PulseAugur
EN
LIVE 10:50:38

New framework enhances Markov chain choice models with panel data

Researchers have introduced a new framework for Markov chain (MC) choice models utilizing panel data, which accounts for dependencies between a customer's historical transactions. This approach incorporates partial-ordering preference information and proposes novel expectation-maximization (EM) algorithms for parameter estimation. The proposed EM algorithms demonstrated superior performance compared to existing methods on synthetic and sushi datasets, while also presenting computational results for conditional choice prediction and assortment optimization problems. AI

IMPACT This research advances choice modeling techniques, potentially improving personalized recommendations and assortment optimization in various applications.

RANK_REASON The cluster contains an academic paper detailing a new framework and algorithms for choice modeling.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New framework enhances Markov chain choice models with panel data

COVERAGE [2]

  1. arXiv stat.ML TIER_1 English(EN) · Yalcin Akcay, Gerardo Berbeglia, Young-San Lin ·

    Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data

    arXiv:2607.09817v1 Announce Type: cross Abstract: We propose a framework for the Markov chain (MC) choice model with panel data, including parameter estimation, personalized choice prediction, and personalized assortment optimization. In contrast to the traditional setting, which…

  2. arXiv stat.ML TIER_1 English(EN) · Young-San Lin ·

    Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data

    We propose a framework for the Markov chain (MC) choice model with panel data, including parameter estimation, personalized choice prediction, and personalized assortment optimization. In contrast to the traditional setting, which assumes that each transaction is independently dr…