© 2022 CFA Institute. All rights reserved.
PYTHON AND DATA SCIENCE FOR
INVESTMENT PROFESSIONALS
INFORMATION SESSION
11 May 2022
Richard Fernand, CFA
Sri Krishnamurthy, CFA, CAP
Powered by
AGENDA
2
1. Introduction
2. The Data revolution in Finance
3. Python and Data Science for Investment Professionals program
4. Sample Case study
- EDGAR Earnings Filing analysis using NLPtechniques
3
• Advisory and Consultancy for FinancialAnalytics
• Prior Experience at MathWorks, Citigroup and Endeca
and 25+ financial services and energy customers.
• Columnist for the Wilmott Magazine
• Author of forthcoming book
“PragmaticAI and MLin Finance”
• TeachesAI/MLand Fintech Related topics in the MS
and MBAprograms at Northeastern University, Boston,
Babson College and Hult International Business School
• Reviewer: Journal ofAsset Management
Sri Krishnamurthy
Founder and CEO
QuantUniversity
YOUR SPEAKER
Part 1
The Data Revolution
5
THE 4TH INDUSTRIAL REVOLUTION IS HERE!
Source: Christoph Roser at AllAboutLean.com
As per Wikipedia*, “The 4th Industrial Revolution ….. marked by emerging technology breakthroughs in a
number of fields, including robotics, artificial intelligence, nanotechnology, quantum computing, biotechnology, the
Internet ofThings, the Industrial Internet ofThings (IIoT), decentralized consensus, fifth-generation wireless
technologies (5G), additive manufacturing/3D printing and fully autonomous vehicles.”
* https://en.wikipedia.org/wiki/Fourth_Industrial_Revolution
6
SCIENTISTS ARE DISRUPTING THE WAY WE LIVE!
Source: https://www.ladn.eu/tech-a-suivre/mobilite-2030-vehicules-volants-open-data/
7
INTEREST IN MACHINE LEARNING CONTINUES TO GROW
https://www.wipo.int/edocs/pubdocs/en/wipo_pub_1055.pdf
8
MACHINE LEARNING AND AI IS REVOLUTIONIZING FINANCE
9
MARKET IMPACT AT THE SPEED OF LIGHT!
9
10
MACHINE LEARNING & AI IN FINANCE: A PARADIGM
SHIFT
10
Stochastic
Models
Factor Models
Optimization
Risk Factors
P/Q Quants
Derivative
pricing
Trading
Strategies
Simulations
Distribution
fitting
Quant
Real-time
analytics
Predictive
analytics
Machine
Learning
RPA
NLP
Deep Learning
Computer Vision
Graph Analytics
Chatbots
Sentiment
Analysis
Alternative Data
Data Scientist
11
THE VIRTUOUS CIRCLE OF
MACHINE LEARNING AND AI
11
Smart
Algorithms
Hardware
Data
12
THE RISE OF BIG DATA AND DATA SCIENCE
12
Image Source: http://www.ibmbigdatahub.com/sites/default/files/infographic_file/4-Vs-of-big-data.jpg
13
SMART ALGORITHMS
13
Distributing Computing Frameworks Deep Learning Frameworks
1. Our labeled datasets were thousands of times
too small.
2. Our computers were millions of times too slow.
3. We initialized the weights in a stupid way.
4. We used the wrong type of non-linearity.
- Geoff Hinton
“Capital One was able to determine fraudulent credit
card applications in 100 milliseconds”*
* http://go.databricks.com/hubfs/pdfs/Databricks-for-FinTech-170306.pdf
HARDWARE
14
Speed up calculations with
1000s of processors
Scale computations with infinite
compute power
15
DATA SCIENCE WORKFLOW
Data
Scraping/
Ingestion
Data
Exploration
Data
Cleansing and
Processing
Feature
Engineering
Model
Evaluation
& Tuning
Model
Selection
Model
Deployment/
Inference
Supervised
Unsupervised
Modeling
Data Engineer, Dev Ops Engineer
Data Scientist/Quants
Software/Web Engineer
• AutoML
• Model Validation
• Interpretability
Robotic Process Automation (RPA) (Microservices, Pipelines )
• SW: Web/ Rest API
• HW: GPU, Cloud
• Monitoring
• Regression
• KNN
• Decision Trees
• Naive Bayes
• Neural Networks
• Ensembles
• Clustering
• PCA
• Autoencoder
• RMS
• MAPS
• MAE
• Confusion Matrix
• Precision/Recall
• ROC
• Hyper-parameter
tuning
• Parameter Grids
Risk Management/ Compliance(All
stages)
Analysts
&
Decision
Makers
Part 2
The Python and Data Science for
Investment Professionals Program
COURSE DETAILS
This introductory course, geared towards
financial professionals will discuss key concepts
needed to write and understand Python. Rather
than overwhelming you with all the syntactical
details, we will focus on the key elements and
packages giving you just enough orientation to
start your Data science journey in Python.
Using QuAcademy, our remote-learning platform
and Jupyter notebooks, we will discuss the key
elements of Python and discuss how to write
applications working with datasets.
CFA Institute is offering this course, powered by
QuantUniversity. It is eligible for Professional
Learning Credits.
14 hours to complete
• Online instruction split into four 3.5 hour sessions delivered by Sri Krishnamurthy CFA,
from QuantUniversity
Beginner level
CFAcandidates and
Charterholders who are
analysts, portfolio managers,
risk managers and quants
wanting to sharpen their data
science skills.
Gain technical
skills
Work with financial
datasets in Python,
understand the importance
of data science, work with
practical examples & real-
world applications.
Certificate of
completion
Upon completion of the
course you will receive a
certificate of completion.
Online
instructor led
training
Access to hands-on labs
and case studies. Live
training delivered online
in boot-camp style,
hands-on learning
COURSE SNAPSHOT
WHAT YOU WILL LEARN
20
• TheData Science Revolution: Whyyou need to
learn Data Science now.
• Implementing an analytics library in Python for
risk and performance calculations.
• Exploring and visualizing techniques using plotly,
seaborn and matplotlib.
• Predicting stock returns using machine learning
techniques.
• Integrating, fundamental, quantitative and data
science techniques within your enterprise.
• Portfolio management with Python.
MODULE 1: THE BASICS
21
Introduction to Python
• The Data Science Revolution: Why you need to learn Data Science now!
• Introduction to Python through examples
• The Python Ecosystem: Popular data science and analysis packages
• Lab:Workingwith Jupyter notebooks
• Exploring data in Python: Time series and Cross-sectional datasets
• Casestudy1: Implementing an analyticslibraryin Pythonfor riskand performance
calculations
MODULES 2: DATA SCIENCE METHODS
Analyzingdata and Visualization
• Understanding relationships in Data
• Descriptive, Prescriptive and Predictive analytics
• Lab:Implementing quantitative methods and metrics
• Exploring and Visualizing Data using pandas,matplotlib, seaborn& plotly
• Casestudy2: Visualizing stockportfolios
MODULES 3: MACHINE LEARNING TECHNIQUES
22
Thepowerof machinelearning
• Supervised, Unsupervised and Reinforcement Learning
• Lab:Clustering Stock Data
• Time series analysis and forecasting
• Casestudy3: Predicting stockreturns usingmachinelearningtechniques
MODULES 4: CASE STUDIES & PRACTICAL
APPLICATIONS IN FINANCE
Data ScienceinAction
• Integrating, fundamental, quantitative and data science techniques within your enterprise -
Aroadmap
• Casestudy4: Extractingsentimentsfrom Edgarfilings usingNLPtechniques
• Casestudy5: Portfoliomanagementwith Python
• Recap,next steps and frontier topics: Reinforcement learning, Quantum Computing,AI,
GPU-accelerated and Cloud computing
DATESAND PRICING
23
Region Date Time
Americas 25 May 2022,1 Jun2022,8 Jun
2022, 15 Jun2022
9:30AM EST
EMEA 21 Jun2022, 23 Jun2022, 28 Jun
2022, 30 Jun2022
1:30 PM CET
Asia Pacific 27 July 2022, 3Aug 2022, 10
Aug 2022, 17Aug 2022
12:00 PM Noon HKT
Standard Enrollment Fee
USD2,099
Member Enrollment Fee
USD1,999
CF
AInstitute membersare eligible for
an additional $100 off! Usecoupon
"CFAQU100"for a $100 discount on
non-member prices.
Part 3
Case study
GOAL
• Understandingsentimentsin Earningscall transcripts
25
26
• Interpreting emotions
• Labeling data
CHALLENGES
WHAT IS NLP?
27
AI
Linguistics
Computer
Science
SAMPLE APPLICATIONS
• Q/A
• Dialog systems- Chatbots
• Topic summarization
• Sentimentanalysis
• Classification
• Keyword extraction- Search
• Informationextraction– Prices,Dates,People etc.
• ToneAnalysis
• MachineTranslation
• Documentcomparison– Similar/Dissimilar
28
NLP IN FINANCE
29
LANGUAGE ALLOWS UNDERSTANDING
• If computerscan understand language,opens huge possibilities
• Read and summarize
• Translate
• Describe what’s happening
• Understandcommands
• Answer questions
• Respondin plain language
30
31
Data Ingestion
from Edgar
Pre-Processing
Invoking APIs
to label data
Compare APIs
Build a new
model for
sentiment
Analysis
NLP PIPELINE
Demo
REGISTERAT:
HTTPS://WWW.CFAINSTITUTE.ORG/EN/EVENTS/PROFESSIONAL-LEARNING/PYTHON-TRAINING
SPECIALALPHASUMMITCONFERENCE PROMOTION
Use codeALPHA15 for 15% OFF!
33
© 2022 CFA Institute. All rights reserved.
For registration and support :
info@qusandbox.com

PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALS

  • 1.
    © 2022 CFAInstitute. All rights reserved. PYTHON AND DATA SCIENCE FOR INVESTMENT PROFESSIONALS INFORMATION SESSION 11 May 2022 Richard Fernand, CFA Sri Krishnamurthy, CFA, CAP Powered by
  • 2.
    AGENDA 2 1. Introduction 2. TheData revolution in Finance 3. Python and Data Science for Investment Professionals program 4. Sample Case study - EDGAR Earnings Filing analysis using NLPtechniques
  • 3.
    3 • Advisory andConsultancy for FinancialAnalytics • Prior Experience at MathWorks, Citigroup and Endeca and 25+ financial services and energy customers. • Columnist for the Wilmott Magazine • Author of forthcoming book “PragmaticAI and MLin Finance” • TeachesAI/MLand Fintech Related topics in the MS and MBAprograms at Northeastern University, Boston, Babson College and Hult International Business School • Reviewer: Journal ofAsset Management Sri Krishnamurthy Founder and CEO QuantUniversity YOUR SPEAKER
  • 4.
    Part 1 The DataRevolution
  • 5.
    5 THE 4TH INDUSTRIALREVOLUTION IS HERE! Source: Christoph Roser at AllAboutLean.com As per Wikipedia*, “The 4th Industrial Revolution ….. marked by emerging technology breakthroughs in a number of fields, including robotics, artificial intelligence, nanotechnology, quantum computing, biotechnology, the Internet ofThings, the Industrial Internet ofThings (IIoT), decentralized consensus, fifth-generation wireless technologies (5G), additive manufacturing/3D printing and fully autonomous vehicles.” * https://en.wikipedia.org/wiki/Fourth_Industrial_Revolution
  • 6.
    6 SCIENTISTS ARE DISRUPTINGTHE WAY WE LIVE! Source: https://www.ladn.eu/tech-a-suivre/mobilite-2030-vehicules-volants-open-data/
  • 7.
    7 INTEREST IN MACHINELEARNING CONTINUES TO GROW https://www.wipo.int/edocs/pubdocs/en/wipo_pub_1055.pdf
  • 8.
    8 MACHINE LEARNING ANDAI IS REVOLUTIONIZING FINANCE
  • 9.
    9 MARKET IMPACT ATTHE SPEED OF LIGHT! 9
  • 10.
    10 MACHINE LEARNING &AI IN FINANCE: A PARADIGM SHIFT 10 Stochastic Models Factor Models Optimization Risk Factors P/Q Quants Derivative pricing Trading Strategies Simulations Distribution fitting Quant Real-time analytics Predictive analytics Machine Learning RPA NLP Deep Learning Computer Vision Graph Analytics Chatbots Sentiment Analysis Alternative Data Data Scientist
  • 11.
    11 THE VIRTUOUS CIRCLEOF MACHINE LEARNING AND AI 11 Smart Algorithms Hardware Data
  • 12.
    12 THE RISE OFBIG DATA AND DATA SCIENCE 12 Image Source: http://www.ibmbigdatahub.com/sites/default/files/infographic_file/4-Vs-of-big-data.jpg
  • 13.
    13 SMART ALGORITHMS 13 Distributing ComputingFrameworks Deep Learning Frameworks 1. Our labeled datasets were thousands of times too small. 2. Our computers were millions of times too slow. 3. We initialized the weights in a stupid way. 4. We used the wrong type of non-linearity. - Geoff Hinton “Capital One was able to determine fraudulent credit card applications in 100 milliseconds”* * http://go.databricks.com/hubfs/pdfs/Databricks-for-FinTech-170306.pdf
  • 14.
    HARDWARE 14 Speed up calculationswith 1000s of processors Scale computations with infinite compute power
  • 15.
  • 16.
    DATA SCIENCE WORKFLOW Data Scraping/ Ingestion Data Exploration Data Cleansingand Processing Feature Engineering Model Evaluation & Tuning Model Selection Model Deployment/ Inference Supervised Unsupervised Modeling Data Engineer, Dev Ops Engineer Data Scientist/Quants Software/Web Engineer • AutoML • Model Validation • Interpretability Robotic Process Automation (RPA) (Microservices, Pipelines ) • SW: Web/ Rest API • HW: GPU, Cloud • Monitoring • Regression • KNN • Decision Trees • Naive Bayes • Neural Networks • Ensembles • Clustering • PCA • Autoencoder • RMS • MAPS • MAE • Confusion Matrix • Precision/Recall • ROC • Hyper-parameter tuning • Parameter Grids Risk Management/ Compliance(All stages) Analysts & Decision Makers
  • 17.
    Part 2 The Pythonand Data Science for Investment Professionals Program
  • 18.
    COURSE DETAILS This introductorycourse, geared towards financial professionals will discuss key concepts needed to write and understand Python. Rather than overwhelming you with all the syntactical details, we will focus on the key elements and packages giving you just enough orientation to start your Data science journey in Python. Using QuAcademy, our remote-learning platform and Jupyter notebooks, we will discuss the key elements of Python and discuss how to write applications working with datasets. CFA Institute is offering this course, powered by QuantUniversity. It is eligible for Professional Learning Credits.
  • 19.
    14 hours tocomplete • Online instruction split into four 3.5 hour sessions delivered by Sri Krishnamurthy CFA, from QuantUniversity Beginner level CFAcandidates and Charterholders who are analysts, portfolio managers, risk managers and quants wanting to sharpen their data science skills. Gain technical skills Work with financial datasets in Python, understand the importance of data science, work with practical examples & real- world applications. Certificate of completion Upon completion of the course you will receive a certificate of completion. Online instructor led training Access to hands-on labs and case studies. Live training delivered online in boot-camp style, hands-on learning COURSE SNAPSHOT
  • 20.
    WHAT YOU WILLLEARN 20 • TheData Science Revolution: Whyyou need to learn Data Science now. • Implementing an analytics library in Python for risk and performance calculations. • Exploring and visualizing techniques using plotly, seaborn and matplotlib. • Predicting stock returns using machine learning techniques. • Integrating, fundamental, quantitative and data science techniques within your enterprise. • Portfolio management with Python.
  • 21.
    MODULE 1: THEBASICS 21 Introduction to Python • The Data Science Revolution: Why you need to learn Data Science now! • Introduction to Python through examples • The Python Ecosystem: Popular data science and analysis packages • Lab:Workingwith Jupyter notebooks • Exploring data in Python: Time series and Cross-sectional datasets • Casestudy1: Implementing an analyticslibraryin Pythonfor riskand performance calculations MODULES 2: DATA SCIENCE METHODS Analyzingdata and Visualization • Understanding relationships in Data • Descriptive, Prescriptive and Predictive analytics • Lab:Implementing quantitative methods and metrics • Exploring and Visualizing Data using pandas,matplotlib, seaborn& plotly • Casestudy2: Visualizing stockportfolios
  • 22.
    MODULES 3: MACHINELEARNING TECHNIQUES 22 Thepowerof machinelearning • Supervised, Unsupervised and Reinforcement Learning • Lab:Clustering Stock Data • Time series analysis and forecasting • Casestudy3: Predicting stockreturns usingmachinelearningtechniques MODULES 4: CASE STUDIES & PRACTICAL APPLICATIONS IN FINANCE Data ScienceinAction • Integrating, fundamental, quantitative and data science techniques within your enterprise - Aroadmap • Casestudy4: Extractingsentimentsfrom Edgarfilings usingNLPtechniques • Casestudy5: Portfoliomanagementwith Python • Recap,next steps and frontier topics: Reinforcement learning, Quantum Computing,AI, GPU-accelerated and Cloud computing
  • 23.
    DATESAND PRICING 23 Region DateTime Americas 25 May 2022,1 Jun2022,8 Jun 2022, 15 Jun2022 9:30AM EST EMEA 21 Jun2022, 23 Jun2022, 28 Jun 2022, 30 Jun2022 1:30 PM CET Asia Pacific 27 July 2022, 3Aug 2022, 10 Aug 2022, 17Aug 2022 12:00 PM Noon HKT Standard Enrollment Fee USD2,099 Member Enrollment Fee USD1,999 CF AInstitute membersare eligible for an additional $100 off! Usecoupon "CFAQU100"for a $100 discount on non-member prices.
  • 24.
  • 25.
  • 26.
    26 • Interpreting emotions •Labeling data CHALLENGES
  • 27.
  • 28.
    SAMPLE APPLICATIONS • Q/A •Dialog systems- Chatbots • Topic summarization • Sentimentanalysis • Classification • Keyword extraction- Search • Informationextraction– Prices,Dates,People etc. • ToneAnalysis • MachineTranslation • Documentcomparison– Similar/Dissimilar 28
  • 29.
  • 30.
    LANGUAGE ALLOWS UNDERSTANDING •If computerscan understand language,opens huge possibilities • Read and summarize • Translate • Describe what’s happening • Understandcommands • Answer questions • Respondin plain language 30
  • 31.
    31 Data Ingestion from Edgar Pre-Processing InvokingAPIs to label data Compare APIs Build a new model for sentiment Analysis NLP PIPELINE
  • 32.
  • 33.
  • 34.
    © 2022 CFAInstitute. All rights reserved. For registration and support : info@qusandbox.com