Course Agenda

Agenda

Machine Learning in Finance - London

Course Agenda*

Day one - Wednesday, November 27, 2019

08:30

Registration and refreshments

09:00

Machine learning in finance: opportunities and limitations

  • Introduction to machine learning in finance

  • Machine learning in banking, risk management & modelling

  • Neural networks

  • Early financial applications: detecting credit card fraud, selecting mutual funds, trading treasury bonds

  • Deep learning models

10:30

Morning break

10:45

Machine learning models

  • Supervised learning
  • Unsupervised learning
  • Deep learning
  • Advanced machine learning models
  • Machine learning and pricing models

Speaker: Sachapon Tungson, Machine learning senior architect, State Street

12:00

Lunch

1:00

Data management for machine learning

  • Data quality
  • Efficient data handling
  • Outlier detection
  • Data anonymization

Speaker: Richard Saldanha, Managing director, Oxquant

2:30

Afternoon break

3:00

Machine learning in risk management

  • Machine learning in banking, risk management and modelling
  • Analysis of rare events;
    • Labelled, unbalanced data
    • Anomaly detection
  • Network analysis
  • Time series spikes and breakouts
  • ML applications in equities vs fixed income

4:30

End of day one

Day two - Thursday, November 28, 2019 

08:30

Refreshments

09:00

Machine learning in trading and portfolio optimisation

  • The impact ML has on portfolio optimisation
  • Data science & machine learning in quantitative finance
  • New tools and techniques in large-scale machine learning and analytics
  • An overview of developments in data science and machine learning through the context of the needs of the quantitative finance industry
  • Multi period portfolio optimisation

Speaker: Rishi Thapar, Head of investment risk and quantitative research, Local Pensions Partnership

10:30

Morning break

10:45

Natural language processing: a deep dive 

  • How is natural language processing transforming finance?

  • Machine learning and deep learning to maximise profits

  • Challenges and opportunities

  • Sentiment analysis

  • Methods for risk modelling 

  • How to assess your competition 

12:00

Lunch

1:00

Managing the human factor and biases in machine learning

  • How can machine learning make banking more personal?

  • Human-augmented training of neural networks

  • Use cases and recent advancements

  • Tackling biases in ML and humans

  • Human judgement to ensure AI supported decision making

  • The ethics of machine learning

2:30

Afternoon break

3:00

Applying machine learning in practice

  • Pros and cons of applying ML to investing 

  • Focusing on use cases which add business value

  • Importance of features selection

  • Subtleties of applying ML to investing 

  • Case study: code in practice

4:30

End of course

* Course agenda is subject to changes