https://quspeakerseries9.splashthat.com/
Lecture 2: Ben Steiner
In this talk we will discuss the challenges of Deep learning and focus on the key aspects of Model Risk Management for Deep Learning and Alpha Strategies
Unlocking Exploration: Self-Motivated Agents Thrive on Memory-Driven CuriosityHung Le
Despite remarkable successes in various domains such as robotics and games, Reinforcement Learning (RL) still struggles with exploration inefficiency. For example, in hard Atari games, state-of-the-art agents often require billions of trial actions, equivalent to years of practice, while a moderately skilled human player can achieve the same score in just a few hours of play. This contrast emerges from the difference in exploration strategies between humans, leveraging memory, intuition and experience, and current RL agents, primarily relying on random trials and errors. This tutorial reviews recent advances in enhancing RL exploration efficiency through intrinsic motivation or curiosity, allowing agents to navigate environments without external rewards. Unlike previous surveys, we analyze intrinsic motivation through a memory-centric perspective, drawing parallels between human and agent curiosity, and providing a memory-driven taxonomy of intrinsic motivation approaches.
The talk consists of three main parts. Part A provides a brief introduction to RL basics, delves into the historical context of the explore-exploit dilemma, and raises the challenge of exploration inefficiency. In Part B, we present a taxonomy of self-motivated agents leveraging deliberate, RAM-like, and replay memory models to compute surprise, novelty, and goal, respectively. Part C explores advanced topics, presenting recent methods using language models and causality for exploration. Whenever possible, case studies and hands-on coding demonstrations. will be presented.
Comparing adaptive management and real options approaches: slides and pre-printiadine Chades
Adaptive management and real options approaches for sequential decisions making have undergone significant evolution over the last two decades. Both approaches are based on stochastic optimal control and Markov decision processes. They evolved independently from each other and their developments were motivated by different needs.
Adaptive management was specifically developed to handle decision problems with imperfect knowledge of the dynamics of the system, and is known as ‘learning by doing’. On the other hand, real options analysis was introduced specifically to value the flexibility to change actions over time in response to the evolution of uncertainty, and represents both optimal sequential decisions under uncertainty and a capital budgeting methodology. Because of these different purposes, different analytic and numerical methods were developed to solve these problems.
In our recent MODSIM paper (Chades et al, 2015), we review and compare the concepts, applications and recent advances in the numerical and analytic techniques in adaptive management and real options methodologies. A large body of knowledge accumulated in both fields makes a comprehensive review impractical in the context of this paper. Therefore, our review focuses on the most recent developments, with the purpose to identify potential areas of new developments that would address new challenges in the environmental decision area.
I. Chadès, T. Tarnopolskaya, S. Dunstall, J.Rhodes, and A.Tulloch (2015). A comparison of adaptive management and real options approaches for environmental decisions under uncertainty. In Weber, T., McPhee, M.J. and Anderssen, R.S. (eds) MODSIM2015, 21st International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, December 2015. ISBN: 978-0-9872143-5-5. (pre-print)
SBA Live Academy: Software Security – Towards a Mature Lifecycle and DevSecOp...SBA Research
Target Audience: Everyone involved in software development (developers, team leaders, CISOs in software-oriented companies)
Focus: technical
Talk language: English
Abstract
*********
Let’s face it: There is no such thing as a big-bang launch any more. We all want to be agile and react quickly to the wishes and demands of our customers in software development. The downside of this approach is that security has a hard time keeping pace, thereby often being completely neglected. That’s why we need to bridge the gap between security and agility. In this talk, we’ll have a look at how security can become an integral part of the development process, and more than just a penetration test at the end. We’ll see how we can overcome immediate pain and get strategic focus in software security.
About the Speaker:
*********************
Thomas Konrad is Principal Security Consultant at SBA Research and has been part of software security team since 2010. He focuses on secure software development, web application security, penetration testing, secure software design, architecture, and process, and trains software development teams in those areas.
Varied encounters with data science (slide share)gilbert.peffer
How does data science relate to traditional scientific and computational approaches? What can we learn about data science pitfalls from these approaches? Is there a role for the social sciences and humanities?
INTE 296 – Assignment 1 Assignment 1 Due Date Februar.docxmariuse18nolet
INTE 296 – Assignment 1
Assignment 1
Due Date: February 3rd, 2015 – Corrections Due: February 17th, 2015 - Material Covered: Lessons 1-9.
Question 1
GlobaTel, a large manufacturer of electrical parts used in cell phone, is about to launch a new product
line. The company psychologist has been asked to administer a Depression, Anxiety, and Stress Test
(DAST) to determine if employees are able to handle the transition to the new line, or if special training
will be needed. A sample of 20 employees is randomly selected to complete the DAST test and their scores
are listed below. The DAST scale ranges from 0 (no anxiety) to 25 (high anxiety).
Employee DAST Score Employee DAST Score
1 0 11 23
2 4 12 12
3 7 13 9
4 1 14 4
5 19 15 0
6 9 16 0
7 12 17 3
8 8 18 2
9 1 19 6
10 5 20 2
a) Calculate the measures of central tendency for the results of the DAST:
i. Mean
ii. Median
iii. Mode
b) Calculate the measures of variability for the results of the DAST:
i. Range
ii. Standard Deviation
c) Identify the measures of position of the DAST:
i. P15
ii. P66
iii. the 5-number summary
INTE 296 – Assignment 1
Question 2
Christy is an avid golf player. Each summer she tries to improve her game by changing golf clubs, trying
new techniques, and getting tips from local pros. After each round that she plays at her favourite golf
course, Christy records the scores into a database so that she can compile her annual statistics. Use the
scores recorded in the graph below to help Christy calculate her statistics for this past season (Note: In
golf, a lower score is better).
a) Calculate the measures of central tendency for Christy’s golf scores for this past season:
i. Mean
ii. Median
iii. Mode
b) Calculate the measures of variability and position for Christy’s golf scores for this past season:
i. Standard Deviation
ii. IQR
iii. P45
iv. P90
c) The reason that Christy records her scores is to determine if she is improving her golf game. What
three suggestions can you give Christy to help her determine if her game is indeed improving?
Your recommendations could also include suggestions about how to use the data she has
collected, other variables she could collect in addition to her scores, and/or changes to the
methodology of her study.
0
2
4
6
8
10
12
14
16
80 81 82 83 84 85 86 87 88 89 90 91 92
F
re
q
u
e
n
cy
Score
Christy's Golf Scores
INTE 296 – Assignment 1
Question 3
The Pinkerton Detective Agency, now called Pinkerton Government Services (PGS), was originally founded
in 1850 when Allen Pinkerton, a coppersmith, helped arrest some counterfeiters in Dundee, U.S.A. Today,
their 1800 agents offer more protective services than investigative services. The table below describes
the agents in terms of their department and speciality, as well as their geographical area of work (U.S.A.,
Canada, or Puerto Rico).
Department Speciality.
Autonomous Driving and Reinforcement Learning - an IntroductionMichael Bosello
The driving problem and the two approaches to managing it: single task handling vs end-to-end.
Basic concepts of theoretical Reinforcement Learning: the environment, MDPs, observability, learning a policy, TD-learning, on-policy (SARSA), off-policy (Q-learning).
A concrete control method: DQN. Practical issues and solutions
Uniform Legal Framework for AI: The EU AI Act establishes a uniform legal framework for the development, marketing, and use of artificial intelligence systems within the EU, aimed at promoting trustworthy and human-centric AI while ensuring a high level of health, safety, and fundamental rights protection.
Risk-Based Approach: The regulation adopts a risk-based approach, classifying AI systems based on the level of risk they pose, from minimal to unacceptable risk, with stringent requirements for high-risk AI systems, particularly those impacting health, safety, and fundamental rights.
Prohibitions for Certain AI Practices: Unacceptable risk practices, such as manipulative social scoring and real-time biometric identification in public spaces without justification, are prohibited to protect individual rights and freedoms.
Mandatory Requirements for High-Risk AI Systems: High-risk AI systems must comply with mandatory requirements before they can be marketed, put into service, or used within the EU. These requirements include transparency, data governance, technical documentation, and human oversight to ensure safety and compliance with fundamental rights.
Conformity Assessment and Compliance: Providers of high-risk AI systems must undergo a conformity assessment procedure to demonstrate compliance with the mandatory requirements. This includes maintaining technical documentation and conducting risk management activities.
Transparency Obligations: AI systems must be transparent, providing users with information about the AI system's capabilities, limitations, and the purpose for which it is intended, ensuring informed use of AI technologies.
Market Surveillance: The EU AI Act establishes mechanisms for market surveillance to monitor and enforce compliance, with the European Artificial Intelligence Board (EAIB) playing a central role in coordinating activities across member states.
Protection of Fundamental Rights: The Act emphasizes the protection of fundamental rights, including privacy, non-discrimination, and consumer rights, with specific provisions to safeguard these rights in the context of AI use.
Innovation and SME Support: The regulation aims to foster innovation and support small and medium-sized enterprises (SMEs) through regulatory sandboxes and by reducing administrative burdens for low and minimal risk AI applications.
Global Impact and Alignment: While the EU AI Act directly applies to the EU market, its global impact is significant, influencing international standards and practices in AI development and use. Financial industry professionals worldwide should be aware of these regulations as they may affect global operations and international collaborations.
The financial industry is witnessing an emerging trend of Large Language Models (LLMs) applications to improve operational efficiency. This article, based on a round table discussion hosted by TruEra and QuantUniversity in New York in May 2023, explores the potential use cases of LLMs in financial institutions (FIs), the risks to consider, approaches to manage these risks, and the implications for people, skills, and ways of working. Frontline personnel from Data and Analytics/AI teams, Model Risk, Data Management, and other roles from fifteen financial institutions devoted over two hours to discussing the LLM opportunities within their industry, as well as strategies for mitigating associated risks.
The discussions revealed a preference for discriminative use cases over generative ones, with a focus on information retrieval and operational automation. The necessity for a human-in-the-loop was emphasized, along with a detailed discourse on risks and their mitigation.
More Related Content
Similar to Model Risk Management for Deep Learning and Investment Strategies
Unlocking Exploration: Self-Motivated Agents Thrive on Memory-Driven CuriosityHung Le
Despite remarkable successes in various domains such as robotics and games, Reinforcement Learning (RL) still struggles with exploration inefficiency. For example, in hard Atari games, state-of-the-art agents often require billions of trial actions, equivalent to years of practice, while a moderately skilled human player can achieve the same score in just a few hours of play. This contrast emerges from the difference in exploration strategies between humans, leveraging memory, intuition and experience, and current RL agents, primarily relying on random trials and errors. This tutorial reviews recent advances in enhancing RL exploration efficiency through intrinsic motivation or curiosity, allowing agents to navigate environments without external rewards. Unlike previous surveys, we analyze intrinsic motivation through a memory-centric perspective, drawing parallels between human and agent curiosity, and providing a memory-driven taxonomy of intrinsic motivation approaches.
The talk consists of three main parts. Part A provides a brief introduction to RL basics, delves into the historical context of the explore-exploit dilemma, and raises the challenge of exploration inefficiency. In Part B, we present a taxonomy of self-motivated agents leveraging deliberate, RAM-like, and replay memory models to compute surprise, novelty, and goal, respectively. Part C explores advanced topics, presenting recent methods using language models and causality for exploration. Whenever possible, case studies and hands-on coding demonstrations. will be presented.
Comparing adaptive management and real options approaches: slides and pre-printiadine Chades
Adaptive management and real options approaches for sequential decisions making have undergone significant evolution over the last two decades. Both approaches are based on stochastic optimal control and Markov decision processes. They evolved independently from each other and their developments were motivated by different needs.
Adaptive management was specifically developed to handle decision problems with imperfect knowledge of the dynamics of the system, and is known as ‘learning by doing’. On the other hand, real options analysis was introduced specifically to value the flexibility to change actions over time in response to the evolution of uncertainty, and represents both optimal sequential decisions under uncertainty and a capital budgeting methodology. Because of these different purposes, different analytic and numerical methods were developed to solve these problems.
In our recent MODSIM paper (Chades et al, 2015), we review and compare the concepts, applications and recent advances in the numerical and analytic techniques in adaptive management and real options methodologies. A large body of knowledge accumulated in both fields makes a comprehensive review impractical in the context of this paper. Therefore, our review focuses on the most recent developments, with the purpose to identify potential areas of new developments that would address new challenges in the environmental decision area.
I. Chadès, T. Tarnopolskaya, S. Dunstall, J.Rhodes, and A.Tulloch (2015). A comparison of adaptive management and real options approaches for environmental decisions under uncertainty. In Weber, T., McPhee, M.J. and Anderssen, R.S. (eds) MODSIM2015, 21st International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, December 2015. ISBN: 978-0-9872143-5-5. (pre-print)
SBA Live Academy: Software Security – Towards a Mature Lifecycle and DevSecOp...SBA Research
Target Audience: Everyone involved in software development (developers, team leaders, CISOs in software-oriented companies)
Focus: technical
Talk language: English
Abstract
*********
Let’s face it: There is no such thing as a big-bang launch any more. We all want to be agile and react quickly to the wishes and demands of our customers in software development. The downside of this approach is that security has a hard time keeping pace, thereby often being completely neglected. That’s why we need to bridge the gap between security and agility. In this talk, we’ll have a look at how security can become an integral part of the development process, and more than just a penetration test at the end. We’ll see how we can overcome immediate pain and get strategic focus in software security.
About the Speaker:
*********************
Thomas Konrad is Principal Security Consultant at SBA Research and has been part of software security team since 2010. He focuses on secure software development, web application security, penetration testing, secure software design, architecture, and process, and trains software development teams in those areas.
Varied encounters with data science (slide share)gilbert.peffer
How does data science relate to traditional scientific and computational approaches? What can we learn about data science pitfalls from these approaches? Is there a role for the social sciences and humanities?
INTE 296 – Assignment 1 Assignment 1 Due Date Februar.docxmariuse18nolet
INTE 296 – Assignment 1
Assignment 1
Due Date: February 3rd, 2015 – Corrections Due: February 17th, 2015 - Material Covered: Lessons 1-9.
Question 1
GlobaTel, a large manufacturer of electrical parts used in cell phone, is about to launch a new product
line. The company psychologist has been asked to administer a Depression, Anxiety, and Stress Test
(DAST) to determine if employees are able to handle the transition to the new line, or if special training
will be needed. A sample of 20 employees is randomly selected to complete the DAST test and their scores
are listed below. The DAST scale ranges from 0 (no anxiety) to 25 (high anxiety).
Employee DAST Score Employee DAST Score
1 0 11 23
2 4 12 12
3 7 13 9
4 1 14 4
5 19 15 0
6 9 16 0
7 12 17 3
8 8 18 2
9 1 19 6
10 5 20 2
a) Calculate the measures of central tendency for the results of the DAST:
i. Mean
ii. Median
iii. Mode
b) Calculate the measures of variability for the results of the DAST:
i. Range
ii. Standard Deviation
c) Identify the measures of position of the DAST:
i. P15
ii. P66
iii. the 5-number summary
INTE 296 – Assignment 1
Question 2
Christy is an avid golf player. Each summer she tries to improve her game by changing golf clubs, trying
new techniques, and getting tips from local pros. After each round that she plays at her favourite golf
course, Christy records the scores into a database so that she can compile her annual statistics. Use the
scores recorded in the graph below to help Christy calculate her statistics for this past season (Note: In
golf, a lower score is better).
a) Calculate the measures of central tendency for Christy’s golf scores for this past season:
i. Mean
ii. Median
iii. Mode
b) Calculate the measures of variability and position for Christy’s golf scores for this past season:
i. Standard Deviation
ii. IQR
iii. P45
iv. P90
c) The reason that Christy records her scores is to determine if she is improving her golf game. What
three suggestions can you give Christy to help her determine if her game is indeed improving?
Your recommendations could also include suggestions about how to use the data she has
collected, other variables she could collect in addition to her scores, and/or changes to the
methodology of her study.
0
2
4
6
8
10
12
14
16
80 81 82 83 84 85 86 87 88 89 90 91 92
F
re
q
u
e
n
cy
Score
Christy's Golf Scores
INTE 296 – Assignment 1
Question 3
The Pinkerton Detective Agency, now called Pinkerton Government Services (PGS), was originally founded
in 1850 when Allen Pinkerton, a coppersmith, helped arrest some counterfeiters in Dundee, U.S.A. Today,
their 1800 agents offer more protective services than investigative services. The table below describes
the agents in terms of their department and speciality, as well as their geographical area of work (U.S.A.,
Canada, or Puerto Rico).
Department Speciality.
Autonomous Driving and Reinforcement Learning - an IntroductionMichael Bosello
The driving problem and the two approaches to managing it: single task handling vs end-to-end.
Basic concepts of theoretical Reinforcement Learning: the environment, MDPs, observability, learning a policy, TD-learning, on-policy (SARSA), off-policy (Q-learning).
A concrete control method: DQN. Practical issues and solutions
Uniform Legal Framework for AI: The EU AI Act establishes a uniform legal framework for the development, marketing, and use of artificial intelligence systems within the EU, aimed at promoting trustworthy and human-centric AI while ensuring a high level of health, safety, and fundamental rights protection.
Risk-Based Approach: The regulation adopts a risk-based approach, classifying AI systems based on the level of risk they pose, from minimal to unacceptable risk, with stringent requirements for high-risk AI systems, particularly those impacting health, safety, and fundamental rights.
Prohibitions for Certain AI Practices: Unacceptable risk practices, such as manipulative social scoring and real-time biometric identification in public spaces without justification, are prohibited to protect individual rights and freedoms.
Mandatory Requirements for High-Risk AI Systems: High-risk AI systems must comply with mandatory requirements before they can be marketed, put into service, or used within the EU. These requirements include transparency, data governance, technical documentation, and human oversight to ensure safety and compliance with fundamental rights.
Conformity Assessment and Compliance: Providers of high-risk AI systems must undergo a conformity assessment procedure to demonstrate compliance with the mandatory requirements. This includes maintaining technical documentation and conducting risk management activities.
Transparency Obligations: AI systems must be transparent, providing users with information about the AI system's capabilities, limitations, and the purpose for which it is intended, ensuring informed use of AI technologies.
Market Surveillance: The EU AI Act establishes mechanisms for market surveillance to monitor and enforce compliance, with the European Artificial Intelligence Board (EAIB) playing a central role in coordinating activities across member states.
Protection of Fundamental Rights: The Act emphasizes the protection of fundamental rights, including privacy, non-discrimination, and consumer rights, with specific provisions to safeguard these rights in the context of AI use.
Innovation and SME Support: The regulation aims to foster innovation and support small and medium-sized enterprises (SMEs) through regulatory sandboxes and by reducing administrative burdens for low and minimal risk AI applications.
Global Impact and Alignment: While the EU AI Act directly applies to the EU market, its global impact is significant, influencing international standards and practices in AI development and use. Financial industry professionals worldwide should be aware of these regulations as they may affect global operations and international collaborations.
The financial industry is witnessing an emerging trend of Large Language Models (LLMs) applications to improve operational efficiency. This article, based on a round table discussion hosted by TruEra and QuantUniversity in New York in May 2023, explores the potential use cases of LLMs in financial institutions (FIs), the risks to consider, approaches to manage these risks, and the implications for people, skills, and ways of working. Frontline personnel from Data and Analytics/AI teams, Model Risk, Data Management, and other roles from fifteen financial institutions devoted over two hours to discussing the LLM opportunities within their industry, as well as strategies for mitigating associated risks.
The discussions revealed a preference for discriminative use cases over generative ones, with a focus on information retrieval and operational automation. The necessity for a human-in-the-loop was emphasized, along with a detailed discourse on risks and their mitigation.
PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALSQuantUniversity
Join CFA Institute and QuantUniversity for an information session about the upcoming CFA Institute Professional Learning course: Python and Data Science for Investment professionals.
Learn how artificial intelligence (AI) and machine learning are revolutionizing industries — this course will introduce key concepts and illustrate the role of machine learning, data science techniques, and AI through examples and case studies from the investment industry. The presentation uses simple mathematics and basic statistics to provide an intuitive understanding of machine learning, as used by firms, to augment traditional decision making.
https://quforindia.splashthat.com/
Mathematical Finance & Financial Data Science Seminar
AI and machine learning are entering every aspect of our life. Marketing, autonomous driving, personalization, computer vision, finance, wearables, travel are all benefiting from the advances in AI in the last decade. As more and more AI applications are being deployed in enterprises, concerns are growing about potential "AI accidents" and the misuse of AI. With increased complexity, some are questioning whether the models actually work! As the debate about fairness, bias, and privacy grow, there is increased attention to understanding how the models work and whether the models are thoroughly tested and designed to address potential issues.
The area "Responsible AI" is fast emerging and becoming an important aspect of the adoption of machine learning and AI products in the enterprise. Companies are now incorporating formal ethics reviews, model validation exercises, and independent algorithmic auditing to ensure that the adoption of AI is transparent and has gone through formal validation phases.
In this talk, Sri will introduce Algorithmic auditing and discuss why Algorithmic auditing will be a formal process industries using AI will need. Sri will also discuss the emerging risks in the adoption of AI and discuss how QuSandbox, his company is building, will address the emerging needs of formal Algorithmic auditing practices in enterprises.
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...QuantUniversity
Machine Learning: Considerations for Fairly and Transparently Expanding Access to Credit
With Raghu Kulkarni and Steve Dickerson
Recently, machine learning has been used extensively in credit decision making. As ML proliferates the industry, issues of considerations for fair and transparent access to credit decision making is becoming important.
In this talk, Dr.Raghu Kulkarni and Dr.Steven Dickerson from Discover Financial Services will share their experiences at Discover. The talk will include:
- An overview of how ML models are used across financial life cycle
- Practical problems practitioners run into and why explainability and bias detection becomes important.
References:
1- https://www.h2o.ai/resources/white-paper/machine-learning-considerations-for-fairly-and-transparently-expanding-access-to-credit/
2- https://arxiv.org/abs/2011.03156
Seeing what a gan cannot generate: paper reviewQuantUniversity
Seeing what a GAN cannot Generate Paper review: Bau, David et al. “Seeing What a GAN Cannot Generate.” 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (2019): 4501-4510.
Machine Learning in Finance: 10 Things You Need to Know in 2021QuantUniversity
Machine Learning and AI has revolutionized Finance! In the last five years, innovations in computing, technology and business models have created multiple products and services in Fintech prompting organizations to prioritize their data and AI strategies. What will 2021 bring and how should you prepare for it? Join Sri Krishnamurthy,CFA as we kickoff the QuantUniversity’s Winter school 2021. We will introduce you to the upcoming programs and have a masterclass on 10 innovations in AI and ML you need to know in 2021!
Markowitz portfolio optimization is optimal in theory, however, when applied in practice it often fails catastrophically. Usually, this is addressed by various simplifications to increase robustness. In this talk I will make the case that the reason this theory fails in practice is because uncertainty in the parameter estimation is not taken into account. By using Bayesian statistics we can fix Markowitz and retain all its desirable properties while still having a robustness technique that can be easily extended. This talk is geared at intermediate and will give a general introduction to Bayesian modeling using PyMC3 and focus on application and code examples rather than theory.
With Alternative Data becoming more and more popular in the industry, quants are eager to adopt them into their investment processes. However, with a plethora of options, API standards, trying and evaluating datasets is a major hindrance to adoption of datasets.
Join Yaacov, Sri, James and Brad discuss the opportunities, pitfalls and challenges of Alternative Data and its adoption in finance
A Unified Framework for Model Explanation
Ian Covert, University of Washington
Explainable AI is becoming increasingly important, but the field is evolving rapidly and requires better organizing principles to remain manageable for researchers and practitioners. In this talk, Ian will discuss a new paper that unifies a large portion of the literature using a simple idea: simulating feature removal. The new class of "removal-based explanations" describes 20+ existing methods (e.g., LIME, SHAP) and reveals underlying links with psychology, game theory and information theory.
Practical examples will be presented and available on the Qu.Academy site
Reference:
Explaining by Removing: A Unified Framework for Model Explanation
Ian Covert, Scott Lundberg, Su-In Lee
https://arxiv.org/abs/2011.14878
Machine Learning Interpretability -
Self-Explanatory Models: Interpretability, Diagnostics and Simplification
With Agus Sudjianto, Wells Fargo
The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box"models without a sufficient level of transparency and interpretability. It is important to demystify the DNNs with rigorous mathematics and practical tools, especially when they are used for mission-critical applications. This talk aims to unwrap the black box of deep ReLU networks through exact local linear representation, which utilizes the activation pattern and disentangles the complex network into an equivalent set of local linear models (LLMs). We develop a convenient LLM-based toolkit for interpretability, diagnostics, and simplification of a pre-trained deep ReLU network. We propose the local linear profile plot and other visualization methods for interpretation and diagnostics, and an effective merging strategy for network simplification. The proposed methods are demonstrated by simulation examples, benchmark datasets, and a real case study in credit risk assessment. The paper that will be presented in this talk can be found here.
Qu speaker series 14: Synthetic Data Generation in FinanceQuantUniversity
In this master class, Stefan shows how to create synthetic time-series data using generative adversarial networks (GAN). GANs train a generator and a discriminator network in a competitive setting so that the generator learns to produce samples that the discriminator cannot distinguish from a given class of training data. The goal is to yield a generative model capable of producing synthetic samples representative of this class. While most popular with image data, GANs have also been used to generate synthetic time-series data in the medical domain. Subsequent experiments with financial data explored whether GANs can produce alternative price trajectories useful for ML training or strategy backtests.
In 2009 author and motivational speaker Simon Sinek delivered the now-classic TED talk “Start with why”. Viewed by over 28 million people, “Start with Why” is the third most popular TED video of all time and it teaches us that great leaders and companies inspire us to take action by focusing on the WHY over the “what” or the “how”. In this talk we’ll ask how applied data and computational scientists can use the power of WHY to frame problems, inspire others, and give them answers to business questions they might never think of asking.
Bio
Jessica Stauth is a Managing Director in Fidelity Labs, an internal startup incubator with a mission to create new fintech businesses that drive growth for the firm. Dr. Stauth previously held roles as Managing Director of Portfolio Management, Research, and Trading at Quantopian, a crowd-sourced systematic hedge fund based in Boston, Director of Quant Product Strategy for Thomson Reuters (now Refinitiv), and as a Senior Quant Researcher at the StarMine Corporation, where she built global stock selection models including the design and implementation of the StarMine Short Interest model. Dr. Stauth holds a PhD in Biophysics from UC Berkeley, where her research focused on computational neuroscience.
Francesca Gottschalk - How can education support child empowerment.pptxEduSkills OECD
Francesca Gottschalk from the OECD’s Centre for Educational Research and Innovation presents at the Ask an Expert Webinar: How can education support child empowerment?
How to Make a Field invisible in Odoo 17Celine George
It is possible to hide or invisible some fields in odoo. Commonly using “invisible” attribute in the field definition to invisible the fields. This slide will show how to make a field invisible in odoo 17.
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
Biological screening of herbal drugs: Introduction and Need for
Phyto-Pharmacological Screening, New Strategies for evaluating
Natural Products, In vitro evaluation techniques for Antioxidants, Antimicrobial and Anticancer drugs. In vivo evaluation techniques
for Anti-inflammatory, Antiulcer, Anticancer, Wound healing, Antidiabetic, Hepatoprotective, Cardio protective, Diuretics and
Antifertility, Toxicity studies as per OECD guidelines
Synthetic Fiber Construction in lab .pptxPavel ( NSTU)
Synthetic fiber production is a fascinating and complex field that blends chemistry, engineering, and environmental science. By understanding these aspects, students can gain a comprehensive view of synthetic fiber production, its impact on society and the environment, and the potential for future innovations. Synthetic fibers play a crucial role in modern society, impacting various aspects of daily life, industry, and the environment. ynthetic fibers are integral to modern life, offering a range of benefits from cost-effectiveness and versatility to innovative applications and performance characteristics. While they pose environmental challenges, ongoing research and development aim to create more sustainable and eco-friendly alternatives. Understanding the importance of synthetic fibers helps in appreciating their role in the economy, industry, and daily life, while also emphasizing the need for sustainable practices and innovation.
A Strategic Approach: GenAI in EducationPeter Windle
Artificial Intelligence (AI) technologies such as Generative AI, Image Generators and Large Language Models have had a dramatic impact on teaching, learning and assessment over the past 18 months. The most immediate threat AI posed was to Academic Integrity with Higher Education Institutes (HEIs) focusing their efforts on combating the use of GenAI in assessment. Guidelines were developed for staff and students, policies put in place too. Innovative educators have forged paths in the use of Generative AI for teaching, learning and assessments leading to pockets of transformation springing up across HEIs, often with little or no top-down guidance, support or direction.
This Gasta posits a strategic approach to integrating AI into HEIs to prepare staff, students and the curriculum for an evolving world and workplace. We will highlight the advantages of working with these technologies beyond the realm of teaching, learning and assessment by considering prompt engineering skills, industry impact, curriculum changes, and the need for staff upskilling. In contrast, not engaging strategically with Generative AI poses risks, including falling behind peers, missed opportunities and failing to ensure our graduates remain employable. The rapid evolution of AI technologies necessitates a proactive and strategic approach if we are to remain relevant.
Safalta Digital marketing institute in Noida, provide complete applications that encompass a huge range of virtual advertising and marketing additives, which includes search engine optimization, virtual communication advertising, pay-per-click on marketing, content material advertising, internet analytics, and greater. These university courses are designed for students who possess a comprehensive understanding of virtual marketing strategies and attributes.Safalta Digital Marketing Institute in Noida is a first choice for young individuals or students who are looking to start their careers in the field of digital advertising. The institute gives specialized courses designed and certification.
for beginners, providing thorough training in areas such as SEO, digital communication marketing, and PPC training in Noida. After finishing the program, students receive the certifications recognised by top different universitie, setting a strong foundation for a successful career in digital marketing.
Unit 8 - Information and Communication Technology (Paper I).pdfThiyagu K
This slides describes the basic concepts of ICT, basics of Email, Emerging Technology and Digital Initiatives in Education. This presentations aligns with the UGC Paper I syllabus.
Normal Labour/ Stages of Labour/ Mechanism of LabourWasim Ak
Normal labor is also termed spontaneous labor, defined as the natural physiological process through which the fetus, placenta, and membranes are expelled from the uterus through the birth canal at term (37 to 42 weeks
Normal Labour/ Stages of Labour/ Mechanism of Labour
Model Risk Management for Deep Learning and Investment Strategies
1. QU Summer School - Ben Steiner - Sept 2020
Ben Steiner
BNP Paribas Asset Management
Adjunct Lecturer, Columbia University
The views expressed in this presentation are those of the speaker and not his current employer
Model Risk Management for
Deep Learning and
Investment Strategies
2. QU Summer School - Ben Steiner - Sept 2020
Agenda
1. Introductory concepts
a. What is model risk management?
b. Machine Learning for investment strategies
c. Introduction to Deep Learning
2. Challenges of Deep Learning
a. Non-stationarity
b. Interpretation
c. Learning what we already know
3. Model Risk Management for Deep Learning investment strategies
a. Backtest evaluation
b. Ongoing monitoring
MRM FOR DL
CHALLENGES
INTRODUCTION
3
3. QU Summer School - Ben Steiner - Sept 2020
Agenda
1. Introductory concepts
a. What is model risk management?
b. Machine Learning for investment strategies
c. Introduction to Deep Learning
2. Challenges of Deep Learning
a. Non-stationarity
b. Interpretation
c. Learning what we already know
3. Model Risk Management for Deep Learning investment strategies
a. Backtest evaluation
b. Ongoing monitoring
MRM FOR DL
CHALLENGES
INTRODUCTION
4
4. QU Summer School - Ben Steiner - Sept 2020
Definitions
A Model is a simplification of the real world into mathematical equations to
forecast some future behavior.
Model Risk comes from either incorrect models (fundamental errors) or models
being misapplied (incorrect or inappropriate usage).
Risk Management is the process of identifying, analysing and controlling
uncertainty around objectives.
Model Risk Management is the understanding, analysing and controlling the risk
inherent in using models.
1. Conceptual Soundness
2. Implementation Validation
3. Ongoing Monitoring
MRM FOR DL
CHALLENGES
INTRODUCTION
5
5. QU Summer School - Ben Steiner - Sept 2020
MRM FOR DL
CHALLENGES
INTRODUCTION
6
6. QU Summer School - Ben Steiner - Sept 2020
Definitions
Machine Learning uses algorithms to learn from data without relying on rules-
based programming
Deep Learning maps inputs to outputs using multiple layers of nonlinear
processing units
MRM FOR DL
CHALLENGES
INTRODUCTION
7
7. QU Summer School - Ben Steiner - Sept 2020
Image credit: Shane Conway, Kepos Capital, SQA Fuzzy Day conference 2017
MRM FOR DL
CHALLENGES
INTRODUCTION
8
8. QU Summer School - Ben Steiner - Sept 2020
Is Machine Learning still “a model”? MRM FOR DL
CHALLENGES
INTRODUCTION
9
9. QU Summer School - Ben Steiner - Sept 2020
Input layer: features (or attributes)
Hidden layers: Bias and weights
Output layer: target variables (or responses)
Deep Learning basics
Input layer
Hidden layer 1
Output layer
Hidden layer 2
Married
Single
Age
Income
Employment
Example: Arno Candel, H20.ai
MRM FOR DL
CHALLENGES
INTRODUCTION
10
10. QU Summer School - Ben Steiner - Sept 2020
Neurons activate each other via weighted sums
y1 = f(( x1u1 + x2u2 + x3u3 ) + b1 )
Non-linear activation function tanh: or rectilinear:
Deep Learning basics
Input layer
Hidden layer 1
Hidden layer 2
Output layer
x1
x2
x3
y1u1
u2
u3
MRM FOR DL
CHALLENGES
INTRODUCTION
11
-1
1
0
11. QU Summer School - Ben Steiner - Sept 2020
Neurons activate each other via weighted sums
z3 = f(( y1v1 + y2v2 + y3v3 + y4v4 ) + c3 )
Non-linear activation function tanh: or rectilinear:
Deep Learning basics
Input layer
Hidden layer 1
Hidden layer 2
Output layer
y1
v1
v2
v3
z3
y2
y3
y4
v4
MRM FOR DL
CHALLENGES
INTRODUCTION
12
-1
1
0
12. QU Summer School - Ben Steiner - Sept 2020
Deep Learning basics
Neurons activate each other via weighted sums
p2 = f(( z1w1 + z2w2 + z3w3 ) + d2 )
Non-linear activation function: softmax
Input layer
Hidden layer 1
Hidden layer 2
Output layer
w1
w2 p2
w3
z3
z2
z1
p(up)
p(down)
p1
MRM FOR DL
CHALLENGES
INTRODUCTION
13
13. QU Summer School - Ben Steiner - Sept 2020
Agenda
1. Introductory concepts
a. What is model risk management?
b. Investment strategy: problem statement & objective
c. Introduction to Deep Learning
2. Challenges of Deep Learning
a. Non-stationarity
b. Interpretation
c. Learning what we already know
3. Model Risk Management for Deep Learning investment strategies
a. Backtest evaluation
b. Ongoing monitoring
MRM FOR DL
CHALLENGES
INTRODUCTION
14
14. QU Summer School - Ben Steiner - Sept 2020
“A model may be reasonable, but the
world itself may be unstable. What’s a
good model today may be inappropriate
tomorrow”
Emanuel Derman, 1996, GS research paper on model risk
MRM FOR DL
CHALLENGES
INTRODUCTION
15
15. QU Summer School - Ben Steiner - Sept 2020
Challenge 1: Non-Stationarity
Stationarity (or Nonstationarity) is an
assumption of a data generating model and not
a property of observed data.
A single realization from a stationary stochastic
process can appear indistinguishable from a
nonstationary deterministic process
‘Change’ is in the timeframe of the beholder
16
16. QU Summer School - Ben Steiner - Sept 2020
Challenge 1: Non-Stationarity
One challenge, many names:
● Concept Drift
● Covariate Shift
● Dataset shift
CONCEPT DRIFT
When the statistical properties of the target
variable, which the model is trying to predict,
change over time in unforeseen ways.
The unforeseen substitution of one data source
𝐒1 (with underlying probability distribution 𝚷S1),
with another source 𝐒2 (with distribution 𝚷S2)
MRM FOR DL
CHALLENGES
INTRODUCTION
17
● Nonstationarity
● Source component shift
● Temporal evolution
Not Concept Drift
17. QU Summer School - Ben Steiner - Sept 2020
Different Types of Concept Drift
S2
S1
S2
S1
S2
S1
S2
S1
S2
S1
S2
S1
MRM FOR DL
CHALLENGES
INTRODUCTION
18Images derived from Dariusz Brzeziński, Mining Data Streams with Concept Drift, 2010
18. QU Summer School - Ben Steiner - Sept 2020
MRM FOR DL
CHALLENGES
INTRODUCTION
19
19. QU Summer School - Ben Steiner - Sept 2020
Challenge 2: Interpretation
Why do we need interpretation?
What do we mean by interpretability?
Zachary Lipton,UCSD, 2016 ICML Workshop on Human Interpretability in Machine Learning
● Causality
● Comprehension
● Decomposition
● Algorithmic transparency
● Post-hoc interpretation
MRM FOR DL
CHALLENGES
INTRODUCTION
20
20. QU Summer School - Ben Steiner - Sept 2020
Challenge 2: Look at the weights!
4 input features: target classification::
Network with 2 hidden layers of 3 & 2 neurons
Weight = thickness
http://playground.tensorflow.org
MRM FOR DL
CHALLENGES
INTRODUCTION
22
21. QU Summer School - Ben Steiner - Sept 2020
Good news: can’t be both!
Solution:
Step 1: Traditional multifactor model (with known factors)
Step 2: Deep Learning (with residuals from step 1)
Learning, but
nothing new
Interpretation
challenge
Challenge 3: Learning what we already know MRM FOR DL
CHALLENGES
INTRODUCTION
23
22. QU Summer School - Ben Steiner - Sept 2020
Challenge 3: Multifactor models MRM FOR DL
CHALLENGES
INTRODUCTION
24
23. QU Summer School - Ben Steiner - Sept 2020
Agenda
1. Introductory concepts
a. What is model risk management?
b. Machine Learning for investment strategies
c. Introduction to Deep Learning
2. Challenges of Deep Learning
a. Non-stationarity
b. Interpretation
c. Learning what we already know
3. Model Risk Management for Deep Learning investment strategies
a. Backtest evaluation
b. Ongoing monitoring
MRM FOR DL
CHALLENGES
INTRODUCTION
25
24. QU Summer School - Ben Steiner - Sept 2020
“The road to
hedge fund failure
is littered with
good backtests”
MRM FOR DL
CHALLENGES
INTRODUCTION
26
25. QU Summer School - Ben Steiner - Sept 2020
Conceptual Soundness = Backtest Evaluation
● Return per unit risk per unit capital required
● Alpha Decay
● Temporal P&L
● Strategy Correlation
● Sensitivity Analysis
● Random Markets
MRM FOR DL
CHALLENGES
INTRODUCTION
27
26. QU Summer School - Ben Steiner - Sept 2020
Evaluation 1: Alpha Decay
Alpha term structure
Cost of implementation delay
Dictates execution speed
Too fast = alpha not capturable
Alpha not declining at all raises
suspicion
Declining alpha indicates profit
from trades at t=0.
✓
✗
!?
MRM FOR DL
CHALLENGES
INTRODUCTION
28
27. QU Summer School - Ben Steiner - Sept 2020 29
Evaluation 2: Temporal P&L
Three strategies with same long run risk
adjusted return but different temporal
performance
Strategy decay: cyclical or secular?
1. Secular decay: avoid
2. Cyclical decay: Trend follow
3. Improving performance: yes please!
✓!
✗
✓?
28. QU Summer School - Ben Steiner - Sept 2020
StrategydP&L
✓✓ What don’t we know?
Evaluation 3: Strategy Sensitivity
Correlation with exogenous factors (eg: macro environment)
MRM FOR DL
CHALLENGES
INTRODUCTION
30
StrategyaP&L
Macro variable
StrategycP&L
StrategybP&L
Macro variable Macro variable
✓✗ ✗ ✓ ✗ ✗✓ ✓ ✓ ✓ ✓ ✓
??
29. QU Summer School - Ben Steiner - Sept 2020
Random portfolio weights. No Deep Learning.
Evaluation 4: Random Portfolios
Long run exposure Active trades
“Impossible” Possible but unlikely
MRM FOR DL
CHALLENGES
INTRODUCTION
31
30. QU Summer School - Ben Steiner - Sept 2020
Evaluation 5: Random Returns
Randomize order of returns. Full retraining on noise…
● Break covariance between returns and features
● Break autocorrelation of returns
● Keep original features
MRM FOR DL
CHALLENGES
INTRODUCTION
32
31. QU Summer School - Ben Steiner - Sept 2020
Strategy Monitoring
“You’ve never experienced your worst drawdown”
Is the strategy performing “as intended”
As intended = per backtest
How bad is bad?
Real world consequences
Out-of-sample:
● Distribution
● Small samples (SPC)
MRM FOR DL
CHALLENGES
INTRODUCTION
33
32. QU Summer School - Ben Steiner - Sept 2020
Summary
1. Introductory concepts
a. Model Risk Management is controlling the risk a model is “wrong”
b. Machine Learning is still a model
c. Deep Learning maps features to price movements via non-linear functions
2. Challenges of Deep Learning for Investment Strategies
a. Financial markets experience Concept Drift (video games do not!)
■ What type of Concept Drift is expected?
■ How much data can be collected before the system changes again?
b. Interpretation can be addressed (hint: look at weights!)
c. Avoid learning what we already know (hint: use residuals as the target)
3. Model Risk Management for Deep Learning investment strategies
a. Backtest evaluation to turn strategies on (but its not about high Sharpe Ratios!)
b. Ongoing monitoring to evaluate when to turn a strategy off
MRM FOR DL
CHALLENGES
INTRODUCTION
34
33. QU Summer School - Ben Steiner - Sept 2020
The road to Strategy
failure is not littered
with Deep Learning
backtests
In conclusion, Model Risk Management can help
make sure ...
35
34. QU Summer School - Ben Steiner - Sept 2020
Speaker Biography
Ben Steiner - BNP Paribas Asset Management
Ben Steiner has spent his career in the application of machine learning and
model risk management for investment firms. In his current role, Ben handles
Chief-of-Staff responsibilities in the Global Fixed Income division of BNP Paribas
Asset Management. He focusses on business management and strategic
initiatives that help BNPP AM deliver long term, sustainable returns for our
clients.
Earlier in his career, Ben was a Head of Model Development, Portfolio Manager
& Quant Researcher at investment managers and quantitative hedge funds. This
covered model development and investment strategies across multiple asset
classes ranging from the traditionally illiquid (Private Debt and Real Estate) to
more liquid products (Global Macro; Managed Futures; Equity Long/Short and
Absolute Return Fixed Income).
Ben holds a BA (Hons.) in Economics from the University of Manchester and an
MSc in Mathematical Finance from Imperial College, London. Since 2013, he
has served on the Board of Directors of the Society of Quantitative Analysts
(www.sqa-us.org). More recently, Ben has presented topics in machine learning
and model risk management at various universities and industry events.
Starting in Jan 2020, he teaches quantitative courses at Columbia University.
36