Dear colleagues,

The Department of Economics cordially invites you to the ad-hoc Economics Research Seminar (Department Seminar) on Wednesday, December 13^th, with

Philippe Goulet Coulombe

(Université du Québec à Montréal)

on

"Maximally Machine-Learnable Portfolios"

Abstract: When it comes to stock returns, any form of predictability can bolster risk-adjusted profitability. We develop a collaborative machine learning algorithm that optimizes portfolio weights so that the resulting synthetic security is maximally predictable. Precisely, we introduce MACE, a multivariate extension of Alternating Conditional Expectations that achieves the aforementioned goal by wielding a Random Forest on one side of the equation, and a constrained Ridge Regression on the other. There are two key improvements with respect to Lo and MacKinlay's original maximally predictable portfolio approach. First, it accommodates for any (nonlinear) forecasting algorithm and predictor set. Second, it handles large portfolios. We conduct exercises at the daily and monthly frequency and report significant increases in predictability and profitability using very little conditioning information. Interestingly, predictability is found in bad as well as good times, and MACE successfully navigates the debacle of 2022.

Date: Wednesday, December 13^th

Time: 2.30 to 3.30 pm (CET)

Location: building D4, 2^nd floor, room D4.2.008

With best regards,

Harald Oberhofer

---

Univ.-Prof. Dr. Harald Oberhofer

Department of Economics

WU Vienna University of Economics and Business

Phone: +43/1/31336-4984

Mail: harald.oberhofer@wu.ac.at

Webpage: https://www.wu.ac.at/en/economics/people/oberhofer-h/

Austrian Institute of Economic Research (WIFO)

Phone: +43/1/7982601-468

Mail: harald.oberhofer@wifo.ac.at

Webpage: http://www.wifo.ac.at/harald_oberhofer