Programme for Machine Learning

Programme

Machine Learning in Finance

23-24 April, Kuala Lumpur

Day 1

09:00

Registration

09:30

Machine learning models

  • Supervised learning
  • Unsupervised learning
  • Reinforcement learning
  • Deep learning
  • Advanced machine learning models

Simon Goo, Executive Director Head, Risk Analytics, UOB

11:00

Morning break

11:30

Machine learning in banking, risk management & modelling – Part I

  • ML applications in banking and risk management
  • Analyze large amounts of data while maintaining granularity of analysis
  • Tools to optimize and accelerate model risk management
  • Reporting requirements within financial services
  • Pre-trade risk controls and best execution analysis
  • Data privacy, security and governance laws in KL

Luke Waddington, CEO & CO-Founder, BLUEFIREAI

13:00

Lunch

14:00

Machine learning in banking, risk management & modelling – Part II

  • Exposure of Current Weakness: Why am I missing big corporate stress events, why aren’t the current processes standing up to rigor?
  • Buying New World Technology & Skills: Incumbent industry doesn’t yet have the technology or the skills (in depth) to execute on the “vision”. 
  • Adoption of “new” machine intelligence: why is always our first reaction to reject it or ask to see all the inputs?
  • Invention - Small Data Problem: Especially in Asian markets we have a small data problem, how do you understand the truth with small data?
  • Real AI - Intelligence Representations: The movement from description, to prescription to prediction the “difficult” super trend.

Luke Waddington, CEO & CO-Founder, BLUEFIREAI

15:30

Afternoon break

16:00

Trading Strategies based on News and Sentiment Data

  • Machine Readable News - Format and Metadata description
  • Analysing News Data
  • Understand Real-time Sentiment Data
  • Using Kalman Filter on Sentiment Data and Identifying Sentiment Regimes
    • Use case Demo and Discussion
  • Trading Strategies based on Sentiment Data
  • Understanding Multidimensional Real time Sentiment Data
  • Cross rotation strategy formulation and back testing
    • Use case Demo and Discussion
  • Deep Learning based trading strategy
    • Use case Demo and Discussion

Radha Pendyala, Enterprise Data Scientist, REFINITIV

17:30

End of Day 1

Day 2

09:00

Registration

09:30

Machine Learning in financial trading: Theory and applications

  • Understanding data structures used for algorithmic trading
  • Benefits of AI on trading
  • Determining the dynamic trading strategy that optimizes expected utility of final wealth is a hard problem
  • Data usage across a typical trading business
  • What a data analytics platform should look like for trading
  • Research in portfolio transitions
  • Case studies

Eric Tham, Senior Lecturer & Consultant of Analytics & AI, NATIONAL UNIVERSITY OF SINGAPORE

11:00

Morning break
11:30

Understanding and developing an effective big data strategy

  • Extracting value from limited information
  • Three Key Components of Big Data Analytics
  • Big Data Management: Infrastructure and Technology
  • Data Availability, Accessibility and Integrity
  • Batch and Stream Processing
  • Advanced Analytics: Insights Generation and Algorithms Development 
  • Modern Data Analysis: Structured/Unstructured Data Modelling
  • Insights Consumption: Application and Visualisation
  • Case Studies: Use Cases in the Financial Services Sector

Johnson Poh, Head Data Analytics, Group Big Data and AI Technology, DBS
13:00

Lunch
14:00

Introduction on AI drivers and applications (Python)

  • Machine Learning in Finance
    • Customer segmentation and visualization
  • Development of predictive model for a continuous time series data set
    • ATM cash demand prediction model
  • Boosting your performance with Ensemble Learning including Random Forest and Gradient Boost
    • Next Best Offer model

Mohammad Yousuf Hussain, Data Scientist, JASMINE22
15:30

Afternoon break
16:00

Natural Language Processing (NLP) in banking

  • Really "know your clients" in their own words
  • Chatbots as a means of starting a client focused dialogue
  • Using "Personality Insights" so that your advisors never make a "cold call" again
  • Understanding "Sentiment Analysis" for people and markets
  • Building a digital wealth proposition that integrates all of these techniques
  • Constructing automated portfolios through robo-advisors or advisor dashboards
  •  The future is in the client centric development of AI, what direction to pursue?
  • Build or buy?

Mohammad Yousuf Hussain, Data Scientist, JASMINE22
17:30

End of Day 2