Supervised Machine Learning for Eliciting Individual Reservation Values

64 Pages Posted: 13 May 2019

See all articles by John A. Clithero

John A. Clithero

Lundquist College of Business, University of Oregon

Jae Joon Lee

Claremont Colleges - Claremont Graduate University

Joshua Tasoff

Claremont Colleges - Claremont Graduate University

Date Written: April 29, 2019

Abstract

Direct elicitation, guided by theory, is the standard method for eliciting individual-level latent variables. We present an alternative approach, supervised machine learning (SML), and apply it to measuring individual valuations for goods. We find that the approach is superior for predicting out-of-sample individual purchases relative to a canonical direct-elicitation approach, the Becker-DeGroot-Marschak (BDM) method. The BDM is imprecise and systematically biased by understating valuations. We characterize the performance of SML using a variety of estimation methods and data. The simulation results suggest that prices set by SML would increase revenue by 22% over the BDM, using the same data.

Keywords: Machine Learning, Willingness to Pay, BDM, Random Forest, Boosted Regression, Response Time

JEL Classification: C81, C91, D12

Suggested Citation

Clithero, John A. and Lee, Jae Joon and Tasoff, Joshua, Supervised Machine Learning for Eliciting Individual Reservation Values (April 29, 2019). Available at SSRN: https://ssrn.com/abstract=3380039 or http://dx.doi.org/10.2139/ssrn.3380039

John A. Clithero (Contact Author)

Lundquist College of Business, University of Oregon ( email )

Lundquist College of Business
1208 University of Oregon
Eugene, OR 97403
United States

Jae Joon Lee

Claremont Colleges - Claremont Graduate University ( email )

150 E. Tenth Street
Claremont, CA 91711
United States

Joshua Tasoff

Claremont Colleges - Claremont Graduate University ( email )

150 E. Tenth Street
Claremont, CA 91711
United States

HOME PAGE: http://sites.cgu.edu/tasoffj/

Register to save articles to
your library

Register

Paper statistics

Downloads
7
Abstract Views
99
PlumX Metrics