Improving Overall Recommendation Quality with Convolutional Autoencoder

Zeynep Batmaz

doi:10.29130/dubited.1898472

TR EN

Evrişimli Otokodlayıcı ile Öneri Kalitesini İyileştirme

Abstract

Öneri sistemleri, kullanıcılara kişiselleştirilmiş öneriler sunarak aşırı bilgi sorununu çözmede önemli bir rol oynar. Oluşturulan önerilerin doğruluğu kullanıcı memnuniyeti için çok önemli olsa da, önerilerin doğruluk ötesindeki kalitesi de kullanıcı memnuniyetini önemli ölçüde etkiler. Bu nedenle araştırmacılar, önerilerin doğruluğunu artırmanın yanı sıra doğruluk ötesindeki kalitesini de iyileştirerek kullanıcı memnuniyetini artırmaya çalışmaktadır. Çok kriterli öneri sistemleri, çeşitli kriterlere göre bir öğenin değerlendirilmesine olanak tanıyarak geleneksel öneri tekniklerini genişletir ve daha kişiselleştirilmiş öneriler sunar. Literatürdeki birçok çalışma, çok kriterli önerilerin doğruluğunu artırmaya odaklanmakla birlikte, kullanıcı odaklı kişiselleştirme ve memnuniyeti artırmak için önerilerin doğruluğunun ötesindeki kalitesini de geliştirmeyi amaçlayan çalışmaların sayısı sınırlıdır. Bu çalışmada, çok kriterli öneri sistemlerinin doğruluğunu ve doğruluk ötesindeki kalitesini iyileştirmek için, evrişimli otokodlayıcıya dayalı iki yeni yöntem önerilmektedir. Ayrıca, hem doğruluk hem de doğruluk ötesindeki ölçütleri dikkate alarak önerilerin genel kalitesini ölçmek için yeni bir ölçüt sunulmaktadır. Gerçek bir veri seti üzerinde yapılan deneysel çalışmalar, önerilen her iki yöntemin de bu alandaki mevcut en gelişmiş yaklaşımlara kıyasla güçlü bir performasergilediğini göstermektedir. Önerilerin genel kalitesi açısından, önerilen CAE_MCCF yaklaşımı tüm TopN seviyelerinde en iyi genel performansı elde etmektedir. CAE_MCCF, en yakın rakibine kıyasla %18,69 ile %45,15 arasında değişen genel kalite puanlarında artış sağlamaktadır. Bu bulgular, evrişimli otokodlayıcıların öneri kalitesini artırmadaki etkinliğini desteklemektedir.

Keywords

Doğruluk ötesi, Doğruluk, Öneri kalitesi, Öneri sistemleri, Doğruluk ötesi, Doğruluk, Öneri kalitesi, Öneri sistemleri, Evrişimli otokodlayıcı

Supporting Institution

Bu çalışma, Eskişehir Teknik Üniversitesi tarafından 21GAP083 numaralı hibe ile kısmen desteklenmiştir.

Project Number

21GAP083

Ethical Statement

Bu çalışma herkese açık bir veri setini kullanmaktadır. Tüm prosedürler bilimsel ve etik ilkelere uygun olarak gerçekleştirilmiş olup, atıfta bulunulan tüm çalışmalar uygun şekilde kaynak gösterilmiştir.

Thanks

Bu çalışma, Eskişehir Teknik Üniversitesi tarafından 21GAP083 numaralı hibe ile kısmen desteklenmiştir.

Improving Overall Recommendation Quality with Convolutional Autoencoder

Abstract

Recommender systems play a crucial role in addressing the information overload problem by providing personalized recommendations to users. Although the accuracy of the generated recommendations is essential for user satisfaction, beyond-accuracy quality of the recommendations significantly impacts user satisfaction. Therefore, researchers strive to enhance user satisfaction by improving not only the accuracy but also the beyond-accuracy quality of recommendations. Multi-criteria recommender systems extend traditional recommendation techniques by allowing the evaluation of an item based on various criteria, enabling more personalized recommendations. Although numerous studies in the literature focus on improving the accuracy of multi-criteria recommendations, there is a limited number of works that aim to enhance beyond-accuracy quality of recommendations as well as accuracy, to increase user-centric personalization and satisfaction. In this study, two new methods, based on a convolutional autoencoder, are proposed to improve accuracy and beyond-accuracy quality of multi-criteria recommender systems. Additionally, to measure the overall quality of the recommendations considering both accuracy and beyond-accuracy metrics, a new metric is presented. Experimental studies conducted on two real datasets show that CAE_MCCF generates strong diversity performance compared to existing state-of-the-art approaches in the field. The other proposed approach CAE_SMCCF shows competitive results on beyond accuracy metrics. In terms of overall quality of the recommendations, the proposed approach CAE_MCCF achieves the best overall performance across all TopN levels. CAE_MCCF provides an increase in overall quality scores. These findings support the effectiveness of convolutional autoencoders in enhancing recommendation quality.

Keywords

Beyond-accuracy, Accuracy, Recommendation quality, Recommender systems, Convolutional autoencoder

Supporting Institution

This work was partially supported by Eskişehir Technical University under Grant No. 21GAP083.

Project Number

21GAP083

Ethical Statement

This study uses publicly available dataset. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.

Thanks

This work was partially supported by Eskişehir Technical University under Grant No. 21GAP083.

References

Abinaya, S., & Kumar, K. U. (2024). Enhancing multicriteria-based recommendations by alleviating scalability and sparsity issues using collaborative denoising autoencoder. Computers, Materials & Continua, 78(2), 2269–2286. https://doi.org/10.32604/cmc.2024.047167
Adomavicius, G., & Kwon, Y. (2007). New recommendation techniques for multicriteria rating systems. IEEE Intelligent Systems, 22(3), 48–55. https://doi.org/10.1109/MIS.2007.58
Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 17(6), 734–749. https://doi.org/10.1109/TKDE.2005.99
Afzal, I., Yilmazel, B., & Kaleli, C. (2024). An approach for multi-context-aware multi-criteria recommender systems based on deep learning. IEEE Access, 12, 99936–99948. https://doi.org/10.1109/ACCESS.2024.3428630
Akbulut, H. (2025). Meta-heuristic optimization for optimal block size in multi-focus image fusion: A comprehensive comparative studys. The Visual Computer, 41(13), 11025–11051. https://doi.org/10.1007/s00371-025-04084-4
Akbulut, H. (2026). A modified starfish optimization algorithm (M-SFOA) for global optimization problems and its application to heart disease risk prediction. Expert Systems with Applications, 307, Article 131088. https://doi.org/10.1016/j.eswa.2026.131088
Batmaz, Z. (2023). Comparative analysis of multi-criteria recommendation techniques: Beyond-accuracy. In Proceedings of the 10th International Baskent Congress on Physical, Engineering, and Applied Sciences (pp. 77–86). BZT Academy Publishing House.
Batmaz, Z., & Kaleli, C. (2019). AE-MCCF: An autoencoder-based multi-criteria recommendation algorithm. Arabian Journal for Science and Engineering, 44, 9235–9247. https://doi.org/10.1007/s13369-019-03946-z
Batmaz, Z., & Kaleli, C. (2022). A new similarity-based multicriteria recommendation algorithm based on autoencoders. Turkish Journal of Electrical Engineering and Computer Sciences, 30(3), 855–870. https://doi.org/10.55730/1300-0632.3815
Batmaz, Z., Yurekli, A., Bilge, A., & Kaleli, C. (2019). A review on deep learning for recommender systems: Challenges and remedies. Artificial Intelligence Review, 52, 1–37. https://doi.org/10.1007/s10462-018-9654-y

Berbague, C. E., Karabadji, N. E.-I., Seridi, H., Symeonidis, P., Manolopoulos, Y., & Dhifli, W. (2021). An overlapping clustering approach for precision, diversity and novelty-aware recommendations. Expert Systems with Applications, 177, Article 114917. https://doi.org/10.1016/j.eswa.2021.114917
Bilge, A., & Kaleli, C. (2014). A multi-criteria item-based collaborative filtering framework. In Proceedings of the 11th International Joint Conference on Computer Science and Software Engineering (18–22). IEEE https://doi.org/10.1109/JCSSE.2014.6841835
Bradley, K., & Smyth, B. (2001). Improving recommendation diversity. In Proceedings of the Twelfth National Conference in Artificial Intelligence and Cognitive Science (AICS-01) (pp. 85–94).
Ge, M., Delgado-Battenfeld, C., & Jannach, D. (2010). Beyond-accuracy: Evaluating recommender systems by coverage and serendipity. In Proceedings of the Fourth ACM Conference on Recommender Systems (pp. 257–260). https://doi.org/10.1145/1864708.1864761
Goodfellow, I. J., Bengio, Y., & Courville, A. C. (2016). Deep learning. MIT Press.
Gupta, S., & Kant, V. (2020). An aggregation approach to multi-criteria recommender system using genetic programming. Evolving Systems, 11(1), 29–44. https://doi.org/10.1007/s12530-019-09296-3
Gunawardana, A., Shani, G., & Yogev, S. (2012). Evaluating recommender systems. In F. Ricci, L. Rokach, & B. Shapira (Eds.), Recommender Systems Handbook (pp. 547–601). Springer. https://doi.org/10.1007/978-0-387-85820-3_17
Hassan, M., & Hamada, M. (2017). A neural networks approach for improving the accuracy of multi-criteria recommender systems. Applied Sciences, 7(9), Article 868. https://doi.org/10.3390/app7090868
Hong, M., & Jung, J. J. (2021). Multi-criteria tensor model for tourism recommender systems. Expert Systems with Applications, 170, Article 114537. https://doi.org/10.1016/j.eswa.2020.114537
Jannach, D., Karakaya, Z., & Gedikli, F. (2012). Accuracy improvements for multi-criteria recommender systems. In Proceedings of the 13th ACM Conference on Electronic Commerce (pp. 674–689). https://doi.org/10.1145/2229012.2229065
Kaminskas, M., & Bridge, D. (2016). Diversity, serendipity, novelty, and coverage: A survey and empirical analysis of beyond-accuracy objectives in recommender systems. ACM Transactions on Interactive Intelligent Systems, 7(1), 1–42. https://doi.org/10.1145/2926720
Kant, V., Jhalani, T., & Dwivedi, P. (2018). Enhanced multi-criteria recommender system based on fuzzy Bayesian approach. Multimedia Tools and Applications, 77, 12935–12953. https://doi.org/10.1007/s11042-017-4924-2
Kaur, G., & Ratnoo, S. (2019). Adaptive genetic algorithm for feature weighting in multi-criteria recommender systems. Pertanika Journal of Science & Technology, 27(1), 123–141.
Kaya, T., & Kaleli, C. (2022). A novel top-n recommendation method for multi-criteria collaborative filtering. Expert Systems with Applications, 198, Article 116695. https://doi.org/10.1016/j.eswa.2022.116695
Kotkov, D., Wang, S., & Veijalainen, J. (2016). A survey of serendipity in recommender systems. Knowledge-Based Systems, 111, 180–192. https://doi.org/10.1016/j.knosys.2016.08.014
Lu, H. (2023). k-surrounding neighbors: Incorporating serendipity in collaborative recommendations. In Proceedings of the 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (pp. 115–122). https://doi.org/10.2991/978-94-6463-222-4_11
Lü, L., Medo, M., Yeung, C. H., Zhang, Y.-C., Zhang, Z.-K., & Zhou, T. (2012). Recommender systems. Physics Reports, 519(1), 1–49. https://doi.org/10.1016/j.physrep.2012.02.006
Majumder, G. S., Dwivedi, P., & Kant, V. (2017). Matrix factorization and regression-based approach for multi-criteria recommender system. In Proceedings of the International Conference on Information and Communication Technology for Intelligent Systems (pp. 103–110). https://doi.org/10.1007/978-3-319-63673-3_13
Nassar, N., Jafar, A., & Rahhal, Y. (2020). A novel deep multi-criteria collaborative filtering model for recommendation systems. Knowledge-Based Systems, 187, Article 104811. https://doi.org/10.1016/j.knosys.2019.06.019
Rajput, I. S., Tewari, A. S., & Tiwari, A. K. (2024). An autoencoder-based deep learning model for solving the sparsity issues of multi-criteria recommender system. Procedia Computer Science, 235, 414–425. https://doi.org/10.1016/j.procs.2024.04.041
Rajput, I. S., Tewari, A. S., & Tiwari, A. K. (2025). NSGA-II optimized deep autoencoders for enhanced multi-criteria recommendation system. Computers and Electrical Engineering, 123, Article 110159. https://doi.org/10.1016/j.compeleceng.2025.110159
Ricci, F., Rokach, L., & Shapira, B. (2015). Recommender systems: Introduction and challenges. In F. Ricci, L. Rokach, & B. Shapira (Eds.), Recommender Systems Handbook (pp. 1–34). Springer. https://doi.org/10.1007/978-1-4899-7637-6_1
Rismala, R., Maulidevi, N. U., & Surendro, K. (2024). Personalized neural network-based aggregation function in multi-criteria collaborative filtering. Journal of King Saud University - Computer and Information Sciences, 36(1), Article 101922. https://doi.org/10.1016/j.jksuci.2024.101922
Salau, L., Mohamed, H., Abdulsalam, Y. S., & Mohammed, H. (2025). Deep learning-based multi-criteria recommender system for technology-enhanced learning. Scientific Reports, 15(1), Article 13075. https://doi.org/10.1038/s41598-025-97407-3
Sedhain, S., Menon, A. K., Sanner, S., Xie, L. (2015). AutoRec: Autoencoders meet collaborative filtering. In Proceedings of the 24th International Conference on World Wide Web (pp. 111–112). https://doi.org/10.1145/2740908.2742726
Shrivastava, R., Sisodia, D. S., & Nagwani, N. K. (2023). Deep neural network-based multi-stakeholder recommendation system exploiting multi-criteria ratings for preference learning. Expert Systems with Applications, 213, Article 119071. https://doi.org/10.1016/j.eswa.2022.119071
Singh, R., Dwivedi, P., & Kant, V. (2024). Comparative analysis of collaborative filtering techniques for the multi-criteria recommender systems. Multimedia Tools and Applications, 83(24), 64551–64571. https://doi.org/10.1007/s11042-024-18164-5
Sinha, B. B., & Dhanalakshmi, R. (2022). DNN-MF: Deep neural network matrix factorization approach for filtering information in multi-criteria recommender systems. Neural Computing and Applications, 34(13), 10807–10821. https://doi.org/10.1007/s00521-022-07012-y
Strub, F., & Mary, J. (2015). Collaborative filtering with stacked denoising autoencoders and sparse inputs. In Proceedings of the NIPS Workshop on Machine Learning for eCommerce (pp. 1–8). https://hal.inria.fr/hal-01256422
Tallapally, D., Sreepada, R. S., Patra, B. K., & Babu, K. S. (2018). User preference learning in multi-criteria recommendations using stacked auto encoders. In Proceedings of the 12th ACM Conference on Recommender Systems (pp. 475–479). https://doi.org/10.1145/3240323.3240412
Tintarev, N., & Masthoff, J. (2007). A survey of explanations in recommender systems. In Proceedings of the IEEE 23rd International Conference on Data Engineering Workshop (pp. 801–810). https://doi.org/10.1109/ICDEW.2007.4401070
Torkashvand, A., Jameii, S. M., & Reza, A. (2023). Deep learning-based collaborative filtering recommender systems: A comprehensive and systematic review. Neural Computing and Applications, 35(35), 24783–24827. https://doi.org/10.1007/s00521-023-08958-3
Türkoğlu Kaya, T. (2025). Mitigating popularity bias in fair and explainable recommender systems using SHAP. Duzce University Journal of Science and Technology, 13(3), 1180–1199. https://doi.org/10.29130/dubited.1667105
Türkoğlu Kaya, T. (2026). A novel clustering-based multi-criteria group recommender system. Neurocomputing, 666, Article 132329. https://doi.org/10.1016/j.neucom.2025.132329
Wang, H., Lu, Y., & Zhai, C. (2011). Latent aspect rating analysis without aspect keyword supervision. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 618–626). https://doi.org/10.1145/2020408.2020505
Wang, S., Yang, J., Chen, Z., Yuan, H., Geng, J., & Hai, Z. (2020). Global and local tensor factorization for multi-criteria recommender system. Patterns, 1(2), Article 100023. https://doi.org/10.1016/j.patter.2020.100023
Yalçın, E., & Bilge, A. (2020). Binary multicriteria collaborative filtering. Turkish Journal of Electrical Engineering and Computer Sciences, 28(6), 3419–3437. https://doi.org/10.3906/elk-2004-184
Yalçın, E., Bilge, A., & Yüksek, A. G. (2019). An empirical evaluation of aggregation techniques used in group recommender systems. In Proceedings of the 8th International Conference on Advanced Technologies (pp. 186–191).

Details

Primary Language

English

Subjects

Deep Learning, Neural Networks

Journal Section

Research Article

Authors

Zeynep Batmaz ^*
0000-0002-7509-9100
Türkiye

Publication Date

July 24, 2026

Submission Date

February 26, 2026

Acceptance Date

May 14, 2026

Published in Issue

Year 2026 Volume: 14 Number: 3

DOI

https://doi.org/10.29130/dubited.1898472

IZ

https://izlik.org/JA78YC54AG

APA

Batmaz, Z. (2026). Improving Overall Recommendation Quality with Convolutional Autoencoder. Duzce University Journal of Science and Technology, 14(3), 832-855. https://doi.org/10.29130/dubited.1898472

AMA

1.Batmaz Z. Improving Overall Recommendation Quality with Convolutional Autoencoder. DUBİTED. 2026;14(3):832-855. doi:10.29130/dubited.1898472

Chicago

Batmaz, Zeynep. 2026. “Improving Overall Recommendation Quality With Convolutional Autoencoder”. Duzce University Journal of Science and Technology 14 (3): 832-55. https://doi.org/10.29130/dubited.1898472.

EndNote

Batmaz Z (July 1, 2026) Improving Overall Recommendation Quality with Convolutional Autoencoder. Duzce University Journal of Science and Technology 14 3 832–855.

IEEE

[1]Z. Batmaz, “Improving Overall Recommendation Quality with Convolutional Autoencoder”, DUBİTED, vol. 14, no. 3, pp. 832–855, July 2026, doi: 10.29130/dubited.1898472.

ISNAD

Batmaz, Zeynep. “Improving Overall Recommendation Quality With Convolutional Autoencoder”. Duzce University Journal of Science and Technology 14/3 (July 1, 2026): 832-855. https://doi.org/10.29130/dubited.1898472.

JAMA

1.Batmaz Z. Improving Overall Recommendation Quality with Convolutional Autoencoder. DUBİTED. 2026;14:832–855.

MLA

Batmaz, Zeynep. “Improving Overall Recommendation Quality With Convolutional Autoencoder”. Duzce University Journal of Science and Technology, vol. 14, no. 3, July 2026, pp. 832-55, doi:10.29130/dubited.1898472.

Vancouver

1.Zeynep Batmaz. Improving Overall Recommendation Quality with Convolutional Autoencoder. DUBİTED. 2026 Jul. 1;14(3):832-55. doi:10.29130/dubited.1898472

Evrişimli Otokodlayıcı ile Öneri Kalitesini İyileştirme

Abstract

Keywords

Supporting Institution

Project Number

Ethical Statement

Thanks

Improving Overall Recommendation Quality with Convolutional Autoencoder

Abstract

Keywords

Supporting Institution

Project Number

Ethical Statement

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite