# Generative Recommendation on Amazon Phone (Cold)

Source: [Generative Recommendation on Amazon Phone (Cold)](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T09:54:03.860Z

Evaluation of generative recommendation performance on the cold-start subset of the Amazon Phone dataset, measured using ranking metrics NDCG and Recall at cutoffs K=10, 20, and 50.

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 | Generative Recommendation |
| Dataset (including any stated split) | Amazon Phone (Cold) |
| Metric | NDCG@10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [NDCG@10](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=NDCG%4010>): Higher is better; unit: PERCENT.

- [NDCG@20](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=NDCG%4020>): Higher is better; unit: PERCENT.

- [NDCG@50](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=NDCG%4050>): Higher is better; unit: PERCENT.

- [Recall@10](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=Recall%4010>): Higher is better; unit: PERCENT.

- [Recall@20](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=Recall%4020>): Higher is better; unit: PERCENT.

- [Recall@50](<https://www.sota2.com/research/sota/generative-recommendation-on-amazon-phone-cold.md?metric=Recall%4050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDCG@10 | Result date | Report paper |
| --- | --- | --- | --- |
| GenRecEdit | 0.52 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| Finetune | 0.41 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| Retrain | 0.33 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| SpecGR | 0.18 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| TIGER | 0.14 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| LC-Rec | 0.04 | Not recorded | 69b8e03b0636e5bf4afbed5e |
| VQ-Rec | 0 | Not recorded | 69b8e03b0636e5bf4afbed5e |

### GenRecEdit

NDCG@10: 0.52. Result ID: 69b924ab47f34ce924a243c9.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

Recorded evaluation configuration: {"Method Category":"Cold-start-based"}. This record does not assert independent reproduction.

### Finetune

NDCG@10: 0.41. Result ID: 69b924ab47f34ce924a243c7.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

Recorded evaluation configuration: {"Method Category":"Cold-start-based"}. This record does not assert independent reproduction.

### Retrain

NDCG@10: 0.33. Result ID: 69b924ab47f34ce924a243c6.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

Recorded evaluation configuration: {"Method Category":"Cold-start-based"}. This record does not assert independent reproduction.

### SpecGR

NDCG@10: 0.18. Result ID: 69b924ab47f34ce924a243c8.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa751a1e209131cea65cb7.md>)

Recorded evaluation configuration: {"Method Category":"Cold-start-based"}. This record does not assert independent reproduction.

### TIGER

NDCG@10: 0.14. Result ID: 69b924ab47f34ce924a243c4.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710f1e209131cea4ef39.md>)

Recorded evaluation configuration: {"Method Category":"Semantic ID-based"}. This record does not assert independent reproduction.

### LC-Rec

NDCG@10: 0.04. Result ID: 69b924ab47f34ce924a243c5.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594c5.md>)

Recorded evaluation configuration: {"Method Category":"Semantic ID-based"}. This record does not assert independent reproduction.

### VQ-Rec

NDCG@10: 0. Result ID: 69b924ab47f34ce924a243c3.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e03b0636e5bf4afbed5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e911e209131cea40b04.md>)

Recorded evaluation configuration: {"Method Category":"Semantic ID-based"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
