Event Agenda

Agenda

Machine Learning in Finance: Agenda

**************************************************
Live virtual course | Agenda timing is in GMT

Respective EST timing is:
Start: 9am
Break 1: 10am
Break 2: 11.15am
Finish: 12.30pm
**************************************************

14:0015:00

Introduction to machine learning and financial applications

14:00 - 15:00

  • From probability and statistics to machine learning (ML)

  • Core components of the ML process

  • Current applications of ML in finance

15:0015:15

Break

15:00 - 15:15

15:1516:15

Supervised learning models

15:15 - 16:15

  • Naïve bayes

  • Decision trees

  • Bias, variance, and cross-validation

  • Ensemble methods: boosting, bagging and random forest

  • Regression models

  • Support vector machines

  • Neural nets and deep learning

16:1516:30

Break

15:00 - 15:15

16:3017:30

Applying ML methods in risk management

14:00 - 15:00

  • Measuring performance

  • Classification with imbalanced data

  • Class weights for cost-sensitive training

  • Synthetic sampling methods

  • Feature engineering

14:0015:00

Neural nets and deep learning

10:45 - 12:00

  • Deep learning and complexity

  • Volatility prediction with neural nets

  • Deep learning and options pricing

  • NLP and word embeddings

  • Other applications

15:0015:15

Break

15:00 - 15:15

15:1516:15

Unsupervised methods and reinforcement learning

14:00 - 15:00

  • Unsupervised learning

    • Dimensionality reduction

    • Clustering

    • Topic models

    • Autoencoders

  • Reinforcement learning and deep Q learning

16:1516:30

Break

15:00 - 15:15

16:3017:30

Anomaly detection

14:00 - 15:00

  • Types of anomalies

  • Challenges in anomaly detection

  • Anomaly detection methods

    • k-nearest neighbours

    • Local outlier factor

    • Cluster-based local outlier factor

    • Isolation forest

14:0015:00

Explainability in machine learning

15:15 - 16:15

  • Definitions of explainability

  • Explainability in finance and financial regulation

  • How to achieve ML explainability

15:0015:15

Break

15:00 - 15:15

15:1516:15

Regulatory implications of machine learning

14:45 - 16:15

  • Adoption of ML

  • Applications of ML in supervisory activities

  • Evolving and emerging risks

16:1516:30

Break

15:00 - 15:15

16:3017:30

Implementing ML models: a roadmap

15:15 - 16:15

  • Reference architecture

  • Implementation at scale

  • Continuous delivery for ML

  • Roles, tasks, and skills

  • Integrating data science teams in the organisation

17:3017:30

End of course

16:15 - 16:16