Blueprints for Machine Learning and Data Science in Finance¶

Notebooks by Application in Finance¶

1. Trading Strategies and Algorithmic Trading¶

• Bitcoin Trading Strategy using classification
• Bitcoin Trading - Enhancing Speed and Accuracy using dimensionality reduction
• Clustering for Pairs Trading Strategy
• Reinforcement Learning based Trading Strategy
• NLP and Sentiments Analysis based Trading Strategy

2. Portfolio Management and robo-advisors¶

• Investor Risk Tolerance and Robo-advisors - using supervised regression
• Robo-Advisor Dashboard-powdered by ML
• Portfolio Management - Eigen Portfolio - using dimensionality reduction
• Portfolio Management - Clustering Investors
• Hierarchial Risk Parity - using clustering
• Portfolio Allocation - using reinforcement learning

3. Derivatives Pricing and Hedging¶

• Derivative Pricing - using supervised regression
• Derivatives Hedging - using reinforcement learning

4. Asset Price Prediction¶

• Stock Price Prediction - using regression and time series
• Yield Curve Prediction - using regression and time series
• Yield Curve Construction and Interest Rate Modeling - using dimensionality reduction

5. Fraud Detection¶

• Fraud Detection - using classification

6. Loan Default probability prediction¶

• Loan Default Probability - using classification

7. Chatbot and automation¶

• Digital Assistant-chat-bots - using NLP
• Documents Summarization - using NLP

Notebooks by Machine Learning Types¶

1. Supervised Learning- Regression and Time series Models¶

• Stock Price Prediction
• Derivative Pricing
• Investor Risk Tolerance and Robo-advisors
• Yield Curve Prediction

2. Supervised Learning- Classification Models¶

• Fraud Detection
• Loan Default Probability
• Bitcoin Trading Strategy

3. Unsupervised Learning- Dimensionality Reduction Models¶

• Portfolio Management - Eigen Portfolio
• Yield Curve Construction and Interest Rate Modeling
• Bitcoin Trading - Enhancing Speed and accuracy

4. Unsupervised Learning- Clustering¶

• Clustering for Pairs Trading
• Portfolio Management - Clustering Investors
• Hierarchial Risk Parity

5. Reinforcement Learning¶

• Reinforcement Learning based Trading Strategy
• Derivatives Hedging
• Portfolio Allocation

6. Natural Language Processing¶

• NLP and Sentiments Analysis based Trading Strategy
• Digital Assistant-chat-bots
• Documents Summarization

Master Template for different machine learning type¶

• Supervised learning - Regression and Time series
• Supervised learning - Classification
• Unsupervised learning - Dimensionality Reduction
• Unsupervised learning - Clustering
• Natural Language Processing

Prerequisites¶

To understand¶

• Python – you don't need to be an expert python programmer, but you do need to know the basics. If you don't, the official Python tutorial is a good place to start.
• Scientific Python – We will be using a few popular python libraries, in particular NumPy, matplotlib and pandas. If you are not familiar with these libraries, you should probably start by going through the tutorials in the Tools section (especially NumPy).

To run the examples¶

• Jupyter – These notebooks are based on Jupyter. If you just plan to read without running any code, there's really nothing more to know, just keep reading!