agenda

agenda

The Fundamentals of Machine Learning | Agenda

Agenda timing is in HKT/SGT

08:4509:00

Registration

09:00 - 10:00

09:0010:00

Introducing machine learning (ML)

10:00 - 11:00

  • Differences between modern statistics, ML and AI
  • Core components of the ML process
  • How does ML apply to financial organisations?
  • Current applications of ML
  • How ML is changing financial markets
Arnab Chakraborty

Client Intelligence Manager

HSBC

Arnab is Client Intelligence Manager with HSBC in Data and Analytics. He has been working with HSBC for more than 5 years where he primarily looks into managing and preventing financial crime risk through right data and analytics. Prior to joining this role he has worked with HSBC in building various data solutions to drive growth and managing risks. He is a data science enthusiast and also loves to build apps in iOS and Android.

10:0011:00

Understanding data

09:00 - 10:00

  • The importance of identifying appropriate data sources and types
    • Alternative data: smart city, spatial and flow data, mobile sensor data (gestures, movement)
    • Semantic data: text, documents 
  • Data quality, quantity and representativeness 
  • The effect of data quality on ML output
  • Data engineering and data quality management
    • The ETL process: Extracting - Transforming - Loading data
    • Data models
  • Analysing data
    • Exploratory data analysis
    • Visualisation 
  • Choosing the best data set 
    • Available data or trial study design
    • Active experimentation 
Arnab Chakraborty

Client Intelligence Manager

HSBC

Arnab is Client Intelligence Manager with HSBC in Data and Analytics. He has been working with HSBC for more than 5 years where he primarily looks into managing and preventing financial crime risk through right data and analytics. Prior to joining this role he has worked with HSBC in building various data solutions to drive growth and managing risks. He is a data science enthusiast and also loves to build apps in iOS and Android.

11:0011:15

Break

10:00 - 11:00

11:1512:15

Objective function

09:00 - 10:00

  • What is an objective function?
  • Representing the business problem in mathematical terms
  • Measuring the sensitivity of a solution 
  • Types of objective function
    • Regression and classification
    • Advanced: text, fidelity, trajectory mismatch
  • Specifying constraints: custom business vs compliance/regulatory 
  • Specifying the objective function based on outcomes 
    • Risk and loss functions – investment, credit
    • Ratings – client analytics (churn, fraud, AdTech), ESG 
  • Model selection
    • Principles of model and variable selection
    • Confidence estimation
    • Determining the complexity of a model
    • Training speed and scalability
Osamu Tsuchiya

Quantitative Analyst

Simplex Inc.

Osamu Tsuchiya is a Quantitative Analyst at Simplex Inc. He has worked for Dresdner Kleinwort and Citigroup as a rates and hybrid derivatives quant analyst. He has also worked for XVA modeling.

Additionally, he has experience working as a financial risk management consultant for Ernst and Young.

Before moving to finance, Osamu worked in the field of mathematical physics. He holds a PhD in Theoretical and Mathematical Physics from The University of Tokyo. His book "The Practical Approach to XVA: The Evolution of Derivatives Valuation After the Financial Crisis" was published in 2019.

12:1512:15

End of Day 1

10:00 - 11:00

09:0010:00

From modern statistics to machine learning models

09:00 - 10:00

  • From linear regression to nearest neighbours and decision trees
  • Ensembles of models
  • Supervised and unsupervised learning 
  • Reinforcement learning 
  • Deep learning
  • Tackling the overfitting problem and tuning hyper parameters

10:0011:00

Interpreting and validating a model

10:00 - 11:00

  • ML-specific model validation issues
  • Accuracy/Explainability trade-off
  • Model explainability techniques
    • Global explainability: variable importance and surrogate models
    • Local explainability: SHAP values
  • Case study:  explaining house price predictions
Alex Botsula

Senior Manager, Banking and Capital Markets

EY

Alex is a senior manager in EY’s Actuarial Services team with a primary focus on credit risk quantitative modelling and model validation. Alex has over 15 years of analytics experience, including 10 years’ experience in multiple areas of credit risk measurement and management, credit risk forecasting, economic capital modelling and strategy development. He holds a Master’s Degree in Applied Mathematics and Computer Science from Lomonosov Moscow State University.

11:0011:15

Break

10:00 - 11:00

11:1512:15

Machine Learning in Investment Management and the Rise of Alternative Data

10:00 - 11:00

  • Introduction
    • Machine Learning Drivers
    • Quantitative Investment Strategies
  • Traditional Factor Investing
    • French/Fama Five-Factor Model
    • Develop and Test Investment Hypothesis including code demo in python
  • Alternative Factor Investing
    • Natural Language Processing and Computer Vision enabled Factor Investing
  • Industry Insight: Bloomberg Alternative Data Portfolio

Carolina is a German Engineer who has been a Developer at Rolls Royce and Innovation Consultant at Roland Berger Strategy Consulting. Following her expertise at Morgan Stanley Investment Management she joined the Technology & Innovation team at EY in Hong Kong combining her tech and finance background serving financial services clients to achieve target business goals leveraging innovative business models and Artificial Intelligence.

She is further the founder Cerebro 天慧人工智能研究 - publishing research in the field of Machine Learning such as stock price prediction on crypto currencies and state of the art lane line finding algorithms for self driving cars. Her publications on applied AI use cases and interviews with leading companies in the field receive more than 30.000 views from her wide ranging personal industry network.

By end of 2020, Carolina will be joining one of the major technology companies in the world and continue to serve financial services clients by engineering cutting edge data solutions.

 

The Rise of Quantitative Investing and Alternative Data

Algortihmic advancements in the field of Machine Learning, the explosion of data and the tremendous upgrade in computing power has fueled Quantititative Investing Strategies with Factor based Investments estimated to grow to US$ 3.4 trillion by 2022 according to Blackrock.

This talk will cover high level insights on Quantitiavie Investment Strategies not only based on macro, and fundamental factors, but also on AI enabled alternative factors leveraging Natural Language Processing (NLP) and Computer Vision. 

At the heart of the presentation is a technical demonstration of a code in python using the French/Fama Five Factor Model (highly recognized in the industry and academia) to visualise historical outperformance of certain Factor strategies within a defined investment universe.

12:1512:15

End of Day 2

10:00 - 11:00

09:0010:00

ML for risk practitioners

10:00 - 11:00

  • Identifying and monitoring risk
  • Applications of ML in different risk areas
  • Reducing credit risk
  • Enforcing regulatory compliance: risk profiling and fairness
  • Mitigating MLs own risk to the business model
Feng Guo

Vice President - Lead Data Scientist

DBS Bank

10:0010:15

Break

10:00 - 11:00

10:1511:15

Machine learning in finance: putting it into practice

10:00 - 11:00

  • ML for quantitative investment: challenges and opportunities 
  • Where does ML have more chance of winning? 
  • Start with a baseline model 
  • Two examples: 
  • Forecasting dividend ends 
  • Building a stock selection model 
  • Future applications of machine learning in finance
Osamu Tsuchiya

Quantitative Analyst

Simplex Inc.

Osamu Tsuchiya is a Quantitative Analyst at Simplex Inc. He has worked for Dresdner Kleinwort and Citigroup as a rates and hybrid derivatives quant analyst. He has also worked for XVA modeling.

Additionally, he has experience working as a financial risk management consultant for Ernst and Young.

Before moving to finance, Osamu worked in the field of mathematical physics. He holds a PhD in Theoretical and Mathematical Physics from The University of Tokyo. His book "The Practical Approach to XVA: The Evolution of Derivatives Valuation After the Financial Crisis" was published in 2019.

11:1511:15

End of course

10:00 - 11:00