Experimental Assortments for Choice Estimation and Nest Identification
Xintong Yu, Will Ma, Michael Zhao

TL;DR
This paper introduces a structured, efficient experiment design for estimating choice models and identifying nests in Nested Logit models, validated through extensive simulations and real-world data from Dream11.
Contribution
It proposes a logarithmic-sample complexity experiment design for choice estimation and a new algorithm for nest identification in Nested Logit models, improving accuracy and interpretability.
Findings
Outperforms heuristic designs in simulations
Successfully identified nests from real user data
Achieved better out-of-sample prediction than feature-based clustering
Abstract
What assortments (subsets of items) should be offered, to collect data for estimating a choice model over total items? We propose a structured, non-adaptive experiment design requiring only distinct assortments, each offered repeatedly, that consistently outperforms randomized and other heuristic designs across an extensive numerical benchmark that estimates multiple different choice models under a variety of (possibly mis-specified) ground truths. We then focus on Nested Logit choice models, which cluster items into "nests" of close substitutes. Whereas existing Nested Logit estimation procedures assume the nests to be known and fixed, we present a new algorithm to identify nests based on collected data, which when used in conjunction with our experiment design, guarantees correct identification of nests under any Nested Logit ground truth. Our experiment design was…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSports Analytics and Performance · Consumer Market Behavior and Pricing · Advanced Bandit Algorithms Research
