Amazon-M2
Multilingual shopping sessions and product attributes for next-item recommendation and title generation.
What the resource contains
- Chronological product interaction sequences
- Product titles, local prices, brands, colors and descriptions
- English, German, Japanese, French, Italian and Spanish task splits
Potential uses
- Test cross-locale recommendation
- Study multilingual transfer
- Generate next-product titles
Access & formats
Session / product benchmark files. Repository / linked release. Follow the project’s instructions on GitHub; some resources require external files, registration or approval.
License & reuse
The reviewed README does not establish comprehensive data reuse rights. Review the dataset and competition terms separately from baseline code.
Important limitations
Locales and evaluation tasks use different splits. Historical local prices are not live price monitoring.
Source & attribution
HaitaoMao — 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.
JSONL · External dependencies
Coveo SIGIR Ecommerce
coveooss
Search and browsing sessions for studying ecommerce recommendation and purchase intent.
CSV · Application / terms
Coveo Shopper Intent
coveooss
Session-level ecommerce events supporting research into early prediction of shopping intent.
CSV · Application / terms