eprintid: 58151
rev_number: 18
eprint_status: archive
userid: 26258
dir: disk0/00/05/81/51
datestamp: 2026-02-09 08:03:46
lastmod: 2026-02-09 08:03:46
status_changed: 2026-02-09 08:03:46
type: thesis
metadata_visibility: show
contact_email: 3337210024@untirta.ac.id
creators_name: Rahman, Wahyu Arief
creators_id: 3337210024
contributors_type: http://www.loc.gov/loc.terms/relators/THS
contributors_type: http://www.loc.gov/loc.terms/relators/THS
contributors_name: Sukarna, Royan Habibie
contributors_name: Darnis, Febriyanti
contributors_id: 199204222022031006
contributors_id: 199002062024062001
corp_creators: UNIVERSITAS SULTAN AGENG TIRTAYASA
corp_creators: FAKULTAS TEKNIK
corp_creators: JURUSAN INFORMATIKA
title: OPTIMASI KINERJA ARSITEKTUR TWO-TOWER NEURAL COLLABORATIVE FILTERING UNTUK PENANGANAN COLD START PADA DATA IMPLICIT FEEDBACK E-COMMERCE
ispublished: pub
subjects: QA75
subjects: QA76
subjects: T1
divisions: TKI
full_text_status: restricted
keywords: NCF, Cold Start, Data Sparsity, Demografi, Two-Tower
note: Penelitian ini bertujuan untuk mengembangkan dan mengevaluasi arsitektur Neural Collaborative Filtering (NCF) hibrida yang efisien, guna mengatasi tiga tantangan utama sistem rekomendasi e-commerce: cold start, data sparsity, dan efisiensi komputasi. Metode penelitian yang digunakan adalah kuantitatif eksperimental dengan mengembangkan model berarsitektur Two-Tower yang mengintegrasikan data interaksi user-item dari dataset publik dengan fitur tambahan berupa data demografis pengguna dan simulasi kategori item.
Untuk menjawab tantangan komputasi pada data berskala besar, diterapkan strategi optimasi pipeline data melalui teknik pre-generation negative sampling. Kinerja model dievaluasi secara komprehensif pada skenario warm start, user cold start, dan item cold start menggunakan metrik Hit Ratio@10 (HR@10) dan Normalized Discounted Cumulative Gain (NDCG@10), serta divalidasi lebih lanjut melalui analisis kualitatif menggunakan data hold-out.
Hasil penelitian menunjukkan bahwa arsitektur yang diusulkan berhasil memberikan solusi efektif. Pertama, strategi optimasi pipeline terbukti mereduksi waktu pelatihan secara drastis dari lebih 2 jam menjadi sekitar 5-7 menit per epoch pada GPU kelas konsumen. Kedua, model hibrida berhasil mengatasi masalah item cold start dengan meningkatkan HR@10 dari 0,0053 (baseline) menjadi 0,0096, yang merepresentasikan peningkatan kinerja sebesar 81%. Ketiga, pada skenario user cold start, meskipun terdapat trade-off pada metrik peringkat presisi, validasi kualitatif membuktikan bahwa model memiliki kemampuan generalisasi yang baik dengan mencapai tingkat relevansi kategori sebesar 65% pada pengguna baru yang belum pernah berinteraksi sebelumnya.
abstract: This study aims to develop and evaluate an efficient hybrid Neural Collaborative Filtering (NCF) architecture to address three major challenges in e-commerce recommendation systems: cold start, data sparsity, and computational efficiency. The research method used is quantitative experimental by developing a Two-Tower architecture model that integrates user-item interaction data from public datasets with additional features in the form of user demographic data and item category simulations.
To address the computational challenges of large-scale data, a data pipeline optimization strategy is applied through the pre-generation negative sampling technique. Model performance was comprehensively evaluated in warm start, user cold start, and item cold start scenarios using the Hit Ratio@10 (HR@10) and Normalized Discounted Cumulative Gain (NDCG@10) metrics, and further validated through qualitative analysis using hold-out data.
The results of the study show that the proposed architecture successfully provides an effective solution. First, the pipeline optimization strategy has been proven to drastically reduce training time from more than 2 hours to around 5-7 minutes per epoch on consumer-grade GPUs. Second, the hybrid model has successfully overcome the cold start problem by increasing HR@10 from 0.0053 (baseline) to 0.0096, representing an 81% improvement in performance. Third, in the user cold start scenario, despite a trade-off in the precision ranking metric, qualitative validation proves that the model has good generalization capabilities by achieving a category relevance rate of 65% for new users who have never interacted before.
date: 2026-01-27
date_type: published
pages: 80
institution: Fakultas Teknik Universitas Sultan Ageng Tirtayasa
department: Informatika
thesis_type: sarjana
thesis_name: sarjana
referencetext: [1]	M. Solihat and D. Sandika, “E-commerce di Industri 4.0,” 2022, doi: 10.32812/jibeka.v16i2.967.
[2]	V. Jain, B. Malviya, and S. Arya, “An Overview of Electronic Commerce (e-Commerce),” Journal of Contemporary Issues in Business and Government, vol. 27, no. 3, Apr. 2021, doi: 10.47750/cibg.2021.27.03.090.
[3]	K. Wu and K. Chi, “Journal of Knowledge Learning and Science Technology Enhanced E-commerce Customer Engagement: A Comprehensive Three-Tiered Recommendation System,” Online), vol. 2, pp. 2959–6386, doi: 10.60087/jklst.vol2.n3.p359.
[4]	F. T. A. Hussien, A. M. S. Rahma, and H. B. Abdulwahab, “An e‐commerce recommendation system based on dynamic analysis of customer behavior,” Sustainability (Switzerland), vol. 13, no. 19, Oct. 2021, doi: 10.3390/su131910786.
[5]	W. Wang, F. Feng, X. He, L. Nie, and T. S. Chua, “Denoising Implicit Feedback for Recommendation,” in WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, Inc, Aug. 2021, pp. 373–381. doi: 10.1145/3437963.3441800.
[6]	S. Rendle, W. Krichene, L. Zhang, and J. Anderson, “Neural Collaborative Filtering vs. Matrix Factorization Revisited,” in RecSys 2020 - 14th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, Sep. 2020, pp. 240–248. doi: 10.1145/3383313.3412488.
[7]	A. Saxe, S. Nelli, and C. Summerfield, “If deep learning is the answer, then what is the question?”
[8]	J. Yang et al., “Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations,” in The Web Conference 2020 - Companion of the World Wide Web Conference, WWW 2020, Association for Computing Machinery, Apr. 2020, pp. 441–447. doi: 10.1145/3366424.3386195.
[9]	F. Z. Lebib and A. Meziane, “Two-Tower Neural Network for Personalizing Service Recommendation in Cloud Environment,” in 2025 IEEE 22nd International Multi-Conference on Systems, Signals & Devices (SSD), IEEE, Feb. 2025, pp. 879–884. doi: 10.1109/SSD64182.2025.10989960.
[10]	J. Bobadilla, F. Ortega, A. Gutiérrez, and S. Alonso, “Classification-based deep neural network architecture for collaborative filtering recommender systems,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 6, no. 1, pp. 68–77, 2020, doi: 10.9781/ijimai.2020.02.006.
[11]	M. Ibrahim, I. S. Bajwa, N. Sarwar, F. Hajjej, and H. A. Sakr, “An Intelligent Hybrid Neural Collaborative Filtering Approach for True Recommendations,” IEEE Access, vol. 11, pp. 64831–64849, 2023, doi: 10.1109/ACCESS.2023.3289751.
[12]	R. J. K. Almahmood and A. Tekerek, “Issues and Solutions in Deep Learning-Enabled Recommendation Systems within the E-Commerce Field,” Nov. 01, 2022, MDPI. doi: 10.3390/app122111256.
[13]	R. A. E. D. Ahmed, M. Fernández-Veiga, and M. Gawich, “Neural Collaborative Filtering with Ontologies for Integrated Recommendation Systems,” Sensors, vol. 22, no. 2, Jan. 2022, doi: 10.3390/s22020700.
[14]	X. Zhang, H. Liu, X. Chen, J. Zhong, and D. Wang, “A novel hybrid deep recommendation system to differentiate user’s preference and item’s attractiveness,” Inf. Sci. (N Y)., vol. 519, pp. 306–316, May 2020, doi: 10.1016/j.ins.2020.01.044.
[15]	S. Khodabandehlou, “Designing an e-commerce recommender system based on collaborative filtering using a data mining approach,” Int. J. Bus. Inf. Syst., vol. 31, no. 4, pp. 455–478, 2019, doi: 10.1504/IJBIS.2019.101582.
[16]	M. Alghieth, “Developing a Recommendation System for Financial Management Using Collaborative Filtering and SequenceMatcher,” Neural Networks, vol. 170, pp. 430–438, 2024, doi: 10.1016/j.neunet.2024.01.436.
[17]	X. Chen, Y. Guo, H. Xu, H. Yan, and L. Lin, “User Demographic Prediction Based on the Fusion of Mobile and Survey Data,” IEEE Access, vol. 10, pp. 111507–111527, 2022, doi: 10.1109/ACCESS.2022.3215732.
[18]	G. Chornous, I. Nikolskyi, M. Wyszyński, G. Kharlamova, and P. Stolarczyk, “A hybrid user-item-based collaborative filtering model for e-commerce recommendations,” Journal of International Studies, vol. 14, no. 4, pp. 157–173, 2021, doi: 10.14254/2071-8330.2021/14-4/11.
[19]	M. Srifi, A. Oussous, A. A. Lahcen, and S. Mouline, “Recommender systems based on collaborative filtering using review texts-A survey,” Jun. 01, 2020, MDPI AG. doi: 10.3390/INFO11060317.
[20]	I. Balush, V. Vysotska, and S. Albota, “Recommendation System Development Based on Intelligent Search, NLP and Machine Learning Methods.”
[21]	Y. Peng, R. Hu, and Y. Wen, “CA-NCF: A Category Assisted Neural Collaborative Filtering Approach for Personalized Recommendation,” in Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 241–247. doi: 10.1109/PIC53636.2021.9687049.
[22]	D. Gao, “Deep Hierarchical Classification for Category Prediction in E-commerce System,” in Proceedings of The 3rd Workshop on e-Commerce and NLP, Stroudsburg, PA, USA: Association for Computational Linguistics, 2020, pp. 64–68. doi: 10.18653/v1/2020.ecnlp-1.10.
[23]	S. Soumik, ✉ Mrinmoy Sarkar, and M. M. Rahman, “Fraud Detection and Personalized Recommendations on Synthetic E-Commerce Data with ML,” 2021, doi: 10.61424/rjbe.
[24]	S. Zhang and K. Balog, “Evaluating Conversational Recommender Systems via User Simulation,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2020, pp. 1512–1520. doi: 10.1145/3394486.3403202.
[25]	F. T. Abdul Hussien, A. M. S. Rahma, and H. B. Abdul Wahab, “Recommendation Systems for E-commerce Systems An Overview,” in Journal of Physics: Conference Series, IOP Publishing Ltd, May 2021. doi: 10.1088/1742-6596/1897/1/012024.
[26]	T. Vu Ngoc and H. Tran Thi, “Techniques, benefits, and challenges of recommendation system in e-commerce: A literature review.” [Online]. Available: www.grandviewresearch.com
[27]	C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Electronic Markets, vol. 31, no. 3, pp. 685–695, Sep. 2021, doi: 10.1007/s12525-021-00475-2.
[28]	J. Bobadilla, A. Gutiérrez, S. Alonso, and Á. González-Prieto, “Neural Collaborative Filtering Classification Model to Obtain Prediction Reliabilities,” Oct. 2024, doi: 10.9781/ijimai.2021.08.010.
[29]	M. Andrus, E. Spitzer, J. Brown, and A. Xiang, “What we can’t measure, We can’t understand: Challenges to demographic data procurement in the pursuit of fairness,” in FAccT 2021 - Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, Inc, Mar. 2021, pp. 249–260. doi: 10.1145/3442188.3445888.
[30]	N. Indah Putri et al., “SISTEM REKOMENDASI HIBRID PEMILIHAN MOBIL BERDASARKAN PROFIL PENGGUNA DAN PROFIL BARANG,” 2021.
[31]	M. Andrus and S. Villeneuve, “Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairness,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Jun. 2022, pp. 1709–1721. doi: 10.1145/3531146.3533226.
citation:   Rahman, Wahyu Arief  (2026) OPTIMASI KINERJA ARSITEKTUR TWO-TOWER NEURAL COLLABORATIVE FILTERING UNTUK PENANGANAN COLD START PADA DATA IMPLICIT FEEDBACK E-COMMERCE.  S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa.   
document_url: https://eprints.untirta.ac.id/58151/1/Wahyu%20Arief%20Rahman_3337210024_Fulltext.pdf
document_url: https://eprints.untirta.ac.id/58151/2/Wahyu%20Arief%20Rahman_3337210024_01.pdf
document_url: https://eprints.untirta.ac.id/58151/3/Wahyu%20Arief%20Rahman_3337210024_02.pdf
document_url: https://eprints.untirta.ac.id/58151/7/Wahyu%20Arief%20Rahman_3337210024_03.pdf
document_url: https://eprints.untirta.ac.id/58151/8/Wahyu%20Arief%20Rahman_3337210024_04.pdf
document_url: https://eprints.untirta.ac.id/58151/9/Wahyu%20Arief%20Rahman_3337210024_05.pdf
document_url: https://eprints.untirta.ac.id/58151/10/Wahyu%20Arief%20Rahman_3337210024_Ref.pdf
document_url: https://eprints.untirta.ac.id/58151/11/Wahyu%20Arief%20Rahman_3337210024_Lamp.pdf
document_url: https://eprints.untirta.ac.id/58151/12/Wahyu%20Arief%20Rahman_3337210024_CP.pdf