Sequential recommendation for canteen food recommendations in NTU
Recently, food recommendation has become more significant due to its potential to serve tremendous service demand and allow users to discover their preferred food items from a variety of choices. Nevertheless, to build an effective food recommender system, understanding the user’s dynamic food prefe...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156633 |
| _version_ | 1826111847008305152 |
|---|---|
| author | Nguyen, Tien Nhan |
| author2 | Hui Siu Cheung |
| author_facet | Hui Siu Cheung Nguyen, Tien Nhan |
| author_sort | Nguyen, Tien Nhan |
| collection | NTU |
| description | Recently, food recommendation has become more significant due to its potential to serve tremendous service demand and allow users to discover their preferred food items from a variety of choices. Nevertheless, to build an effective food recommender system, understanding the user’s dynamic food preference is a prerequisite. In this project, our aim is to apply sequential recommendation (SR) to model such evolving preference in user behaviours. We attempted to evaluate multiple attention-based SR models and apply transfer learning techniques to further improve the models’ performance.
A canteen food review dataset is introduced comprising food stall reviews crawled from the NTU Food Hunter system. Four attention-based SR models, consisting of SASRec, TiSASRec, BERT4Rec, and STOSA models are evaluated on the Food Hunter dataset and other benchmark datasets. The objective of the SR model is to predict the next item based on the user’s past behaviour sequence. In addition, we compare Collaborative Filtering (CF) versus attention-based SR methods on a benchmark dataset and find that SR methods outperform CF methods in predicting the user’s following item.
Because the Food Hunter dataset is relatively small, we use transfer learning techniques by pre-training the SR models on a larger food domain dataset named Amazon Food. The results show that transfer learning can significantly improve some models' performance on the Food Hunter dataset. |
| first_indexed | 2024-10-01T02:57:34Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156633 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:57:34Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1566332022-04-21T06:55:35Z Sequential recommendation for canteen food recommendations in NTU Nguyen, Tien Nhan Hui Siu Cheung School of Computer Science and Engineering ASSCHUI@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Recently, food recommendation has become more significant due to its potential to serve tremendous service demand and allow users to discover their preferred food items from a variety of choices. Nevertheless, to build an effective food recommender system, understanding the user’s dynamic food preference is a prerequisite. In this project, our aim is to apply sequential recommendation (SR) to model such evolving preference in user behaviours. We attempted to evaluate multiple attention-based SR models and apply transfer learning techniques to further improve the models’ performance. A canteen food review dataset is introduced comprising food stall reviews crawled from the NTU Food Hunter system. Four attention-based SR models, consisting of SASRec, TiSASRec, BERT4Rec, and STOSA models are evaluated on the Food Hunter dataset and other benchmark datasets. The objective of the SR model is to predict the next item based on the user’s past behaviour sequence. In addition, we compare Collaborative Filtering (CF) versus attention-based SR methods on a benchmark dataset and find that SR methods outperform CF methods in predicting the user’s following item. Because the Food Hunter dataset is relatively small, we use transfer learning techniques by pre-training the SR models on a larger food domain dataset named Amazon Food. The results show that transfer learning can significantly improve some models' performance on the Food Hunter dataset. Bachelor of Engineering (Computer Science) 2022-04-21T06:55:35Z 2022-04-21T06:55:35Z 2022 Final Year Project (FYP) Nguyen, T. N. (2022). Sequential recommendation for canteen food recommendations in NTU. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156633 https://hdl.handle.net/10356/156633 en SCSE21-0531 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Nguyen, Tien Nhan Sequential recommendation for canteen food recommendations in NTU |
| title | Sequential recommendation for canteen food recommendations in NTU |
| title_full | Sequential recommendation for canteen food recommendations in NTU |
| title_fullStr | Sequential recommendation for canteen food recommendations in NTU |
| title_full_unstemmed | Sequential recommendation for canteen food recommendations in NTU |
| title_short | Sequential recommendation for canteen food recommendations in NTU |
| title_sort | sequential recommendation for canteen food recommendations in ntu |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/156633 |
| work_keys_str_mv | AT nguyentiennhan sequentialrecommendationforcanteenfoodrecommendationsinntu |