Machine learning and the growing availability of diverse financial data has created powerful and exciting new approaches to quantitative investment. In this liveProject, you’ll step into the role of a data scientist for a hedge fund to deliver a machine learning model that can inform a profitable trading strategy.
You’ll go hands-on to build an end-to-end strategy workflow that includes sourcing market data, engineering predictive features, and designing and comparing various ML models. Throughout the liveProject you will work with libraries and tools from the industry-standard Python data ecosystem. You’ll tackle challenges such as training a regularized linear regression model, tuning a gradient boosting ML model, and evaluating the performance of your strategy—all essential skills for success in this highly lucrative area of machine learning.
This project is designed for learning purposes and is not a complete, production-ready application or solution.
The liveProject is for intermediate Python programmers who know the basics of data science. To begin this liveProject, you will need to be familiar with:
- Basics of pandas
- Basics of scikit-learn
- Basics of LightGBM
- Basics of Jupyter Notebook
- Basics of financial metrics and technical indicators
- Basics of ML
you will learn
In this liveProject, you’ll learn skills for designing and implementing an end-to-end machine learning model specializing in asset return prediction. These skills are in high demand from companies across the banking and investment industries.
- Source financial market data containing historic price information
- Engineer financial features based on commonly used technical indicators deemed to contain some predictive information about future returns
- Build, tune and test an ML model to predict asset returns for a given price horizon
- Evaluate the signal quality of the resulting model predictions using Alphalens
- Develop a trading strategy by defining rules that translate model predictions into trades
- Backtest your trading strategy using Zipline
- Evaluate your backtest result with common performance and risk measures using pyfolio