Özellik Tabanlı Kümeleme ile Otel Tavsiyelerinin Geliştirilmesi

Öz

Bu makale, otel endüstrisi için öneri sistemlerinde seyrek etkileşim verilerinin yarattığı zorlukları ele almaktadır. Otel konaklamalarının genellikle yılda bir veya birkaç kez olması, müşteri-ürün etkileşim verilerini seyrek kılar. Bu da geleneksel işbirlikçi filtreleme tekniklerinin etkinliğini engeller. Bu senaryo için özel olarak tasarlanmış yeni bir hibrit öneri çerçevesi öneriyoruz. Yalnızca kullanıcı tercihi benzerliğine dayanan geleneksel sistemlerin aksine, çerçevemiz ürün uzayını bölümlere ayırmak için ikili özniteliklere dayalı otel kümelemesinden yararlanmaktadır. Kullanıcı etkileşimleri bu kümeler içinde analiz edilerek daha rafine bir tavsiye süreci ortaya çıkar. Çeşitli kümeleme ve özellik azaltma tekniklerinden yararlanıyor ve nihai tavsiyeyi oylama puanlaması yoluyla atıyoruz. Deneyler, hem satış bilgilerini hem de otel niteliklerini içeren gerçek dünya otel satış veri seti üzerinde gerçekleştirilmiştir. Sonuçlara göre metodolojimizi kümeleme kullanmayan temel yaklaşımlara göre önemli gelişmeler gösteriyor. Önerilen çerçeve, hem tavsiye alan kullanıcı sayısında hem de doğru tavsiye sayısında iki kat artış sağlıyor. Bu sonuçlar, turizm tavsiye sistemlerindeki seyreklik sorunlarını hafifletmek için küme tabanlı önerilerin potansiyelini vurgulamaktadır.

Anahtar Kelimeler

• Öneri Sistemi
• Işbirlikçi Filtreleme
• Hibrit Öneri Sistemi
• Oylama Puanı

Enhancing Hotel Recommendations through Feature- based Clustering

Öz

This paper addresses the challenge of sparse interaction data in recommendation systems for the hotel industry. Due to the infrequent nature of hotel stays (often once or a few times annually), customer-product interaction data is typically sparse, hindering the effectiveness of traditional collaborative filtering techniques. We propose a novel hybrid recommendation framework specifically designed for this scenario. Unlike conventional systems that rely solely on user preference similarity, our framework leverages hotel clustering based on binary attributes to segment the product space. User interactions are analyzed within these clusters, leading to a more refined recommendation process. We take advantage of several clustering and feature reduction techniques and assign the final recommendation through ballot scoring. The experiments are performed on a real-world hotel sales data set including both sales information and hotel attributes. We evaluate our methodology and demonstrate significant improvements over baseline approaches which is the case of not using the found clusters for recommendation. The proposed framework achieves a two-fold increase in both the number of users receiving recommendations and the number of correct recommendations. These results highlight the potential of cluster- based recommendations for mitigating sparsity issues in tourism recommender systems.

Anahtar Kelimeler

• Recommendation System
• Collaborative Filtering
• Hybrid Recommendation System
• Ballot Score

Kaynakça

1. Unwto world tourism barometer and statistical annex, january 2023. https://www.e- unwto.org/doi/epdf/10.18111/wtobarometereng.2023.21.1.1?role=tab. Accessed: 2024-02-01.
2. Turizm İstatistikleri, ekim-aralık, (2023). https://data.tuik.gov.tr/Bulten/Index? p=Turizm-Istatistikleri-IV.- Ceyrek:-Ekim—Aralik,-2023-53661. Accessed: 2024-02-01.
3. Liu, L.L., & Mpcm, J. (2023). Multi-modal user portrait classification model based on collaborative learning. Information Technology and Control, 52(4):867–877.
4. Lee, M., & Kim, H.J. (2023). A collaborative filtering model incorporating media promotions and users’ variety-seeking tendencies in the digital music market. Decision Support Systems, 174:114022.
5. Iftikhar, A., Mustansar A. G., Mubbashir A., Zahid M., & Muazzam M. (2020). An improved product recommendation method for collaborative filtering. IEEE ACCESS, 8:123841– 123857.
6. Jozani, M., Liu, C.H., & Choo, KK. R. (2023). An empirical study of content-based recommendation systems in mobile app markets. Decision Support Systems, 169:113954.
7. Liu, D.R, Lai, C.H., & Lee, W.J. (2009). A hybrid of sequential rules and collaborative filtering for product recommendation. Information Sciences, 179(20):3505–3519.
8. Wihartiko, F. D., Nurdiati S., Buono, A., & Santosa, E. (2023). Multi-objective entropy optimization model for agricultural product price recommendation problem. Engineering Letters, 31(4),

9. Li, G.H.C.M.Z., Wu, J., & Chen, Y. (2023). Multi-hypergraph neural network with fusion of location information for session-based recommendation. IAENG International Journal of Applied Mathematics, 53(4):1389–1398.
10. Bobadilla, J., Ortega, F., Hernando, A. & Gutiérrez, A. (2013). Recommender systems survey. Knowledge- Based Systems, 46:109–132.
11. Akyol, M. (2021). Clustering hotels and analyzing the importance of their features by machine learning techniques. Bilgisayar Bilimleri ve Teknolojileri Dergisi, 2(1):16–23.
12. Rodrıguez-Victoria, O.E., Puig, F. & González-Loureiro, M. (2017). Clustering, innovation and hotel competitiveness: evidence from the colombia destination. International Journal of Contemporary Hospitality Management, 29(11):2785–2806.
13. Kaya, B. (2020). A hotel recommendation system based on customer location: a link prediction approach. Multimedia Tools Appl., 79(3–4):1745–1758.
14. Chen, T. (2020), A fuzzy ubiquitous traveler clustering and hotel recommendation system by differentiating travelers’ decision-making behaviors. Applied Soft Computing, 96:106585.
15. Lee, T. H., & Jan, F.H. (2023). How does personality affect covid-19 pandemic travel risk perceptions and behaviors? evidence from segment analysis in taiwan. Sustainability, 15(1).
16. Forouzandeh, S., Berahmand, K. Nasiri, E. & Rostami, M. (2021). A Hotel Recommender System for Tourists Using the Artificial Bee Colony Algorithm and Fuzzy TOPSIS Model: A Case Study of TripAdvisor. International Journal of Information Technology & Decision Making (IJITDM), 20(01):399–429.
17. Kwok, P.K., & Lau, H.Y.K. (2019). Hotel selection using a modified topsis-based decision support algorithm. Decision Support Systems, 120:95–105.
18. Chen, T., & Chuang. Y.H. (2018). Fuzzy and nonlinear programming approach for optimizing the performance of ubiquitous hotel recommendation. Journal of Ambient Intelligence and Humanized Computing, 9(2).
19. Lee, S.H., Yun, J.J., Diaz, M.M. & Duque, C.M. (2021). Open innovation through customer satisfaction: A logit model to explain customer recommendations in the hotel sector. Journal of Open Innovation: Technology, Market, and Complexity, 7(3):180.
20. Arifogullari, O., & Orman, G.K. (2023). On experimental study of hotel clustering. In Proceedings of the International MultiConference of Engineers and Computer Scientists 2023, IMECS 2023, pages p. 82–87, Hong Kong.
21. Johnstone, I. M., & Yu, L. A. (2009). On consistency and sparsity for principal components analysis in high dimensions. Journal of the American Statistical Association, 104(486):682–693.
22. Inderjit, S. D., & Suvrit, S. (2005). Generalized nonnegative matrix approximations with bregman divergences. In Proceedings of the 18th International Conference on Neural Information Processing Systems, NIPS’05, page 283–290, Cambridge, MA, USA, MIT Press.
23. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A, 374(2065):20150202–20150202, 2016.
24. Taebel, D.A. (1975). The effect of ballot position on electoral success. American Journal of Political Science, 19(3):519–526.
25. Ye, M., Zhang, P., & Nie, L. (2018). Clustering sparse binary data with hierarchical bayesian bernoulli mixture model. Computational Statistics Data Analysis, 123:p. 32–49.