Kris has presented us his takeaways from the SoFiE Summer School at University of Chicago: Machine Learning and Finance: The New Empirical Asset Pricing. He particulary focused his presentation on Empirical Asset Pricing via Machine Learning, a very recent paper (this version: July 21, 2018) exploring the use of different machine learning regressions on a given dataset of economic variables to predict future stock returns. Personal opinion: To be noticed, despite being a recent paper, they have still a rather outdated view of neural networks being very general (universal approximators) non-linear regressors rather than useful representation builders, the latter being used efficiently by linear models. A big claim of the paper is that one can reach a Sharpe ratio of 2 using these neural networks (once again only an old pyramidal architecture (1993) is tested) whereas linear models only achieve a Sharpe ratio of 0.5- using the same dataset. Bagging/Boosting trees methods lie somewhere in between. It's hard to evaluate and reproduce such papers.

Simon did an introductory talk about deep learning techniques applied for natural language processing: CNNs, LSTMs, bi-LSTMs, CRF bi-LSTMs are networks often used to label sentences at the word, or even the character level. Tan did a visual introduction to Topological Data Analysis (TDA), the application of discrete topology to study point clouds. These techniques allow for a robust description of the point clouds properties at multiple scales via persistence diagrams. Robustness and persistence of patterns at multiple scales are a desirable properties, especially in the case of noisy and highly stochastic financial time series. Tan uses the persistence diagrams as features to a machine learning classifier (say XGBoost) to predict ETFs returns.