Modeling, Prediction, Assortment and Price Optimization Under Consumer Choice Behavior
Chenxu Ke et al.
What the paper says
Understanding how consumers make choices is of paramount importance, as it offers insights into consumer purchase behavior across multiple products, enables accurate predictions of future demand, and informs strategic planning and policy formulation. The examination of discrete consumer choice models plays a central role in decoding the decision-making process, offering a clear perspective on how individuals navigate among multiple options. These models are instrumental in evaluating a wide range of consumer decisions, such as product selection, brand preference, and the impact of various factors on choice. With the growth of e-commerce and the increasing emphasis on data-driven modeling and decision-making, consumer choice models have garnered significant attention. This rising interest underscores their relevance in the digital marketplace and their contribution to a deeper understanding of consumer behavior. The objective of this work is to present a comprehensive overview of choice modeling, covering both the theoretical underpinnings of widely adopted discrete choice models (e.g., the multinomial logit model), and those integrating contemporary elements like network externalities and ranking effects. It also discusses optimal solutions or efficient approximation heuristics for price and assortment optimization problems, where consumer choice behavior is governed by various discrete choice models. To facilitate practical business applications, this work offers estimation strategies and techniques to address data-related issues. Additionally, it includes cutting-edge advancements such as artificial intelligence and deep learning, and outlines future trends in the realm of operations management with discrete choice models. By delving into the intricate details and mechanisms of these models, this work aims to shed light on the methodological foundations and practical implementations of consumer choice modeling, providing researchers, practitioners, and policymakers with valuable insights into this rich and evolving field.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.