Post-Fundamentals Drift in Stock Prices: A Machine-Learning Approach

71 Pages Posted: 27 Jan 2020 Last revised: 21 May 2020

See all articles by Doron Avramov

Doron Avramov

Interdisciplinary Center (IDC) Herzliyah

Guy Kaplanski

Bar-Ilan University - Graduate School of Business Administration

Avanidhar Subrahmanyam

University of California, Los Angeles (UCLA) - Finance Area; Institute of Global Finance, UNSW Business School; Financial Research Network (FIRN)

Date Written: January 8, 2020

Abstract

Deviations of accounting fundamentals from their preceding moving averages forecast drifts
in stock prices. Comprehensive machine-learning measures based on such deviations yield
annualized alphas that exceed 18% (8%) for equal- (value-) weighted portfolios. The return
predictability goes beyond momentum, 52-week highs, profitability, and other prominent
anomalies. The profitability applies strongly to the long-leg and survives value-weighting and
excluding microcaps. We provide evidence that the predictability arises because investors
underreact to deviations from prevailing fundamental anchors.

JEL Classification: G12, G14

Suggested Citation

Avramov, Doron and Kaplanski, Guy and Subrahmanyam, Avanidhar, Post-Fundamentals Drift in Stock Prices: A Machine-Learning Approach (January 8, 2020). Available at SSRN: https://ssrn.com/abstract=3507512 or http://dx.doi.org/10.2139/ssrn.3507512

Doron Avramov

Interdisciplinary Center (IDC) Herzliyah ( email )

P.O. Box 167
Herzliya, 46150
Israel

Guy Kaplanski

Bar-Ilan University - Graduate School of Business Administration ( email )

Ramat Gan
Israel

Avanidhar Subrahmanyam (Contact Author)

University of California, Los Angeles (UCLA) - Finance Area ( email )

Los Angeles, CA 90095-1481
United States
310-825-5355 (Phone)
310-206-5455 (Fax)

Institute of Global Finance, UNSW Business School

Sydney, NSW 2052
Australia

Financial Research Network (FIRN)

C/- University of Queensland Business School
St Lucia, 4071 Brisbane
Queensland
Australia

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
429
Abstract Views
1,468
rank
72,669
PlumX Metrics