Off-the-shelf Machine Learning is Surprisingly Good at Combining Trading Alphas

You have likely read about how the field of machine learning (ML) is making serious inroads into how Wall Street is operating, with firms like BlackRock, Bridgewater, D. E Shaw & Co. among many others all actively using ML and hiring experts in that field.

The team at Deep Value has been using ML for the past few years and has prepared some research aimed at desks new to field — in this installment, on using machine learning to combine trading alphas.

  • Off-the-shelf machine learning, and especially support vector machines, are a defensible starting point for automatedly combining alphas, over purely linear and simple regression-based approaches.
  • Other (clustering and boosting) approaches also show promise, while needing work and calibration to deal with respectively high dimensionality, and high noise.
  • ML-based approaches come with opacity, and the ability of ML models to evolve with the markets can hamper an understanding of what they are doing.

The link to the research is here.

Disclaimers apply.