Relative Valuation with Machine Learning

99 Pages Posted: 17 Dec 2020 Last revised: 24 Apr 2021

See all articles by Paul Geertsema

Paul Geertsema

University of Auckland Business School

Helen Lu

University of Auckland Business School; University of Auckland - Department of Accounting and Finance

Date Written: December 1, 2020

Abstract

We use a decision-tree-based machine learning approach to perform relative valuation. Stocks are valued using market-to-book, enterprise-value-to-assets and enterprise-value-to-sales multiples. Our machine learning models reduce median absolute valuation errors by between 17% and 50% relative to traditional models. The identified valuation drivers are consistent with theoretical predictions derived from a discounted cash flow approach. Accounting variables related to profitability, growth, efficiency and financial soundness are important valuation drivers. The valuations produced by machine learning models behave like fundamental values. A value-weighted strategy that buys (sells) undervalued (overvalued) stocks generates highly significant abnormal returns. When we use models trained on listed firms to value IPOs, machine learning models outperform traditional models in valuation accuracy and can identify mispriced IPOs.

Keywords: Relative Valuation, Fundamental Analysis, Comparable Companies, IPOs, Machine Learning, Gradient Boosting Machines

JEL Classification: G12, G14, M41, C5

Suggested Citation

Geertsema, Paul G. and Lu, Helen, Relative Valuation with Machine Learning (December 1, 2020). Available at SSRN: https://ssrn.com/abstract=3740270 or http://dx.doi.org/10.2139/ssrn.3740270

Paul G. Geertsema

University of Auckland Business School ( email )

12 Grafton Rd
Private Bag 92019
Auckland, 1010
New Zealand

Helen Lu (Contact Author)

University of Auckland Business School ( email )

12 Grafton Rd
Private Bag 92019
Auckland, 1010
New Zealand

HOME PAGE: http://www.business.auckland.ac.nz/people/hlu079

University of Auckland - Department of Accounting and Finance ( email )

Private Bag 92019
Auckland 1001
New Zealand

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

Paper statistics

Downloads
344
Abstract Views
962
rank
112,290
PlumX Metrics