Çapraz Satışı Destekleyebilecek Transformer ile Geliştirilmiş Bir Öneri Sistemi

Yıl 2023, Cilt: 38 Sayı: 2, 571 - 584, 28.07.2023

İbrahim Erdem Kalkan Cenk Şahin

https://doi.org/10.21605/cukurovaumfd.1334166

Öz

Öneri sistemlerinin, perakende sektöründe çapraz satış bağlamında bir ürün grubunu satış için hedeflemek veya hangi müşterilerin diğerlerine göre daha pazarlanabilir olduğunu tahmin edebilen yeteneklere sahip olduğu düşünülmektedir. Bu sayede mevcut müşterilerin bir sonraki seferde hangi ürün veya hizmeti satın alacaklarına ilişkin bir tahmin oluşturularak çapraz satış etkinliği arttırılabilecektir. Bu araştırmada temel amaç, çevrimiçi alışveriş endüstrisine, çapraz satış olanaklarını arttırabilmek bağlamında, belirli bir ürün ya da ürün grubu için, belli bir satın alma tarihçesi bulunan müşterilerinden hangilerinin diğerlerine göre daha uygun olduğunu tahmin etmek için bir öneri sistemi geliştirip sunmaktır. Bu kapsamda transformer kullanılarak probleme adapte edilmiş öneri sisteminin karşılaştırmalı bir çalışması yapılmış ve elde edilen sonuçlara göre önceki çalışmalarda sunulan modellere göre daha başarılı olduğu gözlenmiştir.

Anahtar Kelimeler

Transformer, Öneri sistemi, Çapraz satış, Derin öğrenme

A Transformer-Improved Recommender System Supporting Cross-Selling

Öz

It is believed that recommender systems have the ability to target a product group for sales in cross-selling context or predict which customers are more marketable than others in the retail sector. In this way, cross-selling efficiency can be increased by creating a forecast about which product or service current customers will purchase next time. The main purpose of this research is to develop and present a recommendation system to the online shopping industry to predict which customers with a certain purchasing history are more suitable than others for a particular product or product group, in order to increase cross-selling opportunities. A comparative application of the recommendation system adapted to the problem using transformers is presented in this study, and successful results were observed compared to previous studies.

Anahtar Kelimeler

Transformer, Recommender system, Cross selling, Deep learning

Kaynakça

• 1. Akçura, M.T., Srinivasan, K., 2005. Customer Intimacy and Crossselling Strategy. Manage Sci, 51(6), 1007-1012.
• 2. Kamakura, W.A., Wedel, M., Rosa, F., Mazzon, J.A., 2003. Crossselling Through Database Marketing: A Mixed Data Factor Analyzer for Data Augmentation and Prediction. Int J Res Mark, 20, 45-65.
• 3. Reinartz, W.J., Kumar, V., 2003. The Impact of Customer Relationship Characteristics on Profitable Lifetime Duration. J Mark, 67, 77-99.
• 4. Kamakura, W.A., 2008. Cross-Selling: Offering the Right Product to the Right Customer at the Right Time. J Relationship Market, 6(3-4), 41-58.
• 5. Ansel, J., Archibald, T., 2007. Identifying Cross-Selling Opportunities, Using Lifestyle Segmentation and Survival Analysis. Mark Intell Plan, 25(4), 394-410.
• 6. Knott, A., Hayes, A., Neslin, S.A., 2002. Next-Product-to-Buy Models for Cross-Selling Applications. J Interact Mark, 16(3), 59-75.
• 7. Bogaert, M., Lootens, J., Van den Poel, D., Ballings, M., 2019. Evaluating Multi-Label Classifiers and Recommender Systems in the Financial Service Sector. Eur J Oper Res, 279(2), 620-634.
• 8. Zhang, L., Priestley, J., De Maio, J., Ni, S., Tian, X., 2021. Measuring Customer Similarity and Identifying Cross-Selling Products by Community Detection, Big Data, 9(2), 132-143.
• 9. Lü, L., Medo, M., Yeung, C., Zhang, Y., Zhang, Z., Zhou, T., 2012. Recommender Systems. Phys Rep, 519, 1-49.
• 10. Hu, Y., Koren, Y., Volinsky, C., 2008. Collaborative Filtering for Implicit Feedback Datasets. Eighth IEEE International Conference on Data Mining, 263-272.
• 11. Geuens, S., Coussement, K., De Bock, K.W., 2017, A Framework for Configuring Collaborative Filtering-Based Recommendations Derived from Purchase Data. Eur J Oper Res, 265(1), 208-218.
• 12. Verstrepen. K., Bhaduriy, K., Cule, B., Goethals, B., 2017. Collaborative Filtering for Binary Positiveonly Data ACM SIGKDD Explor Newslett, 19(1), 1-21.
• 13. Adomavicius. G., Tuzhilin, A., 2005. Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Trans Knowl Data Eng, 17(6), 734-749.
• 14. Zhang, S, Yao, L., 2019. Deep Learning Based Recommender System: A Survey and New Perspectives. ACM Comput Surv, 52(1), 1-38.
• 15. Devooght, R., Bersini H., 2017. Collaborative Filtering with Recurrent Neural Networks, 1-9.
• 16. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N. 2017. Attention is All You Need Adv. Neural Inf. Process. Syst. Nips, 5999-6009.
• 17. Thuring, F., Nielsen, J.P., Guillen, M., Bolance, C., 2012. Selecting Prospects for Cross-Selling Financial Products Using Multivariate Credibility. Expert Syst Appl, 39, 8809-8816.
• 18. Martinez, A., Schmuck, C., Pereverzyev, S., Pirker, C., Haltmeier, M., 2020. A Machine Learning Framework for Customer Purchase Prediction in the Non-Contractual Setting. Eur J Oper Res, 281(3), 588-596.
• 19. Chou, P., Chuang, H-C., Chou, Y-C., Liang, T-P., 2021. Predictive Analytics for Customer Repurchase: Interdisciplinary Integration of Buy Till You Die Modeling and Machine Learning. Eur J Oper Res, 296(2022), 635-651.
• 20. Tan, Y.K., Xu, X., Liu, Y., 2016. Improved Recurrent Neural Networks for Session-Based Recommendations. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, 17-22.
• 21. Li, S., Kawale, J., Fu, Y., 2015. Deep Collaborative Filtering via Marginalized Denoising Auto-Encoder. Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM ’15), 811-820.
• 22. Lee, D.D., Seung, H.S., 2000. Algorithms for Non-Negative Matrix Factorization. Proceedings of the 13th International Conference on Neural Information Processing Systems, 535-541.
• 23. Salakhutdinov, R., Mnih, A., 2008. Bayesian Probabilistic Matrix Factorization Using Markov Chain Monte Carlo. Proceedings of the 25th International Conference on Machine Learning, 880-887.
• 24. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T., 2017. Neural Collaborative Filtering. Proceedings of the 26th International Conference on World Wide Web, 173-182.
• 25. Zhang, S., Yao, L., 2019, Deep Learning Based Recommender System: A Survey and New Perspectives. ACM Comput Surv, 52(1), 1-38.
• 26. Salakhutdinov, R., Mnih, A., Hinton, G., 2007. Restricted Boltzmann Machines for Collaborative Filtering. Proceedings of the 24th International Conference on Machine Learning, 791-798.
• 27. Donkers, T., Benedikt, L., Ziegler, J., 2017. Sequential User-Based Recurrent Neural Network Recommendations. Proceedings of RecSys, 17, 27-31.
• 28. Hidasi, B., Karatzoglou, A., 2018. Recurrent Neural Networks with Top-k Gains for Session-Based Recommendations. The 27th ACM International Conference on Information and Knowledge Management (CIKM’18), 843-852.
• 29. Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D., 2016. Session-Based Recommendations with Recurrent Neural Networks, 4th International Conference on Learning Representations (ICLR), 1-10.
• 30. Wu, S., Ren, W., Yu, C., Chen, G., Zhang, D., Zu, J., 2016. Personal Recommendation Using Deep Recurrent Neural Networks in NetEase. IEEE 32nd International Conference on Data Engineering (ICDE), 1218-1229.
• 31. Smirnova, E., Vasile, F., 2017. Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks. Proceedings of the 2nd Workshop on Deep Learning for Recommender Systems, 2-9.
• 32. Kalkan, İ.E., Şahin, C., 2022. Evaluating Cross-Selling Opportunities with Recurrent Neural Networks on Retail Marketing. Neural Computing and Applications, 35(8), 6247-6263.
• 33. Cheng, H.T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., 2016. Wide and Deep Learning for Recommender Systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, 7-10.
• 34. Chen, Q., Zhao, H., Li, W., Huang, P., Ou, W., 2019. Behavior Sequence Transformer for e-commerce Recommendation in Alibaba. Proceedings of the 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data, 1-4.
• 35. Li, W., Qi, F., Tang, M., Yu, Z., 2020. Bidirectional LSTM with Self-Attention Mechanism and Multi-Channel Features for Sentiment Classification. Neurocomputing, 387, 63-77.
• 36. Katrompas, A., Metsis, V., 2022. Enhancing LSTM Models with Self-Attention and Stateful Training. Intell Syst Appl, 217-235.
• 37. Keras. https://keras.io//, Erişim Tarihi: 06.09.2022
• 38. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jozefowicz, R., Jia, Y., Kaiser, L., Kudlur, M., Zheng, X., 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Tensorflow. https://tensorflow.org//, Erişim Tarihi: 06.09.2022.
• 39. Kaggle. Your Machine Learning and Data Science Community. https://www.kaggle. com//, Erişim Tarihi: 06.09.2022.
• 40. Pakistan’s Largest E-Commerce Dataset, Version 2, https://www.kaggle.com/datasets/ zusmani/pakistans-largest-ecommerce–dataset// Erişim Tarihi: 06.9.2022.
• 41. Xu, Q-S., Liang, Y-Z., 2001. Monte Carlo Cross Validation. Chemom Intell Lab Syst, 56(1), 1-11.
• 42. He, X., Chen, T., Kan, M.Y., Chen, X., 2015. TriRank: Review-Aware Explainable Recommendation by Modeling Aspects. CIKM’15: Proceedings of the 24th ACM International Conference on Information and Knowledge Management, 1661-1670.