Meeting Point Recommendation System Using Collaborative Filtering Method

DOI

10.2991/978-94-6463-364-1_43How to use a DOI?

Keywords

Recommendation system; Collaborative filtering; Place gathering; User-based collaborative filtering

Abstract

Recommendation systems aim to provide item recommendations to users. By offering recommendations, users can consider the suggested items. One method for building a recommendation system is Collaborative Filtering. Collaborative filtering works by utilizing user ratings to predict their ratings for specific items. Cafés are popular places for social gatherings with friends or family. Currently, numerous cafés and restaurants are operating with diverse menus and facilities. The variety of options makes it challenging for individuals to choose a suitable place to visit. To simplify the selection process, a recommendation system is needed. In this study, the author develops a system recommending cafés to consumers. The system uses the user-based collaborative filtering algorithm and employs cosine similarity. The dataset used in this research consists of 284 cafes with over 25,000 reviews obtained by scraping Google reviews. The dataset includes usernames, given ratings, cafe names, and cafe ambiance. Currently, with 284 cafes, the system yields cosine similarity values below 0.1. However, experimental findings indicate that these cosine similarity values are expected to increase as the dataset size grows. This observation suggests the system’s recommendations will grow more robust and precise with an expanding dataset. The system’s efficiency was underscored by its performance even with smaller datasets, achieving an average response time of 120ms for smaller and 1600ms for larger datasets. This research lays the groundwork for further exploration of factors shaping user preferences and sets a benchmark for cafe recommendation system performance. Interestingly, even with smaller datasets, the recommended cafes remain consistent despite variations in larger datasets. This finding suggests that the system can provide reliable recommendations even with a smaller dataset, showcasing its effectiveness in capturing user preferences. This research also establishes a foundation for further studies in identifying other factors influencing user preferences when selecting cafes.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Himma Filangga Sutopo
AU  - Tita Karlita
AU  - Entin Martiana Kusumaningtyas
PY  - 2024
DA  - 2024/02/17
TI  - Meeting Point Recommendation System Using Collaborative Filtering Method
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2023 (iCAST-ES 2023)
PB  - Atlantis Press
SP  - 458
EP  - 472
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-364-1_43
DO  - 10.2991/978-94-6463-364-1_43
ID  - Sutopo2024
ER  -