Using Natural Language Processing Techniques for Stock Return Predictions

54 Pages Posted: 28 Mar 2017  

Ming Chew

University of California, Berkeley, Haas School of Business, Financial Engineering, Students

Sahil Puri

University Of California, Berkeley, Haas School of Business, Financial Engineering

Arsh Sood

University of California, Berkeley, Haas School of Business, Financial Engineering, Students

Adam Wearne

University of California, Berkeley, Haas School of Business, Financial Engineering, Students

Date Written: March 7, 2017

Abstract

Our Applied Finance Project aims to develop a framework to determine if financial news headlines have meaningful impact on stock prices. This framework is a novel structure that primarily leverages on existing Natural Language Processing, including Name Entity Recognition, and Global Vector for Word Representation (GloVe) model, before combining them with techniques such as k-means clustering and portfolio optimization. The subsequent study on events with predictive abilities could be of interest to institutional investors.

Starting with 1.8 million financial news headlines obtained from the Internet Archive: Wayback Machine, we successfully identified several events with meaningful post-event drifts. These events include situations where the equities of a firm are oversold, approval is given to a firm, a deal or agreement is signed as well as when an advisor is hired. The out-of-sample information ratios for these events are between a range of -1.02 and 0.76. The events we identified are by no means exhaustive, signifying the potential of our model.

Keywords: NLP, Portfolio Optimization, GloVe, K-Means Clustering, S&P 500, Financial News Headlines

JEL Classification: O33, G14

Suggested Citation

Chew, Ming and Puri, Sahil and Sood, Arsh and Wearne, Adam, Using Natural Language Processing Techniques for Stock Return Predictions (March 7, 2017). Available at SSRN: https://ssrn.com/abstract=2940564 or http://dx.doi.org/10.2139/ssrn.2940564

Ming Chew

University of California, Berkeley, Haas School of Business, Financial Engineering, Students ( email )

2220 Piedmont Avenue
Berkeley, CA
United States

Sahil Puri (Contact Author)

University Of California, Berkeley, Haas School of Business, Financial Engineering ( email )

1328 Colony Plz
Newport Beach, CA 92660
United States
2482701055 (Phone)

Arsh Sood

University of California, Berkeley, Haas School of Business, Financial Engineering, Students ( email )

2220 Piedmont Avenue
Berkeley, CA
United States

Adam Wearne

University of California, Berkeley, Haas School of Business, Financial Engineering, Students ( email )

2220 Piedmont Avenue
Berkeley, CA
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
1,315
rank
13,119
Abstract Views
4,512
PlumX