Trading algorithms with learning in latent alpha models

TL;DR

This paper develops an optimal trading framework for strategies driven by latent factors affecting prices, incorporating learning, price impact, and model calibration, with demonstrated effectiveness through simulations and real data examples.

Contribution

It introduces a method to learn latent states and explicitly solve the optimal trading problem considering price impact and latent factors.

Findings

Optimal trading strategies outperform non-learning strategies in simulations.

The model can be calibrated using a variation of the EM algorithm.

Application to Intel stock demonstrates practical calibration.

Abstract

Alpha signals for statistical arbitrage strategies are often driven by latent factors. This paper analyses how to optimally trade with latent factors that cause prices to jump and diffuse. Moreover, we account for the effect of the trader's actions on quoted prices and the prices they receive from trading. Under fairly general assumptions, we demonstrate how the trader can learn the posterior distribution over the latent states, and explicitly solve the latent optimal trading problem. We provide a verification theorem, and a methodology for calibrating the model by deriving a variation of the expectation-maximization algorithm. To illustrate the efficacy of the optimal strategy, we demonstrate its performance through simulations and compare it to strategies which ignore learning in the latent factors. We also provide calibration results for a particular model using Intel Corporation stock as an example.