What the resource contains
- More than 5 million behavioral events
- Hashed session identifiers
- Action types and timestamps with a repository sample
Potential uses
- Classify purchase intent
- Study early-session signals
- Evaluate behavioral sequence features
Access & formats
CSV. Application / terms. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.
License & reuse
Research and educational use only under publisher terms; the full release requires an application.
Important limitations
The repository is archived. Historical behavior does not imply current consumer intent, and hashed IDs must not be reidentified.
Source & attribution
coveooss — original GitHub project ↗
Documentation reviewed 2026-09-24. Review scope and licensing notes. Suggest a correction.
Related resources
OTTO Sessions
otto-de
An ecommerce interaction benchmark for predicting what a shopper will click, add to cart, or order next.
Open license stated JSONL · External dependencies
Coveo SIGIR Ecommerce
coveooss
Search and browsing sessions for studying ecommerce recommendation and purchase intent.
Restricted use CSV · Application / terms
Coveo Cross-shop Embeddings
coveooss
Two-shop session and item representations for evaluating transfer and recommendation across retail catalogs.
Restricted use JSON / embedding files · Application / terms