Asset Embeddings

41 Pages Posted: 20 Jul 2023 Last revised: 13 Feb 2024

See all articles by Xavier Gabaix

Xavier Gabaix

Harvard University - Department of Economics; National Bureau of Economic Research (NBER); Centre for Economic Policy Research (CEPR); European Corporate Governance Institute (ECGI)

Ralph S. J. Koijen

University of Chicago - Booth School of Business; Centre for Economic Policy Research (CEPR); National Bureau of Economic Research (NBER)

Robert Richmond

New York University (NYU) - Department of Finance; National Bureau of Economic Research (NBER)

Motohiro Yogo

Princeton University - Department of Economics; National Bureau of Economic Research

Date Written: September 14, 2023

Abstract

Firm characteristics are ubiquitously used in economics. These characteristics are often based on readily-available information such as accounting data, but those reflect only a part of investors' information set. We show that useful information about firm characteristics is embedded in investors’ holdings data and, via market clearing, in prices, returns, and trading data. Based on insights from the recent artificial intelligence (AI) and machine learning (ML) literature, in which unstructured data (e.g., words or speech) are represented as continuous vectors in a potentially high-dimensional space, we propose to learn asset embeddings from investors' holdings data. Indeed, just as documents arrange words that can be used to uncover word structures via embeddings, investors organize assets in portfolios that can be used to uncover firm characteristics that investors deem important via asset embeddings. This broad theme provides a natural bridge to connect recent advances in the fields of AI and ML to finance and economics. Specifically, we show how language models, including transformer models that feature prominently in large language models such as BERT and GPT, can handle numerical information, and in particular holdings data to estimate asset embeddings. We provide initial evidence on the value added of asset embeddings through a series of applications in the context of firm valuations, return comovement, and uncovering asset substitution patterns. As a by-product, the models generate investor embeddings, which can be used to measure investor similarity. We propose a programmatic list of potential applications of asset and investor embeddings to finance and economics more generally.

Keywords: Asset embeddings, transformer models, artificial intelligence, machine learning

Suggested Citation

Gabaix, Xavier and Koijen, Ralph S. J. and Richmond, Robert and Yogo, Motohiro, Asset Embeddings (September 14, 2023). Available at SSRN: https://ssrn.com/abstract=4507511 or http://dx.doi.org/10.2139/ssrn.4507511

Xavier Gabaix

Harvard University - Department of Economics ( email )

Littauer Center
Cambridge, MA 02138
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Centre for Economic Policy Research (CEPR)

London
United Kingdom

European Corporate Governance Institute (ECGI)

c/o the Royal Academies of Belgium
Rue Ducale 1 Hertogsstraat
1000 Brussels
Belgium

Ralph S. J. Koijen (Contact Author)

University of Chicago - Booth School of Business ( email )

5807 S. Woodlawn Avenue
Chicago, IL 60637
United States

HOME PAGE: http://faculty.chicagobooth.edu/ralph.koijen/

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Robert Richmond

New York University (NYU) - Department of Finance ( email )

Stern School of Business
44 West 4th Street
New York, NY 10012-1126
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Motohiro Yogo

Princeton University - Department of Economics ( email )

Julis Romo Rabinowitz Building
Princeton, NJ 08544
United States

HOME PAGE: http://sites.google.com/site/motohiroyogo/

National Bureau of Economic Research

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
3,873
Abstract Views
11,070
Rank
5,367
PlumX Metrics