Using Survival Prediction Techniques to Learn Consumer-Specific Reservation Price Distributions
A consumer’s “reservation price” (RP) is the highest
price that s/he is willing to pay for one unit of a speci
fied product or service. A retailer who knew each consumer’s RP could optimize profits by using his/her RP to set a personalized price. While consumers will not
volunteer their RPs, we may be able to predict it, based
on each consumer’s specific information, using a model
learned from earlier consumer transactions.
This paper applies survival prediction techniques to predict consumer-specific RP distributions. This is based
on a stochastic model that incorporates the inherent uncertainty of RP. Note that the stochasticity of this framework solves a long-standing conceptual conflict about
RP in the marketing literature. Moreover, within this
stochastic setting, consumers’ purchasing choices are
equivalent to the censored observations in survival analysis. This allows us to use the rich tools from survival
analysis and prediction to solve the RP estimation problem. We run many experiments on realistic data, to empirically compare various models from three fields (survival analysis, machine learning and economics) – e.g.,
Cox model and multi-task logistic regression. Those
models, based on our stochastic RP setting, performed
very well (under three different criteria), on the task of
estimating consumer-specific RP values, which shows
that our stochastic RP framework can be effective.
Citation
P. Jin,
R. Greiner,
M. Wei,
G. Haeubl.
"Using Survival Prediction Techniques to Learn Consumer-Specific Reservation Price Distributions".
NIPS Workshop on Transactional Machine Learning and E-Commerce, pp n/a, December 2014.
Keywords: |
reservation price, marketing, machine learning, survival prediction |
Category: |
In Workshop |
Web Links: |
NIPS Workshops |
BibTeX
@misc{Jin+al:14,
author = {Ping Jin and Russ Greiner and Muyu Wei and Gerald Haeubl},
title = {Using Survival Prediction Techniques to Learn Consumer-Specific
Reservation Price Distributions},
Pages = {n/a},
booktitle = {NIPS Workshop on Transactional Machine Learning and E-Commerce},
year = 2014,
}
Last Updated: February 11, 2020
Submitted by Sabina P