The Macroeconomy and the Cross-Section of International Equity Index Returns: A Machine Learning Approach

Research output: Working paperOther research output

Abstract

The paper evaluates the out-of-sample predictive ability of machine learning methods in the cross-section of international equity index returns using both firm fundamentals and macroeconomic predictors. The study performs a horserace between classical forecasting methods and the machine learning repertoire, including principal component analysis, partial least squares, and neural networks. Macroeconomic signals seem to substantially improve out-of-sample performance, especially when non-linear features are incorporated via neural networks.
Original languageEnglish
Place of PublicationTilburg
PublisherSSRN
Number of pages62
DOIs
Publication statusPublished - 13 Nov 2019

Fingerprint

Equity
Macroeconomics
Neural networks
Macroeconomy
Cross section
Machine learning
Partial least squares
Learning methods
Forecasting method
Principal component analysis
Predictive ability
Predictors

Keywords

  • Asset Pricing
  • Equity Indices
  • Return Forecasting
  • Machine Learning
  • Neural Networks
  • Macroeconomic predictability

Cite this

@techreport{7764215ab4c4446388a9583d3b00821c,
title = "The Macroeconomy and the Cross-Section of International Equity Index Returns: A Machine Learning Approach",
abstract = "The paper evaluates the out-of-sample predictive ability of machine learning methods in the cross-section of international equity index returns using both firm fundamentals and macroeconomic predictors. The study performs a horserace between classical forecasting methods and the machine learning repertoire, including principal component analysis, partial least squares, and neural networks. Macroeconomic signals seem to substantially improve out-of-sample performance, especially when non-linear features are incorporated via neural networks.",
keywords = "Asset Pricing, Equity Indices, Return Forecasting, Machine Learning, Neural Networks, Macroeconomic predictability",
author = "Popescu, {Andreea Victoria}",
year = "2019",
month = "11",
day = "13",
doi = "10.2139/ssrn.3480042",
language = "English",
publisher = "SSRN",
type = "WorkingPaper",
institution = "SSRN",

}

TY - UNPB

T1 - The Macroeconomy and the Cross-Section of International Equity Index Returns

T2 - A Machine Learning Approach

AU - Popescu, Andreea Victoria

PY - 2019/11/13

Y1 - 2019/11/13

N2 - The paper evaluates the out-of-sample predictive ability of machine learning methods in the cross-section of international equity index returns using both firm fundamentals and macroeconomic predictors. The study performs a horserace between classical forecasting methods and the machine learning repertoire, including principal component analysis, partial least squares, and neural networks. Macroeconomic signals seem to substantially improve out-of-sample performance, especially when non-linear features are incorporated via neural networks.

AB - The paper evaluates the out-of-sample predictive ability of machine learning methods in the cross-section of international equity index returns using both firm fundamentals and macroeconomic predictors. The study performs a horserace between classical forecasting methods and the machine learning repertoire, including principal component analysis, partial least squares, and neural networks. Macroeconomic signals seem to substantially improve out-of-sample performance, especially when non-linear features are incorporated via neural networks.

KW - Asset Pricing

KW - Equity Indices

KW - Return Forecasting

KW - Machine Learning

KW - Neural Networks

KW - Macroeconomic predictability

U2 - 10.2139/ssrn.3480042

DO - 10.2139/ssrn.3480042

M3 - Working paper

BT - The Macroeconomy and the Cross-Section of International Equity Index Returns

PB - SSRN

CY - Tilburg

ER -