ENSAE Paris - École d'ingénieurs pour l'économie, la data science, la finance et l'actuariat

Machine learning for Portfolio Management and Trading

Objectif

This course introduces notebook-based data-science applications for quantitative portfolio management and trading. More precisely, it shows:

  • What kind of data is used by hedges and investment bank trading desks
  • How traditional data (e.g. prices and volume), but also alternative data (e.g. text) is used to predict the returns of stocks and other assets.
  • How machine-learning is used to extract features and train predictive models.

A strong emphasis is on running statistical tests in practice with:

  • Replicable python notebooks
  • Public datasets
  • Open-source code
  • Best practices for data exploration, hyperparameter tuning, building pipelines, etc.

Références

References:

  • Moskowitz, T. J., & Grinblatt, M. (1999). Do industries explain momentum?. The Journal of finance, 54(4), 1249-1290.
  • Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10?Ks. The Journal of finance, 66(1), 35-65.
  • Jegadeesh, N., & Wu, D. (2013). Word power: A new approach for content analysis. Journal of financial economics, 110(3), 712-729.
  • Savor, P., & Wilson, M. (2014). Asset pricing: A tale of two days. Journal of Financial Economics, 113(2), 171-201.
  • Ledoit, O., & Wolf, M. (2004). Honey, I shrunk the sample covariance matrix. The Journal of Portfolio Management, 30(4), 110-119.
  • Lo, A. W. (2002). The statistics of Sharpe ratios. Financial analysts journal, 58(4), 36-52.
  • Frazzini, A., Kabiller, D., & Pedersen, L. H. (2018). Buffett’s alpha. Financial Analysts Journal, 74(4), 35-55.
  • Lo, A. W., & MacKinlay, A. C. (1990). When are contrarian profits due to stock market overreaction?. The review of financial studies, 3(2), 175-205.

Optional background reading:

  • Isichenko, M. (2021). Quantitative Portfolio Management: The Art and Science of Statistical Arbitrage. Wiley.