Model Bisnis Website Rekomendasi Perjalanan Berbasis Sistem Multi Agen

Rafael Simson Riston; Muhammad Jamil; Valentino Aris

doi:10.47134/jacis.v6i2.201

Authors

Rafael Simson Riston Universitas Negeri Makassar
Muhammad Jamil Universitas Negeri Makassar
Valentino Aris Universitas Negeri Makassar

DOI:

https://doi.org/10.47134/jacis.v6i2.201

Keywords:

Cost Benefit Analysis, Large Language Model, rekomendasi perjalanan, sistem multi agen, transformasi digital

Abstract

Perencanaan perjalanan internasional masih menghadapi kendala akibat fragmentasi informasi dan information overload yang menghambat pengambilan keputusan wisatawan. Penelitian ini bertujuan mengembangkan DrTrips, website rekomendasi perjalanan berbasis Multi Agent System (MAS) dan Large Language Model (LLM), serta merumuskan model bisnisnya. Penelitian menggunakan metode Research and Development (R&D) model 4D yang meliputi Define, Design, Develop, dan Disseminate. Sistem dikembangkan dengan arsitektur Orchestrator–Workers yang terdiri atas satu agen orkestrasi dan empat agen spesialis untuk mengelola destinasi, logistik, regulasi perjalanan, dan penyusunan itinerary. Hasil Black-box Testing pada 15 skenario menunjukkan tingkat keberhasilan 100%. Evaluasi menggunakan 180 skenario TravelPlanner menghasilkan Final Pass Rate 48,9%, lebih tinggi dibandingkan konfigurasi single-agent, sedangkan evaluasi usabilitas menggunakan USE Questionnaire memperoleh skor 86,85% dalam kategori Sangat Bermanfaat. Model bisnis disusun menggunakan Lean Canvas dan divalidasi melalui Cost Benefit Analysis berbasis Discounted Cash Flow selama lima tahun yang menghasilkan NPV sebesar Rp2,7 miliar, BCR 1,21, IRR 50,44%, dan Discounted Payback Period 48 bulan. Dalam cakupan evaluasi dan asumsi yang digunakan, hasil penelitian menunjukkan bahwa integrasi MAS dan LLM tidak hanya meningkatkan kualitas rekomendasi perjalanan, tetapi juga mendukung pengembangan platform yang layak secara teknis dan memiliki prospek bisnis yang positif

References

[1] B. D. dan S. Informasi, “Perkembangan Perjalanan Wisatawan Nasional Tahun 2019-2024,” Kementrian Pariwisata Republik Indonesia, 2025. kemenpar.go.id/statistik-wisatawan-nasional/perkembangan-perjalanan-wisatawan-nasional-tahun-2019-2024 (accessed Aug. 26, 2025).

[2] M. D. Kumar Roy, P. Tejaswini, P. U. Chandra, T. J. Latha, and M. Deeksha, “Smart Travel: Your Ultimate Itinerary Companion,” Int. J. Eng. Technol. Manag. Sci., vol. 3, no. 8, pp. 229–235, 2024, doi: 10.46647/ijetms.2024.v08i03.028.

[3] Z. A. Azeez, “The Role of Modern Interactive Media in Making Travel Decisions,” Int. J. Prof. Stud., vol. 18, no. 1, pp. 47–70, 2024, doi: 10.37648/ijps.v18i01.005.

[4] E. Erbil and W. Worndl, “Personalization Of Multi-Day Round Trip Itineraries According To Travelers’ Preferences,” in Proceedings of the ENTER 2022 eTourism Conference, 2022, pp. 187–199. doi: 10.1007/978-3-030-94751-4_17.

[5] A. N. Deshmukh, A. Monga, K. Gawade, and S. Gawade, “Smart Travel Companion : AI-Driven Trip Planning Mobile Application,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 5, no. 2, pp. 393–397, 2025, doi: 10.48175/IJARSCT-23763.

[6] H. Kaur, “Consumer Decision-Making in the Era of Information Overload,” Univers. Res. Reports, vol. 11, no. 2, pp. 27–31, 2024, doi: 10.36676/urr.v11.i2.04.

[7] R. Guo and H. Li, “Can the amount of information and information presentation reduce choice overload ? An empirical study of online hotel booking,” J. Travel Tour. Mark., vol. 39, no. 1, pp. 87–108, 2022, doi: 10.1080/10548408.2022.2044970.

[8] Y. Choi, B. Hickerson, J. Lee, H. Lee, and Y. Choe, “Digital Tourism and Wellbeing: Conceptual Framework to Examine Technology Effects of Online Travel Media,” Int. J. Environ. Res. Public Heal. Artic., vol. 19, no. 5639, p. 13, 2022, doi: 10.3390/ ijerph19095639 Academic.

[9] M.-E. Pérez-Pons et al., “A brief review on Multi-Agent System Approaches and Methodologies,” in Proceedings of the IV Workshop on Disruptive Information and Communication Technologies for Innovation and Digital Transformation, 2022, pp. 35–47.

[10] S. Chen et al., “Applied sciences Application of Ant Colony Optimization Computing to a Recommended Travel Itinerary Planning System with Repeatedly Used Nodes,” Appl. Sci., vol. 13, no. 13221, p. 23, 2023, doi: 10.3390/app132413221.

[11] O. Fagbohun, R. M. Harrison, and A. Dereventsov, “An Empirical Categorization of Prompting Techniques For Large Language Models: A Practitioner’s Guide,” 4th Int. Conf. AI, ML, Data Sci. Robot. (2023)., pp. 1–16, 2023, doi: 10.48550/arXiv.2402.14837.

[12] X. Li, S. Wang, S. Zeng, Y. Wu, and Y. Yang, “A survey on LLM ‑ based multi ‑ agent systems: workflow , infrastructure, and challenges,” Vicinagearth, vol. 1, no. 9, pp. 1–43, 2024, doi: 10.1007/s44336-024-00009-2.

[13] A. Kumar, M. M. Tripathi, and P. Prajapati, “Voyage Ai: The Smart & Ai-Driven Navigation Companion,” Int. J. Multidiscip. Res., vol. 7, no. 2, pp. 1–7, 2025, doi: 10.36948/ijfmr.2025.v07i03.46840.

[14] A. Chen, X. Ge, Z. Fu, Y. Xiao, and J. Chen, “TravelAgent: An AI Assistant for Personalized Travel Planning,” Artif. Intell., no. September, 2024, doi: 10.48550/arXiv.2409.08069.

[15] A. Singh, R. Madhogaria, A. Misra, and E. Elakiya, “Automated Travel Planning Via Multi-Agent Systems and Real- Time Intelligence,” Proc. 3rd Int. Conf. Optim. Tech. F. Eng., vol. 15 Novembe, p. 13, 2024, doi: 10.2139/ssrn.5089025.

[16] V. Udandarao, N. Abraham, M. Vairamuthu, and H. Mistry, “Roamify : Designing and Evaluating an LLM Based Google,” Human-Computer Interact., vol. Maret, pp. 1–12, 2025, doi: 10.48550/arXiv.2504.10489.

[17] J. Xie, K. Zhang, J. Chen, T. Zhu, and R. Lou, “TravelPlanner: A Benchmark for Real-World Planning with Language Agents,” Comput. Lang., vol. Oktober, p. 24, 2024, doi: 10.48550/arXiv.2402.01622.

[18] T. D. Harjanto, A. Vatresia, and R. Faurina, “Analisis Penetapan Skala Prioritas Penanganan Balita Stunting Menggunakan Metode DBSCAN Clustering (Studi Kasus Data Dinas Kesehatan Kabupaten Lebong),” Rekursif J. Inform., vol. 9, no. 1, pp. 30–42, 2021, doi: 10.33369/rekursif.v9i1.14982.

[19] R. Ambarwati, “PENGEMBANGAN MAKANAN TAMBAHAN BERBASIS F100 DENGAN SUBSTITUSI TEPUNG LABU KUNING DAN TEPUNG PISANG,” J. Nutr. Coll., 2020, doi: 10.14710/jnc.v9i2.27033.

[20] M. Suhendra, W. Swastika, and M. Subianto, “Analisis Sentimen Pada Ulasan Aplikasi Video Conference Menggunakan Naive Bayes,” Sainsbertek J. Ilm. Sains Teknol., vol. 2, no. 1, pp. 1–9, 2021, doi: 10.33479/sb.v2i1.145.

[21] M. N. Maskuri, Harliana, K. Sukerti, and R. M. H. Bhakti, “Penerapan Algoritma K-Nearest Neighbor (KNN) untuk Memprediksi Penyakit Stroke,” J. Ilm. Intech Inf. Technol. J. UMUS, vol. 4, no. 1, pp. 130–140, 2022.

[22] D. Darwis, N. Siskawati, and Z. Abidin, “Penerapan Algoritma Naive Bayes Untuk Analisis Sentimen Review Data Twitter BMKG Nasional,” J. Tekno Kompak, vol. 15, no. 1, p. 131, 2021, doi: 10.33365/jtk.v15i1.744.