Machine Valuation

56 Pages Posted: 7 Sep 2019

See all articles by Paul Geertsema

Paul Geertsema

University of Auckland - Department of Accounting and Finance

Helen Lu

University of Auckland - Department of Accounting and Finance

Date Written: September 4, 2019

Abstract

We present a machine learning approach to firm valuation that requires only historical accounting data as input. The machine learning model generates a median absolute percentage error of 17.2% in out-of-sample firm value predictions. The model out-performs a sample of final-year finance students (41.3%) and individual analyst forecasts of one-year-ahead firm value (22.4%). We show that subsequent market valuations move towards the model valuation, generating return predictability over horizons of up to five years.

Keywords: valuation; asset pricing; return predictability; machine learning; gradient boosted trees

JEL Classification: G12; G14; C38

Suggested Citation

Geertsema, Paul G. and Lu, Helen, Machine Valuation (September 4, 2019). Available at SSRN: https://ssrn.com/abstract=3447683 or http://dx.doi.org/10.2139/ssrn.3447683

Paul G. Geertsema (Contact Author)

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

12 Grafton Rd
Private Bag 92019
Auckland, 1010
New Zealand

Helen Lu

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

Private Bag 92019
Auckland 1001
New Zealand

Register to save articles to
your library

Register

Paper statistics

Downloads
105
Abstract Views
417
rank
258,151
PlumX Metrics