This code repository pertains to the seminar project titled "Using Machine Learning for Empirical Asset Pricing", supervised by Patrick Jaquart at the chair of Information & Market Engineering at KIT (winter semester 2019/20).
The project aims to predict the excess returns for a defined asset universe by means of advanced machine learning methods such as LSTM Networks and Gradient-Boosted Decision Trees and to devise derived trading strategies to capitalize on opportunities for arbitrage.
This work extends the previous work by [1][2].
[1] Fischer, Thomas; Krauss, Christopher (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research 270 (2), S. 654–669. DOI: 10.1016/j.ejor.2017.11.054.
[2] Krauss, Christopher; Do, Xuan Anh; Huck, Nicolas (2017). Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Research 259 (2), S. 689–702. DOI: 10.1016/j.ejor.2016.10.031.