Deep Learning, Text, and Patent Valuation

42 Pages Posted: 28 Feb 2021

See all articles by Po-Hsuan Hsu

Po-Hsuan Hsu

National Tsing Hua University - Department of Quantitative Finance; National University of Singapore (NUS) - Asian Bureau of Finance and Economic Research (ABFER)

Dokyun Lee

Boston University - Questrom School of Business

Prasanna Tambe

Wharton School, U. Pennsylvania

David H. Hsu

University of Pennsylvania - Management Department

Date Written: November 16, 2020

Abstract

This paper uses deep learning and natural language processing (NLP) methods on the US patent corpus to evaluate their predictive power in estimating two measures of patent value: (i) investor reaction to patent announcements as measured in Kogan et al., 2017 and (ii) forward citations. While forward citations have traditionally been used as measures of economic value in the literature, their utility is mainly retrospective. Contemporaneous predictions of patent value, as embodied in investor reactions to patent grants, can be important for managers and policy-makers for prospective decision making. We compare the prediction performance of models using the structured features of the patent (number of citations, technology class, etc.) to deep learning and NLP methods. Relative to linear regression models using the same features, deep learning models reduce mean absolute error (MAE) by approximately 32%. Incorporating patent text further lowers the MAE by 13%.

Keywords: patent value; deep learning; natural language processing

Suggested Citation

Hsu, Po-Hsuan and Lee, Dokyun and Tambe, Prasanna and Hsu, David H., Deep Learning, Text, and Patent Valuation (November 16, 2020). Available at SSRN: https://ssrn.com/abstract=3758388 or http://dx.doi.org/10.2139/ssrn.3758388

Po-Hsuan Hsu

National Tsing Hua University - Department of Quantitative Finance ( email )

101, Section 2, Kuang-Fu Road
Hsinchu, Taiwan 300
China

National University of Singapore (NUS) - Asian Bureau of Finance and Economic Research (ABFER) ( email )

BIZ 2 Storey 4, 04-05
1 Business Link
Singapore, 117592
Singapore

Dokyun Lee

Boston University - Questrom School of Business ( email )

595 Commonwealth Avenue
Boston, MA MA 02215
United States

Prasanna Tambe

Wharton School, U. Pennsylvania ( email )

Philadelphia, PA 19104
United States

David H. Hsu (Contact Author)

University of Pennsylvania - Management Department ( email )

The Wharton School
Philadelphia, PA 19104-6370
United States
215-746-0125 (Phone)
215-898-0401 (Fax)

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

Paper statistics

Downloads
576
Abstract Views
2,143
Rank
95,619
PlumX Metrics