Pengembangan Sistem Rekomendasi Venue Hotel Berbasis Retrieval-Augmented Generation (RAG) untuk Perencanaan Event MICE.

Pengembangan Sistem Rekomendasi Venue Hotel Berbasis Retrieval-Augmented Generation (RAG) untuk Perencanaan Event MICE.

• By Nuryani Mawar Putri;
• Tesis
• 15
• 1-111

Hotel venue selection for Meetings, Incentives, Conventions, and Exhibitions (MICE) in Indonesia still faces manual search, fragmented information, and keyword-based search that cannot capture multi-criteria needs. This study aims to develop and evaluate a hotel venue recommendation system based on Retrieval-Augmented Generation (RAG). The research method combines system development with an ablation of eight configurations integrating Multi-Query Retrieval, Metadata Filtering (MF), Hypothetical Document Embeddings, and Reciprocal Rank Fusion over 1,741 venues in 36 provinces and 142 cities, tested on 40 ground-truth queries (320 runs) and evaluated by 38 MICE practitioners (TAM, SUS). The results show the MF configuration performs best, with Context Precision@8 1.000 and Constraint Violation Rate 0%, outperforming the baseline (0.181; 37.5%) and the full configuration (0.241), significant under Wilcoxon (p<0.001), with TAM 4.41 to 4.47 and SUS 77.7 exceeding the reference 68. This study shows Metadata Filtering is key to improving relevance and compliance with user constraints.

Keywords: Retrieval-Augmented Generation, Metadata Filtering, Venue Recommendation System, Ablation Study, MICE

• Katakunci Retrieval-Augmented Generation, Metadata Filtering, Sistem Rekomendasi Venue, Studi Ablasi, MICE
• URL http://
• Penerbit Universitas Nusa Mandiri,

REFERENSI

[1]      Iis Zatnika, “Kinerja MICE Hingga September 2025, 134 Acara, Serap 95 Ribu Pekerja, Hasilkan Perputaran Ekonomi Rp11,82 Triliun,” Media Indonesia, Dec. 03, 2025. Accessed: Jul. 27, 2026. [Online]. Available: https://mediaindonesia.com/ekonomi/836583/kinerja-mice-hingga-september-2025-134-acara-serap-95-ribu-pekerja-hasilkan-perputaran-ekonomi-rp1182-triliun-#google_vignette

[2]      Biro Komunikasi, “Wamenpar menegaskan Bali memiliki potensi yang sangat besar dalam industri MICE global. Berdasarkan data International Congress and Convention Association (ICCA), Bali menempati peringkat ke-38 dunia sebagai destinasi penyelenggaraan pertemuan internasional asosiasi.,” kemenpar.go.id, Jun. 06, 2026. Accessed: Aug. 01, 2026. [Online]. Available: https://kemenpar.go.id/pelatihan-parekraf/siaran-pers-wamenpar-bali-punya-modal-besar-jadi-destinasi-mice-kelas-dunia

[3]      D. Hur, S. Lee, and H. Kim, “Are we ready for MICE 5.0? An investigation of technology use in the MICE industry using social media big data,” Tour. Manag. Perspect., vol. 43, 2022, doi: 10.1016/j.tmp.2022.100991.

[4]      D. Hradecky, J. Kennell, W. Cai, and R. Davidson, “Organizational readiness to adopt artificial intelligence in the exhibition sector in Western Europe,” Int. J. Inf. Manage., vol. 65, 2022, doi: 10.1016/j.ijinfomgt.2022.102497.

[5]      S. Klinmalai and P. Kaewlai, “Assessment and selection criteria for MICE destinations and convention centers in Thailand,” Journal of Architectural/Planning Research and Studies, vol. 21, no. 2, pp. 245–262, 2024, doi: 10.56261/jars.v21.258316.

[6]      D. Buhalis and R. Leung, “Smart hospitality - Interconnectivity and interoperability towards an ecosystem,” Int. J. Hosp. Manag., vol. 71, pp. 41–50, 2018, doi: 10.1016/j.ijhm.2017.11.011.

[7]      Q. Y. Shambour, A. A. Abu-Shareha, and M. M. Abualhaj, “A hotel recommender system based on multi-criteria collaborative filtering,” Information Technology and Control, vol. 51, no. 2, pp. 390–402, 2022, doi: 10.5755/j01.itc.51.2.30701.

[8]      M. A. Setiyawan and E. D. Kenoya, “Pengembangan chatbot Telegram FAQ layanan ICT menggunakan algoritma Random Forest dan metode Word2Vec,” INTI Nusa Mandiri, vol. 20, no. 1, pp. 150–162, 2025, doi: 10.33480/inti.v20i1.5766.

[9]      A. Ro’uf, H. Asy’ari, M. Y. Urrohman, and F. D. Rahmawati, “Rekomendasi pekerjaan bidang ekonomi: Sistem rekomendasi menggunakan content based,” INTI Nusa Mandiri, vol. 20, no. 1, pp. 56–64, 2025, doi: 10.33480/inti.v20i1.6786.

[10]    N. M. Putri and I. Saputra, “A Multimodal Graph-Based Recommendation Architecture for Vendor Discovery in Context-Aware Event Planning,” Journal of Novel Engineering Science and Technology, vol. 5, no. 01, pp. 1–8, May 2026, doi: 10.56741/jnest.v5i01.1050.

[11]    Y. K. Dwivedi, N. Pandey, W. Currie, and A. Micu, “Leveraging ChatGPT and other generative artificial intelligence (AI)-based applications in the hospitality and tourism industry: practices, challenges and research agenda,” International Journal of Contemporary Hospitality Management, vol. 36, no. 1, pp. 1–12, Jan. 2024, doi: 10.1108/IJCHM-05-2023-0686.

[12]    Z. Zhao et al., “Recommender Systems in the Era of Large Language Models (LLMs),” IEEE Trans. Knowl. Data Eng., vol. 36, no. 11, pp. 6889–6907, Nov. 2024, doi: 10.1109/TKDE.2024.3392335.

[13]    A. Suryadi and I. Saputra, “Privacy-Preserving Automated QA Dataset Generation for Fine-Tuning LLMs with Local Models and Information Retrieval,” JURNAL INFOTEL, vol. 17, no. 4, pp. 825–838, Jan. 2026, doi: 10.20895/infotel.v17i4.1388.

[14]    Y. X. X. G. K. J. J. P. Y. B. Y. D. J. S. M. W. and H. W. Yunfan Gaoa, “Retrieval-Augmented Generation for Large Language Models: A Survey”.

[15]    E. P. A. P. F. P. V. K. N. G. H. K. M. L. W. Y. T. R. S. R. D. K. Patrick Lewis, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems, 2020, pp. 9459–9474.

[16]    M. H. Wijaya and H. Jayadianti, “Implementation of RAG-based LLM chatbot for hotel services: A case study,” International Journal of Multidisciplinary Sciences and Arts, vol. 5, no. 1, pp. 275–281, 2026, doi: 10.47709/ijmdsa.v5i1.7927.

[17]    R. Karlović, M. Rovis, A. Smajić, L. Sever, and I. Lorencin, “Context-aware tourism recommendations using retrieval-augmented large language models and semantic re-ranking,” Electronics (Basel)., vol. 14, no. 22, 2025, doi: 10.3390/electronics14224448.

[18]    A. Banerjee, A. Satish, and W. Wörndl, “Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation,” 2025, pp. 19–34. doi: 10.1007/978-3-031-87654-7_3.

[19]    S. Song, C. Yang, L. Xu, H. Shang, Z. Li, and Y. Chang, “TravelRAG: A tourist attraction retrieval framework based on multi-layer knowledge graph,” ISPRS Int. J. Geoinf., vol. 13, no. 11, 2024, doi: 10.3390/ijgi13110414.

[20]    C. Wei, K. Duan, S. Zhuo, H. Wang, S. Huang, and J. Liu, “Enhanced recommendation systems with retrieval-augmented large language model,” Journal of Artificial Intelligence Research, vol. 82, pp. 1147–1173, 2025, doi: 10.1613/jair.1.17809.

[21]    X. Ma, Y. Gong, P. He, H. Zhao, and N. Duan, “Query rewriting for retrieval-augmented large language models,” in Proc. 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023, pp. 5303–5315. doi: 10.18653/v1/2023.emnlp-main.322.

[22]    L. Gao, X. Ma, J. Lin, and J. Callan, “Precise zero-shot dense retrieval without relevance labels,” in Proc. 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023. doi: 10.18653/v1/2023.acl-long.99.

[23]    G. V Cormack, C. L. A. Clarke, and S. Buettcher, “Reciprocal rank fusion outperforms Condorcet and individual rank learning methods,” in Proc. 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2009, pp. 758–759. doi: 10.1145/1571941.1572114.

[24]    N. F. L. et al., “Lost in the middle: How language models use long contexts,” Trans. Assoc. Comput. Linguist., vol. 12, pp. 157–173, 2024, doi: 10.1162/tacl_a_00638.

[25]    S. Es, J. James, L. Espinosa Anke, and S. Schockaert, “RAGAs: Automated Evaluation of Retrieval Augmented Generation,” in Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Stroudsburg, PA, USA: Association for Computational Linguistics, 2024, pp. 150–158. doi: 10.18653/v1/2024.eacl-demo.16.

[26]    F. D. Davis, “Perceived usefulness, perceived ease of use, and user acceptance of information technology,” MIS Quarterly, vol. 13, no. 3, pp. 319–340, 1989, doi: 10.2307/249008.

[27]    A. Bangor, P. T. Kortum, and J. T. Miller, “An empirical evaluation of the System Usability Scale,” Int. J. Hum. Comput. Interact., vol. 24, no. 6, pp. 574–594, 2008, doi: 10.1080/10447310802205776.

[28]    D. Getz and S. J. Page, “Progress and prospects for event tourism research,” Tour. Manag., vol. 52, pp. 593–631, 2016, doi: 10.1016/j.tourman.2015.03.007.

[29]    G. I. Crouch and J. J. Louviere, “The determinants of convention site selection: A logistic choice model from experimental data,” J. Travel Res., vol. 43, no. 2, pp. 118–130, 2004, doi: 10.1177/0047287504268233.

[30]    J. Borràs, A. Moreno, and A. Valls, “Intelligent tourism recommender systems: A survey,” Expert Syst. Appl., vol. 41, no. 16, pp. 7370–7389, 2014, doi: 10.1016/j.eswa.2014.06.007.

[31]    D. Jannach, A. Manzoor, W. Cai, and L. Chen, “A survey on conversational recommender systems,” ACM Comput. Surv., vol. 54, no. 5, 2021, doi: 10.1145/3453154.

[32]    J. L. et al., “How can recommender systems benefit from large language models: A survey,” ACM Trans. Inf. Syst., vol. 43, no. 2, 2025, doi: 10.1145/3678004.

[33]    V. K. et al., “Dense passage retrieval for open-domain question answering,” in Proc. EMNLP, 2020. doi: 10.18653/v1/2020.emnlp-main.550.

[34]    N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-networks,” in Proc. EMNLP-IJCNLP, 2019. doi: 10.18653/v1/D19-1410.

[35]    A. Vaswani, “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017.

[36]    J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019. doi: 10.18653/v1/N19-1423.

[37]    T. B. B. et al., “Language models are few-shot learners,” in Advances in Neural Information Processing Systems (NeurIPS), 2020.

[38]    Z. J. et al., “Survey of hallucination in natural language generation,” ACM Comput. Surv., vol. 55, no. 12, 2023, doi: 10.1145/3571730.

[39]    W. F. et al., “A survey on RAG meeting LLMs: Towards retrieval-augmented large language models,” in Proc. 30th ACM SIGKDD, 2024. doi: 10.1145/3637528.3671470.

[40]    Z. Rackauckas, “RAG-Fusion: A new take on retrieval-augmented generation,” 2024.

[41]    L. Wang, N. Yang, and F. Wei, “Query2doc: Query expansion with large language models,” 2023.

[42]    J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with GPUs,” IEEE Trans. Big Data, vol. 7, no. 3, pp. 535–547, 2021, doi: 10.1109/TBDATA.2019.2921572.

[43]    V. Venkatesh, M. G. Morris, G. B. Davis, and F. D. Davis, “User acceptance of information technology: Toward a unified view,” MIS Quarterly, vol. 27, no. 3, pp. 425–478, 2003, doi: 10.2307/30036540.

[44]    J. Brooke, “SUS: A ‘quick and dirty’ usability scale,” in Usability Evaluation in Industry, London: Taylor & Francis, 1996, pp. 189–194.

[45]    P. Vlachogianni and N. Tselios, “Perceived usability evaluation of educational technology using the System Usability Scale (SUS): A systematic review,” Journal of Research on Technology in Education, vol. 54, no. 3, pp. 392–409, 2022, doi: 10.1080/15391523.2020.1867938.

[46]    W. S. et al., “REPLUG: Retrieval-augmented black-box language models,” 2024.

[47]    A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi, “Self-RAG: Learning to retrieve, generate, and critique through self-reflection,” 2024.

[48]    A. Bozanta and B. Kutlu, “HybRecSys: Content-based contextual hybrid venue recommender system,” J. Inf. Sci., 2019.

[49]    K. A. F. et al., “Hybrid recommender system for tourism based on big data and AI: A conceptual framework,” Big Data Mining and Analytics, vol. 4, no. 1, pp. 47–55, 2021, doi: 10.26599/BDMA.2020.9020015.

[50]    I. Pujiono, I. M. Agtyaputra, and Y. Ruldeviyani, “Implementing Retrieval-Augmented Generation and Vector Databases for Chatbots in Public Services Agencies Context,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 10, no. 1, pp. 216–223, 2024, doi: 10.33480/jitk.v10i1.5572.

[51]    V. F. Hakim and D. Riana, “Analysis of User Complaints for Telecommunication Brands on X (Twitter) using IndoBERT and Deep Learning,” JANAPATI (Jurnal Nasional Pendidikan Teknik Informatika), vol. 13, no. 2, 2024, doi: 10.23887/janapati.v13i2.76497.