company fundamentals such as earnings and revenues. In this talk we examine why fundamental forecasts are powerful and survey some classic methods for generating these forecasts. Next we explore some newer methodologies which can be effective in generating more accurate fundamental forecasts, including new uses of traditional data as well as novel crowdsourced and online behavior databases. Finally, we present new research examining the temporal variation in efficacy of these forecasts with an eye towards understanding the market conditions in which an accurate fundamental forecast can be more or less profitable.
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...Quantopian
From QuantCon 2017: Implementation is the efficient translation of alpha research into portfolios. It includes portfolio construction and trading. It is a vital step in the quant equity workflow, as poor implementation can ruin even the best alpha ideas. Two crucial challenges must be solved: how to construct a portfolio that most efficiently captures a given alpha signal; and, in the presence of multiple signals, how to optimally combine them into a single composite alpha factor.
This talk addresses these challenges, examines common pitfalls in the implementation of quantitative strategies and good practices to avoid them. A common theme is striking the right balance between factor signal purity and investability. We look at how factor models and optimisation techniques help professional investors answer three key questions:
· What risks should your risk model be cognisant of?
· What objective function should you use?
· What effect do investability constraints have on your portfolio?
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...Quantopian
From QuantCon 2017: Financial trading is essentially a search problem. The buy-side agent needs to find a counterpart sell-side agent willing to trade the financial asset at the set quantity and price.
Ilija will present a deep reinforcement learning algorithm for optimizing the execution of limit-order actions to find an optimal order placement. The reinforcement learning agent utilizes historical limit-order data to learn an optimal compromise between fast order completion but with higher costs and slow, riskier order completion but with lower costs.
The talk will continue with the challenges of applying reinforcement learning to optimal trading and their potential solutions. Finally, Ilija will share the system architecture and discuss future work.
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...Quantopian
Hierarchical Risk Parity (HRP) portfolios address three major concerns of quadratic optimizers in general and Markowitz’s CLA in particular: Instability, concentration and underperformance. HRP applies modern mathematics (graph theory and machine learning techniques) to build a diversified portfolio based on the information contained in the covariance matrix. However, unlike quadratic optimizers, HRP does not require the invertibility of the covariance matrix. In fact, HRP can compute a portfolio on an ill-degenerated or even a singular covariance matrix, an impossible feat for quadratic optimizers. Monte Carlo experiments show that HRP delivers lower out-of-sample variance than CLA, even though minimum-variance is CLA’s optimization objective. HRP also produces less risky portfolios out-of-sample compared to traditional risk parity methods.
Read the corresponding white paper here: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2713516
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...Quantopian
Contrary to popular wisdom the difference between a retail quant trader and a professional portfolio manager is not in "having better trade entry and exit rules". Rather it is the difference in how each approaches the concepts of portfolio optimisation and risk management.
Both of these topics are synonymous with heavy math, which can be off-putting for beginner retail systematic traders. Hence, it can be extremely daunting for those without institutional experience to know how to turn a set of trading rules into a robust portfolio and risk management system.
In this talk, Mike will discuss how to take a typical retail quant strategy and place it in a professional quantitative trading framework, with proper position sizing and risk assessment, without resorting to pages of formulas or the need to have a PhD in statistics!
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...Quantopian
Reinforcement Learning (RL) has been around for a long time, but it has not attracted much attention over the last decade. Until, that is, a group of Google researchers showed how RL can be used to train a computer to play video games at far above human capabilities.
Besides video games, the RL problem is also well aligned to solve trading problems as well (e.g., work by Dr. Michael Kearns). In this talk, Tucker will provide a gentle introduction to Q-Learning, one of the leading RL methods.
He will also show how Q-Learning can be integrated with artificial neural network learners and how such a system can be used to learn and execute a trading strategy. This is joint work with David Byrd at Georgia Tech.
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...Quantopian
Maxwell will present the methodologies and results behind the algorithm that has been developed by 1QBit, named Quantum Hierarchical Risk Parity, or QHRP.
This is an extension of the work done by Marcos Lopez de Prado on
Hierarchical Risk Parity in his paper "Building Diversified Portfolios that Outperform Out-of-Sample."
QHRP tackles the problem of minimizing the risk of a portfolio of assets using a quantum-inspired approach. Although the ideas surrounding this go back to Markowitz’s mean-variance portfolio optimization of 1952’s Portfolio Selection, we have applied recent quantum-ready machine learning tools to the problem to demonstrate strong performance in terms of a variety of risk measures and lower susceptibility to inaccuracies in the input data.
The quantum-ready approach to portfolio optimization is based on
an optimization problem that can be solved using a quantum annealer. The algorithm utilizes a hierarchical clustering tree that is based on the covariance matrix of the asset returns. The results of real market data used to benchmark this approach against other common portfolio optimization methods will be shared in this presentation.
View the White Paper: https://bit.ly/2k5xTxW.
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...Quantopian
BlackRock forecasts smart beta investing oriented toward size, value, quality, momentum, and low volatility to reach $1 trillion by 2020 and $2.4 trillion by 2025. Gary’s talk will show that this growth may not be justified due to these factors' lack of robustness, consistency, persistence, intuitiveness, and investability. Gary will also show that the success attributed to these factors would be better directed toward macro momentum and the short interest ratio.
"From Trading Strategy to Becoming an Industry Professional – How to Break in...Quantopian
You have created a great trading strategy, backtested, traded it and now you want to take it to the next level. You may find that developing the strategy was just the first of many difficult steps.
With the increased availability of low cost, high quality quant modelling platforms, the field is much more open than it once was. The interest for algorithmic trading his higher than ever and anyone has the potential develop a great trading model.
But having a great trading model is not enough. The work is not done yet.
This presentation will discuss turning your algorithmic trading strategy into a business or a great job, and becoming a professional trader. We’re going to talk about what it takes to move to the next level and where the common pitfalls lay. What kind of strategies are marketable are which are not. The pros and cons of trading your own money and how to go about finding external capital and gaining traction in the business.
Are you ready to take the step?
how to sell pi coins effectively (from 50 - 100k pi)DOT TECH
Anywhere in the world, including Africa, America, and Europe, you can sell Pi Network Coins online and receive cash through online payment options.
Pi has not yet been launched on any exchange because we are currently using the confined Mainnet. The planned launch date for Pi is June 28, 2026.
Reselling to investors who want to hold until the mainnet launch in 2026 is currently the sole way to sell.
Consequently, right now. All you need to do is select the right pi network provider.
Who is a pi merchant?
An individual who buys coins from miners on the pi network and resells them to investors hoping to hang onto them until the mainnet is launched is known as a pi merchant.
debuts.
I'll provide you the Telegram username
@Pi_vendor_247
The secret way to sell pi coins effortlessly.DOT TECH
Well as we all know pi isn't launched yet. But you can still sell your pi coins effortlessly because some whales in China are interested in holding massive pi coins. And they are willing to pay good money for it. If you are interested in selling I will leave a contact for you. Just telegram this number below. I sold about 3000 pi coins to him and he paid me immediately.
Telegram: @Pi_vendor_247
what is the future of Pi Network currency.DOT TECH
The future of the Pi cryptocurrency is uncertain, and its success will depend on several factors. Pi is a relatively new cryptocurrency that aims to be user-friendly and accessible to a wide audience. Here are a few key considerations for its future:
Message: @Pi_vendor_247 on telegram if u want to sell PI COINS.
1. Mainnet Launch: As of my last knowledge update in January 2022, Pi was still in the testnet phase. Its success will depend on a successful transition to a mainnet, where actual transactions can take place.
2. User Adoption: Pi's success will be closely tied to user adoption. The more users who join the network and actively participate, the stronger the ecosystem can become.
3. Utility and Use Cases: For a cryptocurrency to thrive, it must offer utility and practical use cases. The Pi team has talked about various applications, including peer-to-peer transactions, smart contracts, and more. The development and implementation of these features will be essential.
4. Regulatory Environment: The regulatory environment for cryptocurrencies is evolving globally. How Pi navigates and complies with regulations in various jurisdictions will significantly impact its future.
5. Technology Development: The Pi network must continue to develop and improve its technology, security, and scalability to compete with established cryptocurrencies.
6. Community Engagement: The Pi community plays a critical role in its future. Engaged users can help build trust and grow the network.
7. Monetization and Sustainability: The Pi team's monetization strategy, such as fees, partnerships, or other revenue sources, will affect its long-term sustainability.
It's essential to approach Pi or any new cryptocurrency with caution and conduct due diligence. Cryptocurrency investments involve risks, and potential rewards can be uncertain. The success and future of Pi will depend on the collective efforts of its team, community, and the broader cryptocurrency market dynamics. It's advisable to stay updated on Pi's development and follow any updates from the official Pi Network website or announcements from the team.
how to sell pi coins at high rate quickly.DOT TECH
Where can I sell my pi coins at a high rate.
Pi is not launched yet on any exchange. But one can easily sell his or her pi coins to investors who want to hold pi till mainnet launch.
This means crypto whales want to hold pi. And you can get a good rate for selling pi to them. I will leave the telegram contact of my personal pi vendor below.
A vendor is someone who buys from a miner and resell it to a holder or crypto whale.
Here is the telegram contact of my vendor:
@Pi_vendor_247
how to sell pi coins in all Africa Countries.DOT TECH
Yes. You can sell your pi network for other cryptocurrencies like Bitcoin, usdt , Ethereum and other currencies And this is done easily with the help from a pi merchant.
What is a pi merchant ?
Since pi is not launched yet in any exchange. The only way you can sell right now is through merchants.
A verified Pi merchant is someone who buys pi network coins from miners and resell them to investors looking forward to hold massive quantities of pi coins before mainnet launch in 2026.
I will leave the telegram contact of my personal pi merchant to trade with.
@Pi_vendor_247
how to sell pi coins on Bitmart crypto exchangeDOT TECH
Yes. Pi network coins can be exchanged but not on bitmart exchange. Because pi network is still in the enclosed mainnet. The only way pioneers are able to trade pi coins is by reselling the pi coins to pi verified merchants.
A verified merchant is someone who buys pi network coins and resell it to exchanges looking forward to hold till mainnet launch.
I will leave the telegram contact of my personal pi merchant to trade with.
@Pi_vendor_247
Empowering the Unbanked: The Vital Role of NBFCs in Promoting Financial Inclu...Vighnesh Shashtri
In India, financial inclusion remains a critical challenge, with a significant portion of the population still unbanked. Non-Banking Financial Companies (NBFCs) have emerged as key players in bridging this gap by providing financial services to those often overlooked by traditional banking institutions. This article delves into how NBFCs are fostering financial inclusion and empowering the unbanked.
Turin Startup Ecosystem 2024 - Ricerca sulle Startup e il Sistema dell'Innov...Quotidiano Piemontese
Turin Startup Ecosystem 2024
Una ricerca de il Club degli Investitori, in collaborazione con ToTeM Torino Tech Map e con il supporto della ESCP Business School e di Growth Capital
how to sell pi coins in South Korea profitably.DOT TECH
Yes. You can sell your pi network coins in South Korea or any other country, by finding a verified pi merchant
What is a verified pi merchant?
Since pi network is not launched yet on any exchange, the only way you can sell pi coins is by selling to a verified pi merchant, and this is because pi network is not launched yet on any exchange and no pre-sale or ico offerings Is done on pi.
Since there is no pre-sale, the only way exchanges can get pi is by buying from miners. So a pi merchant facilitates these transactions by acting as a bridge for both transactions.
How can i find a pi vendor/merchant?
Well for those who haven't traded with a pi merchant or who don't already have one. I will leave the telegram id of my personal pi merchant who i trade pi with.
Tele gram: @Pi_vendor_247
#pi #sell #nigeria #pinetwork #picoins #sellpi #Nigerian #tradepi #pinetworkcoins #sellmypi
Resume
• Real GDP growth slowed down due to problems with access to electricity caused by the destruction of manoeuvrable electricity generation by Russian drones and missiles.
• Exports and imports continued growing due to better logistics through the Ukrainian sea corridor and road. Polish farmers and drivers stopped blocking borders at the end of April.
• In April, both the Tax and Customs Services over-executed the revenue plan. Moreover, the NBU transferred twice the planned profit to the budget.
• The European side approved the Ukraine Plan, which the government adopted to determine indicators for the Ukraine Facility. That approval will allow Ukraine to receive a EUR 1.9 bn loan from the EU in May. At the same time, the EU provided Ukraine with a EUR 1.5 bn loan in April, as the government fulfilled five indicators under the Ukraine Plan.
• The USA has finally approved an aid package for Ukraine, which includes USD 7.8 bn of budget support; however, the conditions and timing of the assistance are still unknown.
• As in March, annual consumer inflation amounted to 3.2% yoy in April.
• At the April monetary policy meeting, the NBU again reduced the key policy rate from 14.5% to 13.5% per annum.
• Over the past four weeks, the hryvnia exchange rate has stabilized in the UAH 39-40 per USD range.
The European Unemployment Puzzle: implications from population agingGRAPE
We study the link between the evolving age structure of the working population and unemployment. We build a large new Keynesian OLG model with a realistic age structure, labor market frictions, sticky prices, and aggregate shocks. Once calibrated to the European economy, we quantify the extent to which demographic changes over the last three decades have contributed to the decline of the unemployment rate. Our findings yield important implications for the future evolution of unemployment given the anticipated further aging of the working population in Europe. We also quantify the implications for optimal monetary policy: lowering inflation volatility becomes less costly in terms of GDP and unemployment volatility, which hints that optimal monetary policy may be more hawkish in an aging society. Finally, our results also propose a partial reversal of the European-US unemployment puzzle due to the fact that the share of young workers is expected to remain robust in the US.
Even tho Pi network is not listed on any exchange yet.
Buying/Selling or investing in pi network coins is highly possible through the help of vendors. You can buy from vendors[ buy directly from the pi network miners and resell it]. I will leave the telegram contact of my personal vendor.
@Pi_vendor_247
What website can I sell pi coins securely.DOT TECH
Currently there are no website or exchange that allow buying or selling of pi coins..
But you can still easily sell pi coins, by reselling it to exchanges/crypto whales interested in holding thousands of pi coins before the mainnet launch.
Who is a pi merchant?
A pi merchant is someone who buys pi coins from miners and resell to these crypto whales and holders of pi..
This is because pi network is not doing any pre-sale. The only way exchanges can get pi is by buying from miners and pi merchants stands in between the miners and the exchanges.
How can I sell my pi coins?
Selling pi coins is really easy, but first you need to migrate to mainnet wallet before you can do that. I will leave the telegram contact of my personal pi merchant to trade with.
Tele-gram.
@Pi_vendor_247
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael M. Beal, Managing Member & CEO of Data Capital Management
1. T H E F U T U R E O F I N V E S T I N G I N T H E D ATA E C O N O M Y
0
2. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 1
Saturday, April 29, 2017
Michael M. Beal
DCM@datacapitalmanagement.com
#DCMMilestones
THE FUTURE OF PUBLIC MARKET INVESTING
IN THE DATA ECONOMY
3. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 2
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
4. LESSONS FROM THE INDUSTRIAL REVOLUTION
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 3
Suggestions for Companies in the Data Economy
• Standardize industry taxonomies
• Be the best at depth of information for a given vertical
• Take responsibility for the veracity of information
• Focus on speed of delivery
• Focus on historical consistency
• Make adjustments visible to upstream users
• Focus on permissible data use rights
• Don’t be all things to all people
Got API?
dcm@datacapitalmanagement.com
Our goal is to help drive a standard for other players in our ecosystem to coalesce around
• This approach helps avoid the “tragedy of the commons” and maximize collective ROI
• We are set up to be “early customers” of new technologies / beta releases
• We drive a culture of focused and targeted feedback
For those with self-interests congruent to ours; let’s help each other
5. CHALLENGE 1: DATA INTEGRATION
Data are just summaries of thousands of stories – Chip & Dan Heath
OUTCOME: Broader, deeper, faster access to relevant data
Data Querying
Data Bi-temporality
Data linkage
Unified query layer on top of multiple data
storage engines
Treatment of bi-temporality as a
fundamental property of all data, with
support over distributed systems
DCM approach
Hybrid, explicit relationships as required,
and machine learning where appropriate
Relational, using SQL
queries over fact and
dimension tables of star
schemas
Data columns added and
treated as regular data, with
redundant indexing
Traditional approach
Implicit in encoded business
logic; all linkage done while
ingesting data
Task specialized: relational,
graph-like, key-based with
lightly integrated query
layers
Not really emphasized; geo-
location of data is similar
problem in essence
Silicon Valley approach
Machine learning based
clustering of identifiable
information
Source: http://www.slideshare.net/DavidColebatch/20121029-graph-tointro-to-pacer
For illustrative purposes only.
| DATA CAPITAL MANAGEMENT | 9
TRADEOFF: High Frequency Trading Speed
6. CHALLENGE 2: DATA ANALYSIS
Data by itself is useless. Data is only useful if you apply it – Todd Park
OUTCOME: Non-obvious data-driven investment opportunities
Entity interconnections
Strategy development
Regime determination
Data driven relationships, using
unsupervised machine learning on top of
available information
Adaptive model calibration as
information becomes available
DCM approach
Guided pattern recognition based on
financial specific feature engineering
built by traditional methods
Pre-defined relationships
through sector, region, client
relationships, etc
Static models with ad-hoc
re-calibration (usually batch
based)
Traditional approach
Generative models:
parametric models are fitted
to data
Data driven relationships, using
unsupervised machine learning on
top of connection information
Finance specific, no analog
Silicon Valley approach
Pattern recognition breakthroughs
in complete information games
(Go)
Source: http://cs231n.github.io/convolutional-networks/
http://www.businessinsider.com/magic-mushrooms-change-brain-connections-2014-10
For illustrative purposes only.
| DATA CAPITAL MANAGEMENT | 10
7. CHALLENGE 3 : DATA PROCESSING?
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 6
8. CHALLENGE 4 : NEAR-TERM DATA REGULATION?
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 7
9. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 8
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
10. LESSONS FROM PAST REVOLUTIONS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 9
dcm@datacapitalmanagement.com
It’s time for Asset Management’s Dance with Technological Disruption
• Traditional ”Fundamental Long/Short” managers face challenges and must adapt or fail
• The “Data Economy” enables machines to access information that was previously the exclusive domain of
fundamentally-trained human investors
• “Active Smart-Beta” will accelerate a shift to a world where alpha is a function of ability to rotate exposures to
factors most likely to outperform in the current regime
• Beta allocations over long durations are “good enough” to replicate many existing managers
• Increase in allocator tools to attribute returns post 2008 crisis and relative asset class underperformance since
• As new Betas are exposed and Alphas commoditized; only the strong will thrive:
• Large Diversified “Asset Managers”
• Highly-Differentiated Absolute Return Funds
• Access to new Distributed Technologies & advances in Artificial Intelligence have altered the barriers to entry:
2011 2014 2015Year Founded: 2015
11. ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 10
Suggestions for Scientists in the Data Economy
• Consistent Absolute Returns Requires a Regime Aware Approach
• Machine Learning is better-suited for Regime-aware investing than Humans
• Machine Learning requires new Approaches
• Technological approaches
• Mathematical approaches
• Human approaches
• Scientists will make Artificial Generalized Intelligence a Reality
• Capturing the “Data Economy” opportunity requires:
• New frameworks for knowledge sharing
• Declining costs of compute power
• Transfer Learning to overcome catastrophic forgetting
• “Fair” Access to Data
dcm@datacapitalmanagement.com#GotSkills?
12. ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
| DATA CAPITAL MANAGEMENT | 9
Fat FileTall File
“Smart-
Beta”
,
“Big
Data”
13. ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 12
dcm@datacapitalmanagement.com#GotSkills?
14. ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 13
https://www.ssga.com/investment-topics/risk-management/Optimizing-Asset-Allocations-to-Market-Regimes.pdf 13
Generalized Artificial Intelligence that outperforms the best human investors over any duration
15. ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
| DATA CAPITAL MANAGEMENT | 9
Optimal Error (Bayesian Rate): 75%
• Human Level: 57%
• Training Set: 73%:
• Validation: 72%
• Test: 69%
Train Validation Test
Import Learning_algorithm as Awesome
Duration = {[x[0],,,x[k]]}
Win_periods = {}
Win_Loss = {}
Transaction_cost = h
df = LOTS_of_Data_Factors
Win_periods[x[0]…x[k]] = df[df[‘returns_Duration[k]’]=>transaction cost] for k in Duration]
Win_Loss[x[0]…x[k]] = [[len(Win_periods[0…k]) / len(df)] for k in Duration]
LifeofCodingOnTheBeach = Awesome.DeepLearning.CapitalMarketsTerminator[[df], [Win_Loss]]
16. ARTIFICIAL GENERAL INTELLIGENCE (AGI) AND THE FUTURE OF INVESTING
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 15
AGI + Data Economy enables investment across multiple company cycles
Positive
Momentum
Negative
Momentum
==+
ALPHA VIA ARTIFICIAL GENERALIZED INTELLIGENCE
17. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 16
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
20. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 19
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
25. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 24
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING WORKS WE’VE ALL SEEN IT!!
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
26. | DATA CAPITAL MANAGEMENT | 9
Training Error High?
Bigger Model / More
Data / Train Longer /
New Model
Architecture
Train-Validation Error
High?
More Data
Regularization New
Model Tuning
Validation error high?
More Data similar to
test
Data synthesis
New architecture
Test Set Error High Overfit Dev-Set:
More Dev Data
Better Labels
Error Analysis
Train
Training-
Dev
Dev-
Validation
Test
BUT MACHINE LEARNING WORKS; WE HAVE ALL SEEN IT!
Optimal Error (Bayesian Rate): ??
• Human Level: 57%
• Training Set: 73%:
• Validation: 67%
• Test: 52%
27. BUT MACHINE LEARNING WORKS; WE HAVE ALL SEEN IT!
| DATA CAPITAL MANAGEMENT | 12
Source: Y LeCun; MA Ranzato:
Shallow Depth Approaches Deep Depth Approaches
Asynchronous Learning
Hyper Paramaters
Simulations
Synthetic Data
Optimal Error (Bayesian Rate): ??
• Human Level: 57%
• Training Set: 73%:
• Validation: 72%
• Test: 69%
29. BUT MACHINE LEARNING WORKS; WE HAVE ALL SEEN IT!
| DATA CAPITAL MANAGEMENT | 9
Answer = [[0,1],[[0,,,k]]
https://www.slideshare.net/perone/deep-learning-convolutional-neural-networks
30. | DATA CAPITAL MANAGEMENT | 9
BUT MACHINE LEARNING WORKS; WE HAVE ALL SEEN IT!
Asynchronous Learning
Hyper Paramaters
Simulations
Synthetic Data
=
Lots of Compute and
Data Transfer!
31. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 30
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
32. | DATA CAPITAL MANAGEMENT | 31
• Long History of Objective Function (price returns)
• Short History of Clean Explanatory “Big Data” Variables
• Sequential Learning on BiTemporal Data Problem
• Never see the exact same combination of paramaters more than once
WHAT MAKES FINANCE SO DIFFERENT FOR MACHINE LEARNING?
Answer = [[0,1],[[0,,,k]]
34. NEW SOLUTIONS…. BUT CORE LIMITATION… F OR ASSET MANAGEMENT
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 33
“The ability to learn tasks in a sequential fashion is crucial to the development of artificial
[Generalized] intelligence. Neural networks are not, in general, capable of this and it has
been widely thought that catastrophic forgetting is an inevitable feature of connectionist
models” – Google Deepmind
PROGRESSIVE NEURAL NETWORKS AND CATASTROPHIC FORGETTING
35. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 34
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
36. Predict Return based upon
Shallow Network Learning
Predict Epsilon based upon
Deep Network Learning
| DATA CAPITAL MANAGEMENT | 35
SCALABLE AP P ROACHES F OR REGIME AWARE INVESTING
Focus on Specific Subsets of the problem:
37. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 36
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
38. SEEK TO UNDERSTAND THE INTERMEDIATE REPRESENTATIONS
| DATA CAPITAL MANAGEMENT | 12
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
40. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 39
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
41. | DATA CAPITAL MANAGEMENT | 9
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
42. | DATA CAPITAL MANAGEMENT | 9
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
43. | DATA CAPITAL MANAGEMENT | 9
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
44. | DATA CAPITAL MANAGEMENT | 9
Source: Deutsche Bank
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
45. | DATA CAPITAL MANAGEMENT | 9
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
46. | DATA CAPITAL MANAGEMENT | 9
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
47. TABLE OF CONTENTS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 46
RECAP: QUANTCON 2016 – LESSONS FROM THE INDUSTRIAL REVOLUTION
QUANTCON 2017 – IN PURSUIT OF VIAARTIFICIAL GENERALIZED INTELLIGENCE
WHAT IS {‘MACHINE_LEARNING’, ‘ARTIFICIAL_INTELLIGENCE, ‘DEEP_LEARNING’}
MACHINE LEARNING CAN DO THAT!!! ...RIGHT?
NEW SOLUTIONS; BUT CORE LIMITATION… FOR ASSET MANAGEMENT
WHERE SHOULD SCIENTISTS FOCUS OUR RESEARCH?`
48. SCALABLE AP P ROACHES F OR REGIME AWARE INVESTING
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 47
Source: Google Images
For illustrative purposes only. Back test results are not indicative of future returns. 47
49. Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 48
Source: Google Images
For illustrative purposes only. Back test results are not indicative of future returns. 48
Focus on Progressive Neural Networks via Transfer Learning:
SCALABLE APPROACHES FOR REGIME AWARE INVESTING
50. SCALABLE AP P ROACHES F OR REGIME AWARE INVESTING
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 49
Source: Google Images
For illustrative purposes only. Back test results are not indicative of future returns. 49
51. SCALABLE AP P ROACHES F OR REGIME AWARE INVESTING
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 50
Source: Google Images
For illustrative purposes only. Back test results are not indicative of future returns. 50
52. LESSONS FROM PAST REVOLUTIONS
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 51
dcm@datacapitalmanagement.com
It’s time for Asset Management’s Dance with Technological Disruption
• Traditional ”Fundamental Long/Short” managers face challenges and must adapt or fail
• The “Data Economy” enables machines to access information that was previously the exclusive domain of
fundamentally-trained human investors
• “Active Smart-Beta” will accelerate a shift to a world where alpha is a function of ability to rotate exposures to
factors most likely to outperform in the current regime
• Beta allocations over long durations are “good enough” to replicate many existing managers
• Increase in allocator tools to attribute returns post 2008 crisis and relative asset class underperformance since
• As new Betas are exposed and Alphas commoditized; only the strong will thrive:
• Large Diversified “Asset Managers”
• Highly-Differentiated Absolute Return Funds
• Access to new Distributed Technologies & advances in Artificial Intelligence have altered the barriers to entry:
2011 2014 2015Year Founded: 2015
53. SKY NET HAS NOT BEEN BORNE… YET… BUT WE KNOW WHAT
THE DAY WILL LOOK LIKE WHEN IT ARRIVES
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 52
Monday, November 14, 2016
HFM US Hedge Fund Technology Leaders Summit 2016
# Gotskill
dcm@datacapitalmanagement.com
54. LESSONS FROM THE INDUSTRIAL REVOLUTION
Extremely Confidential. Not for Public Distribution. | DATA CAPITAL MANAGEMENT | 53
Got API?
dcm@datacapitalmanagement.com
For those with the Skill and Will
DCM@datacapitalmanagement.com