Integrating machine learning and discrete choice modeling for enhanced shopping destination choice model
Bibliographic record
Abstract
• Develops a modeling framework using machine learning and econometrics for parcel-level shopping destination choice. • Generates shopping location choice sets based on business types and locations. • Predicts individual shopping location choices using an econometric model considering unobserved behavior variations. • Results show longer travel times decrease routine shopping, while high retail areas attract shoppers variably. This study develops a two-stage modeling framework for parcel-level shopping destination choice, accounting for multi-dimensional factors and the heterogeneity in shopping location choice behavior. The study follows two steps: (i) developing a shopping location choice set generation process comprising feature selection and encompassing business types and locations, and (ii) developing an econometric model to predict individual shopping location choice behavior considering unobserved heterogeneity. The study advances a novel approach of combined machine learning (ML) and random utility-based discrete choice modeling (i.e., mixed logit model (MXL)). Results from the MXL model reveal that the longer the travel time and distance from the central business district, the less likely people are to visit a store for routine shopping (e.g., groceries). The random parameter analysis reveals that although high retail concentration surrounding the desired shopping location should attract individuals for shopping, there will be people who still may not intend to shop at those locations. Similarly, people may be willing to travel to stores requiring longer travel times for special item shopping. The models developed in this study will be implemented within an integrated transport, land use, and energy (iTLE) modeling system to improve the behavioral representation of destination choices.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".