Whence LASSO? A Rational Interpretation
Rotman School of Management Working Paper No. 4279679
George Mason University School of Business Research Paper No. 4279679
56 Pages Posted: 22 Nov 2022 Last revised: 17 May 2024
Date Written: June 19, 2021
Abstract
This paper rationalizes the use of LASSO for return predictions based on robust optimization with uncertain fat-tail priors. Our theory avoids assumptions of heuristic learning or restrictive priors
made in the statistical interpretation of LASSO by its inventor Tibshirani (1996). In our setting, agents (arbitrageurs) are uncertain about the scale of fat-tail shocks. In equilibrium, they rationally discard a wide range of ambiguous signals and respond conservatively to almost unambiguous signals. Using this LASSO equivalent strategy, arbitrageurs can amass extra market power which induces a "cartel" to protect their total trading profits from being competed away. This result shows a new mechanism for limits to arbitrage.
Keywords: LASSO, Fat Tails, Model Risk, Robust Optimization, Limits to Arbitrage
JEL Classification: C44, D81, G12, G14
Suggested Citation: Suggested Citation