SavedAdd your journal

Journals / Avrupa Bilim ve Teknoloji Dergisi / 2023 / Sayı: 51

A User and Item-Based, Wide and Deep Learning Based Travel Recommendation System

Kullanıcı ve Öğe Bazlı, Geniş ve Derin Öğrenme Tabanlı Seyahat Öneri Sistemi

Alihan ÖZ
Meryem UZUN-PER
Mert BAL
Pages
334–351
Publication Date
2023-08-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of this study, 82.37% accuracy rate was achieved in the top five recommendations given to the users.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the development of technology, the increasing amount of digital information and the widespread use of the internet, and the increase in the number of websites where trade transactions such as products, services and subscriptions are carried out on the internet, along with it, personalized and accurate; The importance of recommending products, services and subscriptions has also increased.
📊
Key Findings & Data:Product-based, user-based, and hybrid traditional approaches, which are widely used in recommendations to customers, are used in most studies.
💡
Conclusion & Impact:As a result of this study, 82.37% accuracy rate was achieved in the top five recommendations given to the users.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:öneri sistemleri · derin öğrenme · derin ve geniş öneri sistemleri

Abstract

With the development of technology, the increasing amount of digital information and the widespread use of the internet, and the increase in the number of websites where trade transactions such as products, services and subscriptions are carried out on the internet, along with it, personalized and accurate; The importance of recommending products, services and subscriptions has also increased. Product-based, user-based, and hybrid traditional approaches, which are widely used in recommendations to customers, are used in most studies. Overcoming the problems of traditional approaches such as working with large and sparse data, inability to find complex relationships between user and product, and cold start has been possible with the use of deep and wide learning systems. Within the scope of this study, a comprehensive view of deep and wide neural networks and their applications in travel recommendation systems is presented. After giving the basic information about deep learning, Google's Wide and Deep Algorithm and Facebook's Deep Learning Recommendation Model (DLRM) algorithm, which are the most popular recommendation algorithms, are included. Within the scope of this study, a new travel recommendation system was created in which numerical data is fed to the model by applying the embedding process of categorical user and product features with a broad and deep learning approach. The proposed method was applied on the data set of a real travel agency company. As a result of this study, 82.37% accuracy rate was achieved in the top five recommendations given to the users.

Özet

Teknolojinin gelişmesi ile birlikte artan dijital bilgi miktarı ve internetin yaygınlaşması ile internet üzerinden ürün, hizmet, abonelik gibi ticaret işlemlerinin gerçekleştiği web sitelerinin sayısının da artması, beraberinde, müşterilere kişiselleştirilmiş ve doğru; ürün, hizmet ve abonelikleri sunmanın (önermenin) de önemini artmıştır. Müşterilere önerilerde yaygın olarak kullanılan ürün bazlı, kullanıcı tabanlı ve bu ikisinin birlikte kullanıldığı hibrit geleneksel yaklaşımlar çoğu çalışmada kullanılmaktadır. Geleneksel yaklaşımların, büyük ve seyrek veriler ile çalışma, kullanıcı ve ürün arasındaki karışık ilişkileri bulamama ve soğuk başlangıç (cold start) gibi problemlerinin üstesinden gelmek, derin ve geniş öğrenme sistemlerinin kullanımı ile mümkün olmuştur. Bu çalışma kapsamında, derin ve geniş sinir ağlarına ve bunların seyahat öneri sistemlerindeki uygulamalarına kapsamlı bir bakış açısı sunulmuştur. Derin öğrenme ile ilgili temel bilgilere yer verildikten sonra, en popüler öneri algoritmaları olan Google'ın Geniş ve Derin Algoritması ve Facebook'un Deep Learning Recommendation Model (DLRM) algoritmasına yer verilmiştir. Bu çalışma kapsamında, geniş ve derin öğrenme yaklaşımı ile kullanıcı ve ürün özelliklerinin kategorik olanlarının gömme işlemi uygulanarak, nümerik veriler ile modele beslendiği yeni bir seyahat öneri sistemi oluşturulmuştur. Önerilen yöntem gerçek bir seyahat acentesi şirketinin veri seti üzerinde uygulanmıştır. Bu çalışma sonucunda kullanıcılara verilen en iyi beş öneride, %82.37 doğruluk oranı yakalanmıştır.

🔖

Cite This Article

ÖZ, A., UZUN-PER, M., BAL, M. (2023). A User and Item-Based, Wide and Deep Learning Based Travel Recommendation System. Avrupa Bilim ve Teknoloji Dergisi, Sayı: 51, 334–351. https://ajindex.com/articles/971266

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Cheng, H.-T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., Anil, R., Haque, Z., Hong, L., Jain, V., Liu, X., & Shah, H. (2016). Wide & Deep Learning for Recommender Systems. Içinde Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. DLRS 2016: Workshop on Deep Learning for Recommender Systems. ACM. https://doi.org/10.1145/2988450.2988454
  2. Naumov, M., Mudigere, D., Shi, H.-J. M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C.-J., Azzolini, A. G., Dzhulgakov, D., Mallevich, A., Cherniavskii, I., Lu, Y., Krishnamoorthi, R., Yu, A., Kondratenko, V., Pereira, S., Chen, X., … Smelyanskiy, M. (2019). Deep Learning Recommendation Model for Personalization and Recommendation Systems (Versiyon 1). arXiv. https://doi.org/10.48550/ARXIV.1906.00091
  3. Fan, W., Zhao, X., Chen, X., Su, J., Gao, J., Wang, L., Liu, Q., Wang, Y., Xu, H., Chen, L., & Li, Q. (2022). A Comprehensive Survey on Trustworthy Recommender Systems (Versiyon 1). arXiv. https://doi.org/10.48550/ARXIV.2209.10117
  4. Karimova, F. (2016). A Survey of e-Commerce Recommender Systems. Içinde European Scientific Journal, ESJ (C. 12, Issue 34, s. 75). European Scientific Institute, ESI. https://doi.org/10.19044/esj.2016.v12n34p75
  5. Belluf, T., Xavier, L., & Giglio, R. (2012). Case study on the business value impact of personalized recommendations on a large online retailer. Içinde Proceedings of the sixth ACM conference on Recommender systems. RecSys ’12: Sixth ACM Conference on Recommender Systems. ACM. https://doi.org/10.1145/2365952.2366014
  6. Amatriain, X., & Basilico, J. (2016).
  7. Past, Present, and Future of Recommender Systems. Içinde Proceedings of the 10th ACM Conference on Recommender Systems. RecSys ’16: Tenth ACM Conference on Recommender Systems. ACM. https://doi.org/10.1145/2959100.2959144
  8. Koren, Y. (2008). Factorization meets the neighborhood. Içinde Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. KDD08: The 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. https://doi.org/10.1145/1401890.1401944
  9. Rendle, S. (2010). Factorization Machines. Içinde 2010 IEEE International Conference on Data Mining. 2010 IEEE 10th International Conference on Data Mining (ICDM). IEEE. https://doi.org/10.1109/icdm.2010.127
  10. Paparrizos, I., Cambazoglu, B. B., & Gionis, A. (2011). Machine learned job recommendation. Içinde Proceedings of the fifth