Practice Prize Winner—A Nested Logit Model of Product and Transaction-Type Choice for Planning Automakers' Pricing and Promotions

Marketing Science · 2008 · Volume 27 · Issue 4

Abstract

We develop a consumer response model to evaluate and plan pricing and promotions in durable-good markets. We discuss its implementation in the U.S. automotive industry, which “spends” about $45 billion each year in price promotions. The approach is based on a random effects multinomial nested logit model of product (e.g., a vehicle model, such as Hyundai Tucson), and transaction-type choice. Transaction types include combinations of acquisition types (e.g., purchase versus lease) and pricing instruments (cash rebates, reduced APR financing, lease payment discounts). We estimate the model using hierarchical Bayes methods to capture response heterogeneity at the local market level. We find key characteristics unique to durable-good markets. First, consumers are heterogeneous in both their brand and transaction-type preferences. Second, consumers differ in their overall price sensitivity as well as in their relative sensitivity to alternative pricing instruments (e.g., cash discounts, reduced monthly payments). Third, the most effective pricing programs tend to be those in which automakers offer consumers a menu of options to choose from (e.g., a choice among a cash discount, reduced interest rate financing, or a lease payment discount). We illustrate the model through an empirical application to a sample of data drawn from J.D. Power transaction records in the entry SUV segment and discuss examples of actual implementations.

Keywords

choice models, nested logit, random coefficients, pricing, promotions, automobiles, hierarchical Bayes

Enable JavaScript for citation tools and additional paper interactions.