Sensitivity of Vehicle Market Share Predictions to Alternative Discrete Choice Model Specifications

2013 ◽  
Author(s):  
C. Grace Heckmann ◽  
Jeremy J. Michalek ◽  
W. Ross Morrow ◽  
Yimin Liu
Keyword(s):  
Utility Function ◽  
Market Share ◽  
Predictive Accuracy ◽  
Choice Model ◽  
Forecast Error ◽  
Revealed Preference ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Vehicle Market ◽  
Random Guessing

When design decisions are informed by consumer choice models, uncertainty in the choice model and its share predictions creates uncertainty for the designer. We take a first step in investigating the variation in and accuracy of market share predictions by characterizing fit and forecast accuracy of multinomial logit, mixed logit, and nested logit models over a variety of utility function specifications for the US light duty new vehicle market. Using revealed preference data for years 2004–2006, we estimate a multinomial logit model for each combination of a chosen set of utility function covariates found in the literature. We then use each of the models to predict vehicle shares for the 2007 market and examine several metrics to measure fit and predictive accuracy. We find that the best models selected using any of the proposed metrics outperform random guessing yet retain substantial error in fit and prediction for individual vehicle models. For example, with no information (random guessing) 30% of share predictions are within 0.2% absolute share error in a market with an average share of ∼0.4%, whereas for the best models 70% are within 0.2% (for the 2007 vehicle market this translates to an error of ∼33,000 units sold). Share predictions are sensitive to the presence of utility covariates but less sensitive to the form. Models that perform well on one metric tend to perform well on the other metrics as well. In particular, models selected for best fit have comparable forecast error to those with the best forecasts, and residual error in model fit is a major source of forecast error.

Sensitivity of Vehicle Market Share Predictions to Discrete Choice Model Specification

2014 ◽  
Vol 136 (12) ◽  
Author(s):  
C. Grace Haaf ◽  
Jeremy J. Michalek ◽  
W. Ross Morrow ◽  
Yimin Liu
Keyword(s):  
Market Share ◽  
Discrete Choice ◽  
Consumer Choice ◽  
Predictive Accuracy ◽  
Choice Model ◽  
Choice Models ◽  
Discrete Choice Models ◽  
Model Fit ◽  
Model Specification ◽  
Vehicle Market

When design decisions are informed by consumer choice models, uncertainty in choice model predictions creates uncertainty for the designer. We investigate the variation and accuracy of market share predictions by characterizing fit and forecast accuracy of discrete choice models for the US light duty new vehicle market. Specifically, we estimate multinomial logit models for 9000 utility functions representative of a large literature in vehicle choice modeling using sales data for years 2004–2006. Each model predicts shares for the 2007 and 2010 markets, and we compare several quantitative measures of model fit and predictive accuracy. We find that (1) our accuracy measures are concordant: model specifications that perform well on one measure tend to also perform well on other measures for both fit and prediction. (2) Even the best discrete choice models exhibit substantial prediction error, stemming largely from limited model fit due to unobserved attributes. A naïve “static” model, assuming share for each vehicle design in the forecast year = share in the last available year, outperforms all 9000 attribute-based models when predicting the full market one year forward, but attribute-based models can predict better for four year forward forecasts or new vehicle designs. (3) Share predictions are sensitive to the presence of utility covariates but less sensitive to covariate form (e.g., miles per gallons versus gallons per mile), and nested and mixed logit specifications do not produce significantly more accurate forecasts. This suggests ambiguity in identifying a unique model form best for design. Furthermore, the models with best predictions do not necessarily have expected coefficient signs, and biased coefficients could misguide design efforts even when overall prediction accuracy for existing markets is maximized.

scholarly journals Railway and road discrete choice model for foreign trade freight between Antioquia and the Port of Cartagena

2016 ◽  
Vol 36 (3) ◽  
pp. 22 ◽  
Author(s):  
Juan Diego Pineda Jaramillo ◽  
Iván Reinaldo Sarmiento Ordosgoitia ◽  
Jorge Eliécer Córdoba Maquilón
Keyword(s):  
Qualitative Research ◽  
Discrete Choice ◽  
Logit Model ◽  
Choice Model ◽  
Stated Preference ◽  
Revealed Preference ◽  
Freight Transportation ◽  
Multinomial Logit Model ◽  
Discrete Choice Model ◽  
The Cost

Most Colombian freight is transported on roads with barely acceptable conditions, and although there is a speculation about the need for a railway for freight transportation, there is not a study in Colombia showing the variables that influence the modal choice by the companies that generate freight transportation. This article presents the calculation of demand for a hypothetical railway through a discrete choice model. It begins with a qualitative research through focus group techniques to identify the variables that influence the choice of persons responsible for the transportation of large commercial companies in Antioquia (Colombia). The influential variables in the election were the cost and service frequency, and these variables were used to apply a Stated Preference (SP) and Revealed Preference (RP) survey, then to calibrate a Multinomial Logit Model (MNL), and to estimate the influence of each of them. We show that the probability of railway choice by the studied companies varies between 67% and 93%, depending on differences in these variables.

Pricing Competition Under Specific Discrete Choice Models

2020 ◽  
Vol 37 (02) ◽  
pp. 2050008
Author(s):  
Farhad Etebari
Keyword(s):  
Discrete Choice ◽  
Logit Model ◽  
Choice Model ◽  
Public Information ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Discrete Choice Models ◽  
Nested Logit ◽  
Nested Logit Model ◽  
Substitution Pattern

Recent developments of information technology have increased market’s competitive pressure and products’ prices turned to be paramount factor for customers’ choices. These challenges influence traditional revenue management models and force them to shift from quantity-based to price-based techniques and incorporate individuals’ decisions within optimization models during pricing process. Multinomial logit model is the simplest and most popular discrete choice model, which suffers from an independence of irrelevant alternatives limitation. Empirical results demonstrate inadequacy of this model for capturing choice probability in the itinerary share models. The nested logit model, which appeared a few years after the multinomial logit, incorporates more realistic substitution pattern by relaxing this limitation. In this paper, a model of game theory is developed for two firms which customers choose according to the nested logit model. It is assumed that the real-time inventory levels of all firms are public information and the existence of Nash equilibrium is demonstrated. The firms adapt their prices by market conditions in this competition. The numerical experiments indicate decreasing firm’s price level simultaneously with increasing correlation among alternatives’ utilities error terms in the nests.

scholarly journals Airport choice model in multiple airport regions

2017 ◽  
Vol 7 (1) ◽  
pp. 1 ◽  
Author(s):  
Claudia Muñoz ◽  
Jorge Cordoba ◽  
Iván Sarmiento
Keyword(s):  
Utility Function ◽  
Choice Model ◽  
Stated Preference ◽  
Multinomial Logit Model ◽  
Air Transportation ◽  
Future Market ◽  
Support Tool ◽  
Modeling Process ◽  
Market Shares ◽  
Crucial Component

Purpose: This study aims to analyze travel choices made by air transportation users in multi airport regions because it is a crucial component when planning passenger redistribution policies. The purpose of this study is to find a utility function which makes it possible to know the variables that influence users’ choice of the airports on routes to the main cities in the Colombian territory.Design/methodology/approach: This research generates a Multinomial Logit Model (MNL), which is based on the theory of maximizing utility, and it is based on the data obtained on revealed and stated preference surveys applied to users who reside in the metropolitan area of Aburrá Valley (Colombia). This zone is the only one in the Colombian territory which has two neighboring airports for domestic flights. The airports included in the modeling process were Enrique Olaya Herrera (EOH) Airport and José María Córdova (JMC) Airport. Several structure models were tested, and the MNL proved to be the most significant revealing the common variables that affect passenger airport choice include the airfare, the price to travel the airport, and the time to get to the airport.Findings and Originality/value: The airport choice model which was calibrated corresponds to a valid powerful tool used to calculate the probability of each analyzed airport of being chosen for domestic flights in the Colombian territory. This is done bearing in mind specific characteristic of each of the attributes contained in the utility function. In addition, these probabilities will be used to calculate future market shares of the two airports considered in this study, and this will be done generating a support tool for airport and airline marketing policies.

scholarly journals Display Optimization for Vertically Differentiated Locations Under Multinomial Logit Preferences

2020 ◽  
Author(s):  
Ali Aouad ◽  
Danny Segev
Keyword(s):  
Optimization Problem ◽  
Approximation Scheme ◽  
Predictive Accuracy ◽  
Choice Model ◽  
Multinomial Logit ◽  
Constant Factor ◽  
Space Representation ◽  
Consideration Sets ◽  
Priority Rules ◽  
Data Set

We introduce a new optimization model, dubbed the display optimization problem, that captures a common aspect of choice behavior, known as the framing bias. In this setting, the objective is to optimize how distinct items (corresponding to products, web links, ads, etc.) are being displayed to a heterogeneous audience, whose choice preferences are influenced by the relative locations of items. Once items are assigned to vertically differentiated locations, customers consider a subset of the items displayed in the most favorable locations before picking an alternative through multinomial logit choice probabilities. The main contribution of this paper is to derive a polynomial-time approximation scheme for the display optimization problem. Our algorithm is based on an approximate dynamic programming formulation that exploits various structural properties to derive a compact state space representation of provably near-optimal item-to-position assignment decisions. As a byproduct, our results improve on existing constant-factor approximations for closely related models and apply to general distributions over consideration sets. We develop the notion of approximate assortments that may be of independent interest and applicable in additional revenue management settings. Lastly, we conduct extensive numerical studies to validate the proposed modeling approach and algorithm. Experiments on a public hotel booking data set demonstrate the superior predictive accuracy of our choice model vis-à-vis the multinomial logit choice model with location bias, proposed in earlier literature. In synthetic computational experiments, our approximation scheme dominates various benchmarks, including natural heuristics—greedy methods, local search, priority rules—and state-of-the-art algorithms developed for closely related models. This paper was accepted by Yinyu Ye, optimization.

A Mode Choice Model for a Public Transport Transfer Center in Istanbul

2011 ◽  
Vol 97-98 ◽  
pp. 606-610
Author(s):  
Huseyın Onur Tezcan ◽  
Fatih Yonar ◽  
Sabahat Topuz Kiremitci
Keyword(s):  
Public Transport ◽  
Logit Model ◽  
Choice Model ◽  
Mode Choice ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Questionnaire Data ◽  
Mode Choice Model

The aim of this study is to understand the reasons behind the mode choice preferences of passengers using a public transport transfer center. For this aim, a questionnaire data obtained at an interim transfer center in Istanbul is utilized. This interim center hosts stops for paratransit, bus and metro modes. A multinomial logit model of modal preferences is estimated and the coefficient results of this model are used to analyze and compare modes.

A Monté Carlo Comparison of Estimators for the Multinomial Logit Model

1989 ◽  
Vol 26 (1) ◽  
pp. 56-68 ◽  
Author(s):  
David S. Bunch ◽  
Richard R. Batsell
Keyword(s):  
Discrete Choice ◽  
Logit Model ◽  
Repeated Measures ◽  
Predictive Accuracy ◽  
Multinomial Logit Model ◽  
Multinomial Logit ◽  
Point Estimation ◽  
Test Statistics ◽  
Chi Square ◽  
Mnl Model

Marketing researchers use the multinomial logit (MNL) model to analyze discrete choice, and estimate parameters either by maximum likelihood (ML) or minimum logit chi square (MLCS). Some controversy persists, however, over which is better. Review articles in marketing recommend ML over MLCS, but the statistics literature suggests that MLCS should be preferred. No studies have directly compared the performance of ML and MLCS in a marketing context. The authors assess the relative performance of ML, MLCS, and three other candidate estimators for MNL marketing applications involving repeated-measures datasets collected by means of multiple-subset designs. In contrast to most previous findings in the statistics literature, the results strongly support the use of ML. ML is found to outperform the other estimators on a variety of point estimation, predictive accuracy, and statistical inference criteria and ML test statistics are found to have asymptotic behavior for datasets involving relatively few replications.

Assortment Optimization and Pricing Under the Multinomial Logit Model with Impatient Customers: Sequential Recommendation and Selection

2021 ◽  
Author(s):  
Pin Gao ◽  
Yuhang Ma ◽  
Ningyuan Chen ◽  
Guillermo Gallego ◽  
Anran Li ◽  
...  
Keyword(s):  
Logit Model ◽  
Choice Model ◽  
Multinomial Logit Model ◽  
Polynomial Time Algorithm ◽  
Time Algorithm ◽  
Multinomial Logit ◽  
Impatient Customers ◽  
Purchasing Decisions ◽  
Assortment Optimization ◽  
Decision Variables

Sequential Recommendation Under the Multinomial Logit Model with Impatient Customers In many applications, customers incrementally view a subset of offered products and make purchasing decisions before observing all the offered products. In this case, the decision faced by a firm is not only what assortment of products to offer, but also in what sequence to offer the products. In “Assortment Optimization and Pricing Under the Multinomial Logit Model with Impatient Customers: Sequential Recommendation and Selection”, Gao, Ma, Chen, Gallego, Li, Rusmevichientong, and Topaloglu propose a choice model where each customer incrementally view the assortment of products in multiple stages, and their patience level determines the maximum number of stages. Under this choice model, the authors develop a polynomial-time algorithm that finds a revenue-maximizing sequence of assortments. If the sequence of assortments is fixed, the problem of finding revenue-maximizing prices can be transformed to a convex program. They combine these results to develop an effective approximation algorithm when both the sequence of assortments and prices are decision variables.

Sign in / Sign up

Export Citation Format

Share Document