New method learns consumer preferences from bundle sales data

This paper introduces a novel approach for estimating consumer preferences from bundle sales data, a common strategy in retail. The proposed methodology defines a utility model and uses an EM algorithm to estimate the parameters of a valuation distribution, maximizing the likelihood of observed transaction data. The framework is extended to handle unobserved non-purchases, market segments, and synergy effects in bundles, with theoretical results on identifiability and convergence provided. The algorithm offers practical guidance for retailers seeking to leverage bundle sales data to understand customer valuations. AI

IMPACT Provides a methodological advancement for learning consumer preferences from sales data, potentially improving retail strategies.

RANK_REASON Academic paper on a statistical machine learning method. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv stat.ML →

• Setareh Farajollahzadeh

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →