The Keys of Predictability: A Comprehensive Study

69 Pages Posted: 21 Mar 2019 Last revised: 4 Apr 2019

See all articles by Giovanni Barone-Adesi

Giovanni Barone-Adesi

University of Lugano; Swiss Finance Institute

Antonietta Mira

Università della Svizzera italiana - InterDisciplinary Institute of Data Science

Matteo Pisati

Universita' della Svizzera Italiana

Date Written: March 20, 2019

Abstract

The problem of market predictability can be decomposed into two parts: predictive models and predictors. At first, we show how the joint employment of model selection and machine learning models can dramatically increase our capability to forecast the equity premium out-of-sample. Secondly, we introduce batteries of powerful predictors which brings the monthly S&P500 R-square to a high level of 24%. Finally, we prove how predictability is a generalized characteristic of U.S. equity markets. For each of the three parts, we consider potential and challenges posed by the new approaches in the asset pricing field.

Keywords: Markets Predictability, Machine Learning, Model Selection

Suggested Citation

Barone-Adesi, Giovanni and Mira, Antonietta and Pisati, Matteo, The Keys of Predictability: A Comprehensive Study (March 20, 2019). Swiss Finance Institute Research Paper No. 19-15. Available at SSRN: https://ssrn.com/abstract=3356736 or http://dx.doi.org/10.2139/ssrn.3356736

Giovanni Barone-Adesi (Contact Author)

University of Lugano ( email )

Via Buffi 13
CH-6904 Lugano
Switzerland
+41 58 666 4671 (Phone)
+41 58 666 46 47 (Fax)

Swiss Finance Institute

c/o University of Geneva
40 Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Antonietta Mira

Università della Svizzera italiana - InterDisciplinary Institute of Data Science ( email )

Via Giuseppe Buffi 13
CH-6900 Lugano, CH-6904
Switzerland

Matteo Pisati

Universita' della Svizzera Italiana ( email )

Via Buffi, 13
Lugano, 6900
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
225
Abstract Views
940
rank
138,169
PlumX Metrics