From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908617219768320 |
|---|---|
| author | Kim, Yejin Agah, Shaghayegh Nankani, Mayur Sharma, Neeraj Peng, Feifei Peifer, Maria Hamidian, Sardar Huang, H Howie |
| author_facet | Kim, Yejin Agah, Shaghayegh Nankani, Mayur Sharma, Neeraj Peng, Feifei Peifer, Maria Hamidian, Sardar Huang, H Howie |
| contents | Most recommender systems treat timestamps as numeric or cyclical values, overlooking real-world context such as holidays, events, and seasonal patterns. We propose a scalable framework that uses large language models (LLMs) to generate geo-temporal embeddings from only a timestamp and coarse location, capturing holidays, seasonal trends, and local/global events. We then introduce a geo-temporal embedding informativeness test as a lightweight diagnostic, demonstrating on MovieLens, LastFM, and a production dataset that these embeddings provide predictive signal consistent with the outcomes of full model integrations. Geo-temporal embeddings are incorporated into sequential models through (1) direct feature fusion with metadata embeddings or (2) an auxiliary loss that enforces semantic and geo-temporal alignment. Our findings highlight the need for adaptive or hybrid recommendation strategies, and we release a context-enriched MovieLens dataset to support future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations Kim, Yejin Agah, Shaghayegh Nankani, Mayur Sharma, Neeraj Peng, Feifei Peifer, Maria Hamidian, Sardar Huang, H Howie Information Retrieval Most recommender systems treat timestamps as numeric or cyclical values, overlooking real-world context such as holidays, events, and seasonal patterns. We propose a scalable framework that uses large language models (LLMs) to generate geo-temporal embeddings from only a timestamp and coarse location, capturing holidays, seasonal trends, and local/global events. We then introduce a geo-temporal embedding informativeness test as a lightweight diagnostic, demonstrating on MovieLens, LastFM, and a production dataset that these embeddings provide predictive signal consistent with the outcomes of full model integrations. Geo-temporal embeddings are incorporated into sequential models through (1) direct feature fusion with metadata embeddings or (2) an auxiliary loss that enforces semantic and geo-temporal alignment. Our findings highlight the need for adaptive or hybrid recommendation strategies, and we release a context-enriched MovieLens dataset to support future research. |
| title | From Time and Place to Preference: LLM-Driven Geo-Temporal Context in Recommendations |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.24430 |