Mitigating choice model ambiguity: A consensus framework and its application to assortment optimization
Bibliographic record
Abstract
Discrete choice models have become a popular tool to accurately predict complex choice behavior. Due to a variety of possible error sources, estimated choice models tend to be subject to ambiguity, inducing different optimal decisions of highly varying quality. This study aims at mitigating choice model ambiguity associated with a given set of models in terms of their ability to yield optimal decisions. We propose a framework and a set of performance metrics to assess the reliability of choice models and their induced decisions. The use of this framework is then exemplified in the context of rank-based choice models for assortment optimization. Extensive sets of numerical results suggest that our proposed approaches indeed allow decision-makers to identify choice models that are likely to produce high quality decisions, boosting confidence in using choice models in practice. While robust optimization on the original set of choice models tends to be rather conservative, we then use the proposed metrics to reduce the size of the ambiguity set, allowing us to improve the expected assortment quality and the overall downside risk. Given the practical usefulness of robust optimization in this context, we further propose a decomposition algorithm, solving the optimization problem in a fraction of the original time and revealing that only a few among a large set of choice models are determinant in optimal robust solutions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.016 | 0.040 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".