# Session-based recommendation on SIGIR E-commerce Data Challenge Leaderboard 2021 Source: [Session-based recommendation on SIGIR E-commerce Data Challenge Leaderboard 2021]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:50:21.090Z Evaluation of session-based recommendation performance using MRR and F1 metrics on the SIGIR E-commerce Data Challenge Leaderboard 2021 dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Session-based recommendation | | Dataset (including any stated split) | SIGIR E-commerce Data Challenge Leaderboard 2021 | | Metric | MRR | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [MRR](): Higher is better; unit: PERCENT. - [F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | MRR | Result date | Report paper | | --- | --- | --- | --- | | Full Ensemble | 27.84 | Not recorded | 68fa6a541e209131cea276e0 | | Final Ensemble | 27.71 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-2 | 27.46 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-3 | 27.41 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-FC-2 | 27.26 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-FC-3 | 26.93 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-S-3 | 26.71 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-S-2 | 26.69 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-FC-1 | 26.4 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-IM-1 | 26.38 | Not recorded | 68fa6a541e209131cea276e0 | | XLNET-S-1 | 26.34 | Not recorded | 68fa6a541e209131cea276e0 | | TransfoXL-IM-2 | 24.21 | Not recorded | 68fa6a541e209131cea276e0 | | TransfoXL-IM-3 | 24.06 | Not recorded | 68fa6a541e209131cea276e0 | | TransfoXL-IM-1 | 23.17 | Not recorded | 68fa6a541e209131cea276e0 | ### Full Ensemble MRR: 27.84. Result ID: 698e2a6dffc3901de09b51c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of models":"60"}. This record does not assert independent reproduction. ### Final Ensemble MRR: 27.71. Result ID: 698e2a6dffc3901de09b51bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Number of models":"24"}. This record does not assert independent reproduction. ### XLNET-IM-2 MRR: 27.46. Result ID: 698e2a6dffc3901de09b51b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"2"}. This record does not assert independent reproduction. ### XLNET-IM-3 MRR: 27.41. Result ID: 698e2a6dffc3901de09b51b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"3"}. This record does not assert independent reproduction. ### XLNET-IM-FC-2 MRR: 27.26. Result ID: 698e2a6dffc3901de09b51ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"2"}. This record does not assert independent reproduction. ### XLNET-IM-FC-3 MRR: 26.93. Result ID: 698e2a6dffc3901de09b51bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"3"}. This record does not assert independent reproduction. ### XLNET-S-3 MRR: 26.71. Result ID: 698e2a6dffc3901de09b51b8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"3"}. This record does not assert independent reproduction. ### XLNET-S-2 MRR: 26.69. Result ID: 698e2a6dffc3901de09b51b7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"2"}. This record does not assert independent reproduction. ### XLNET-IM-FC-1 MRR: 26.4. Result ID: 698e2a6dffc3901de09b51b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"1"}. This record does not assert independent reproduction. ### XLNET-IM-1 MRR: 26.38. Result ID: 698e2a6dffc3901de09b51b3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"1"}. This record does not assert independent reproduction. ### XLNET-S-1 MRR: 26.34. Result ID: 698e2a6dffc3901de09b51b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"1"}. This record does not assert independent reproduction. ### TransfoXL-IM-2 MRR: 24.21. Result ID: 698e2a6dffc3901de09b51bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"2"}. This record does not assert independent reproduction. ### TransfoXL-IM-3 MRR: 24.06. Result ID: 698e2a6dffc3901de09b51be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"3"}. This record does not assert independent reproduction. ### TransfoXL-IM-1 MRR: 23.17. Result ID: 698e2a6dffc3901de09b51bc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Ensemble Strategy":"5-folds","Variant":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.