Machine Invasion: Automation in Information Processing and the Cross Section of Stock Returns

58 Pages Posted: 24 Aug 2018 Last revised: 25 Mar 2020

See all articles by Raunaq S. Pungaliya

Raunaq S. Pungaliya

Sungkyunkwan University (SKK) Graduate School of Business

Yanbo Wang

Sungkyunkwan University (SKK) Graduate School of Business

Date Written: August 1, 2018

Abstract

We separate downloads on the SEC EDGAR database into human and machine actions by the intensity of information retrieval (Ryans, 2017). The split shows that the extent of machine downloads has risen 35 times since 2004, accounting for over 96% of total downloads as of 2016. We formally investigate the relationship of machine automation in information processing and the cross-section of stock returns. We find that stocks in the lowest quintile of machine coverage outperform those in the highest quintile by 6 to 7% annually after adjusting for risk. Our results are consistent with recent theoretical work on big data (Begenau, Farboodi, and Veldkamp, 2018) and are supported by a natural experiment on the implementation of XBRL tags that enabled machine readable financial disclosure.

Keywords: Machine, Automation, Information, Cross-Section of Stock Returns

JEL Classification: G1,D8, J1

Suggested Citation

Pungaliya, Raunaq S. and Wang, Yanbo, Machine Invasion: Automation in Information Processing and the Cross Section of Stock Returns (August 1, 2018). Available at SSRN: https://ssrn.com/abstract=3221816 or http://dx.doi.org/10.2139/ssrn.3221816

Raunaq S. Pungaliya

Sungkyunkwan University (SKK) Graduate School of Business ( email )

53 Myeongnyun-dong 3-ga Jongno-ju
Guro-gu
Seoul, 110-745
Korea, Republic of (South Korea)

Yanbo Wang (Contact Author)

Sungkyunkwan University (SKK) Graduate School of Business ( email )

53 Myeongnyun-dong 3-ga Jongno-ju
Guro-gu
Seoul, 110-745
Korea, Republic of (South Korea)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
330
Abstract Views
2,103
Rank
167,196
PlumX Metrics