Fundamentals of Machine Learning in Finance

Description

The course aims to help students solve practical ML-amenable problems that they may encounter in real life, such as: (1) understanding where the problem lies on a general landscape of available ML methods, (2) understanding which specific ML approach(es) would be most appropriate for resolving the problem, and (3) ability to successfully implement and assess a solution.

Syllabus :

1. Fundamentals of Supervised Learning in Finance

• What is Machine Learning in Finance?
• Introduction to Fundamentals of Machine Learning in Finance
• Support Vector Machines
• SVM. The Kernel Trick
• Example: SVM for Prediction of Credit Spreads
• Tree Methods. CART Trees
• Tree Methods: Random Forests
• Tree Methods: Boosting

 

2. Core Concepts of Unsupervised Learning, PCA & Dimensionality Reduction

• Core Concepts of UL
• PCA for Stock Returns
• Dimension Reduction with PCA
• Dimension Reduction with tSNE
• Dimension Reduction with Autoencoders

 

3. Data Visualization & Clustering

• Clustering Algorithms
• K-clustering
• K-means Neural Algorithm
• Hierarchical Clustering Algorithms
• Clustering and Estimation of Equity Correlation Matrix
• Minimum Spanning Trees, Kruskal Algorithm
• Probabilistic Clustering

 

4. Sequence Modeling and Reinforcement Learning

• Latent Variables
• Sequence Modeling
• Latent Variables for Sequences
• State-Space Models
• Hidden Markov Models
• Neural Architecture for Sequential Data
• Core Ideas
• Markov Decision Process and RL
• Bellman Equation
• RL and Inverse Reinforcement Learning

Show more