A Weighted Hybrid Filtering Approach for Cold-Start and Diversity Evaluation in Culinary Recommender Systems

Lukman Lukman; Fiki  Fiki; Manaf Manaf; Wildan Wildan; Rifqi Rifqi

doi:10.15408/jti.v19i2.51692

Authors

Nur Lukman Department of Informatics, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung, Indonesia
Fiki Aprian PT. Sasana Solusi Digital, Indonesia
Khaerul Manaf Department of Information System Engineering, Sangga Buana University, Indonesia
Wildan Budiawan Zulfikar Department of Informatics, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung, Indonesia
Rifqi Syamsul Fuadi Department of Informatics, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung, Indonesia

DOI:

https://doi.org/10.15408/jti.v19i2.51692

Keywords:

Cold start, Collaborative filtering, Content-based filtering, Diversity, Hybrid filtering, Recommender system

Abstract

Recommender systems play a crucial role in helping users discover relevant and diverse products tailored to their preferences. However, challenges such as the cold-start problem and low recommendation diversity still persist, particularly in single-approach models such as Content-Based Filtering (CBF) and Collaborative Filtering (CF). This study implements and evaluates a Weighted Hybrid Filtering approach that linearly combines prediction scores from CBF, which recommends items based on content similarity to a user's preference profile, and CF, which recommends items based on rating patterns from similar users, using a weighting parameter α. The model was evaluated on a real-world transaction dataset from Tantri Point of Sale (POS) consisting of more than 300,000 user–item interactions, with a user–item interaction sparsity of 99.93%, using Precision@10, Recall@10, F1@10, Intra-List Diversity (ILD@10), RMSE, and MAE. Cold-start conditions were assessed through simulation by masking user interaction histories. Results show that the hybrid configuration with α = 0.9 achieves the highest Recall@10 (0.8153) among all evaluated models, along with an F1@10 of 0.6634, an ILD@10 of 0.8030, an RMSE of 0.2984, and an MAE of 0.1924, although the standalone CF model attains higher F1@10 and ILD@10, and the standalone CBF model attains higher precision, individually. Compared to existing weighted hybrid recommender approaches, which have primarily been evaluated on non-culinary benchmark datasets, this study applies and evaluates the method on a large-scale, real-world culinary transaction dataset, providing an explicit assessment of the accuracy–diversity trade-off across multiple weighting configurations. These findings provide empirical insight into the trade-offs of weighted hybrid filtering for cold-start and diversity assessment in culinary recommender systems.

References

[1] A. Hakim, “The Digital Transformation of Traditional Culinary Businesses Towards Online Success,” Involv. Int. J. Bus., vol. 2, no. 1, pp. 11–25, Jan. 2025, doi: 10.62569/iijb.v2i1.105.

[2] J. J. Yun, X. Zhao, G. Del Gaudio, V. Della Corte, and Y. Sadoi, “Leveraging business model innovation through the dynamics of open innovation: a multi-country investigation in the restaurant industry,” Eur. J. Innov. Manag., vol. 28, no. 4, pp. 1342–1365, Apr. 2025, doi: 10.1108/EJIM-07-2023-0607.

[3] A. Dhaliwal, “Deconstructing contemporary consumer decision-making towards culinary consumption patterns: A multidimensional analysis of dine-in services in the age of cloud-based food service ecosystems,” Food Humanity, vol. 6, p. 100996, May 2026, doi: 10.1016/j.foohum.2026.100996.

[4] O. Alshareet and A. Awasthi, “Collaborative filtering in the age of AI: foundations, innovations, and emerging trends,” Computing, vol. 107, no. 11, p. 216, Nov. 2025, doi: 10.1007/s00607-025-01564-2.

[5] D. B. Rajesh and A. Kumar, “Collaborative filtering models an experimental and detailed comparative study,” Sci. Rep., vol. 15, no. 1, p. 31667, Aug. 2025, doi: 10.1038/s41598-025-15096-4.

[6] M. Muflih, S. Ratna, and G. Mahalisa, “Development of A Collaborative Recommendation System Based on Singular Value Decomposition (SVD) on E-Commerce Data,” J. Appl. Inform. Comput. JAIC, vol. 9, no. 6, Dec. 2025.

[7] C. A. M. Zulaeka et al., “Recommendation System for Solaria Food Menu Based on Customer Ratings Using Singular Value Decomposition,” J. Ris. Dan Apl. Mat. JRAM, vol. 9, no. 1, Apr. 2025.

[8] M. A. Dzulqarnain, “Application of item-based collaborative filtering method for culinary tourism recommendations in Bandung City,” UIN Sunan Gunung Djati Bandung, 2019. [Online]. Available: https://dspace.uinsgd.ac.id/items/1b2ef8e7-7a54-40cd-8566-6aa852a4aaf5

[9] R. Garapati and M. Chakraborty, “Recommender systems in the digital age: a comprehensive review of methods, challenges, and applications,” Knowl. Inf. Syst., vol. 67, no. 8, pp. 6367–6411, Aug. 2025, doi: 10.1007/s10115-025-02453-y.

[10] B. Akkaya, “Current Trends in Recommender Systems: A Survey of Approaches and Future Directions,” J. Comput. Sci., vol. 10, no. 1, Jun. 2025, doi: https://doi.org/10.53070/bbd.1652022.

[11] Z. Xia, A. Sun, J. Xu, Y. Peng, R. Ma, and M. Cheng, “Contemporary Recommendation Systems on Big Data and Their Applications: A Survey,” IEEE Access, vol. 12, pp. 196914–196928, 2024, doi: 10.1109/ACCESS.2024.3517492.

[12] D. K. Panda and S. Ray, “Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review,” J. Intell. Inf. Syst., vol. 59, no. 2, pp. 341–366, Oct. 2022, doi: 10.1007/s10844-022-00698-5.

[13] S. Shinagam, “Comparison of Collaborative Filtering and Content-Based Filtering for Food Recommender Systems,” Universiteit Utrech, 2025.

[14] M. R. Firdaus, “Integration of user context and diversity in content-based filtering for food recipe recommendations,” UIN Sunan Gunung Djati Bandung, 2025. [Online]. Available: https://dspace.uinsgd.ac.id/items/6dfc1a17-d000-4c3f-8496-6636b5372e80

[15] Q. Zhou et al., “Hybrid collaborative filtering model for consumer dynamic service recommendation based on mobile cloud information system,” Inf. Process. Manag., vol. 59, no. 2, p. 102871, Mar. 2022, doi: 10.1016/j.ipm.2022.102871.

[16] K. Peng, M. Raghavan, E. Pierson, J. Kleinberg, and N. Garg, “Reconciling the Accuracy-Diversity Trade-off in Recommendations,” in Proceedings of the ACM Web Conference 2024, Singapore Singapore: ACM, May 2024, pp. 1318–1329. doi: 10.1145/3589334.3645625.

[17] A. Chaudhari, A. A. Hitham Seddig, A. Sarlan, and R. Raut, “A Hybrid Recommendation System: A Review,” IEEE Access, vol. 12, pp. 157107–157126, 2024, doi: 10.1109/ACCESS.2024.3480693.

[18] C. S. Rajpoot, V. Tiwari, and S. K. Vishwakarma, “An enhanced hybrid recommender system using an adaptive optimization approach,” Jun. 2026, doi: https://doi.org/10.1007/s44163-026-00999-6.

[19] R. Widayanti, M. H. R. Chakim, C. Lukita, U. Rahardja, and N. Lutfiana, “Improving Recommender Systems using Hybrid Techniques of Collaborative Filtering and Content-Based Filtering,” vol. 4, no. 3, Sep. 2023.

[20] J. Karaman and Triyanna Widiyaningtyas, “Ensemble Hybrid Recommender System (CBF, CF, KNN, NBC) With Multi-View TF-IDF for Robust Preliminary Medical Diagnosis,” J. Tek. Inform., vol. 19, no. 1, pp. 62–72, Apr. 2026, doi: 10.15408/jti.v19i1.48705.

[21] P. Kouki, J. Schaffer, J. Pujara, J. O’Donovan, and L. Getoor, “Generating and Understanding Personalized Explanations in Hybrid Recommender Systems,” ACM Trans. Interact. Intell. Syst., vol. 10, no. 4, pp. 1–40, Dec. 2020, doi: 10.1145/3365843.

[22] S. Suriati, M. Dwiastuti, and T. Tulus, “Weighted hybrid technique for recommender system,” J. Phys. Conf. Ser., vol. 930, p. 012050, Dec. 2017, doi: 10.1088/1742-6596/930/1/012050.

[23] M. F. Aljunid and M. D. Huchaiah, “An efficient hybrid recommendation model based on collaborative filtering recommender systems,” CAAI Trans. Intell. Technol., vol. 6, no. 4, pp. 480–492, Dec. 2021, doi: 10.1049/cit2.12048.

[24] A. Sonule, H. Jagtap, and V. Mendhe, “Weighted Hybrid Recommendation System,” Int. J. Res. Anal. Rev., vol. 11, no. 1, 2024, doi: 10.56975/ijrar.v11i1.284204.

[25] M. E. Çakır, Z. Çetinkaya, F. Horasan, and A. H. Yurttakal, “Adaptive weighting-based hybrid recommender system: self-learning adaptive recommendation (SL-ARec),” PeerJ Comput. Sci., vol. 12, p. e3856, May 2026, doi: 10.7717/peerj-cs.3856.

[26] Muhammad Azhari Desky, Defry Hamdhana, and Munirul Ula, “Diet Food Recommendation System with Hybrid Content-Based and Collaborative Filtering Approach,” Rabit J. Teknol. Dan Sist. Inf. Univrab, vol. 11, no. 1, pp. 111–121, Jan. 2026, doi: 10.36341/rabit.v11i1.6647.

[27] S. Suwitno, A. H. Wijaya, and W. Wiyono, “Integration Content-Based and Collaborative Filtering in AI-Based Culinary Recommendation For Community of Tangerang City,” Bit-Tech, vol. 8, no. 2, pp. 1983–1994, Dec. 2025, doi: 10.32877/bt.v8i2.3182.

[28] V. Alfiati, “Identifikasi kelengkapan bacaan Al-Qur’an menggunakan transfer learning wav2vec2,” UIN Sunan Gunung Djati Bandung, 2024. [Online]. Available: https://dspace.uinsgd.ac.id/items/1b2ef8e7-7a54-40cd-8566-6aa852a4aaf5