Rancang Bangun AI Sales Agent Menggunakan Metode SDLC dan Large Language Model untuk Otomatisasi Penjualan
Keywords:
AI Sales Agent, Large Language Model, Retrieval-Augmented Generation, conversational commerce, System Development Life CycleAbstract
Proses penjualan berbasis percakapan pada bisnis retail masih menghadapi kendala seperti keterlambatan respon, inkonsistensi layanan, dan ketergantungan pada tenaga penjualan. Penelitian ini bertujuan merancang dan membangun AI Sales Agent menggunakan metode System Development Life Cycle (SDLC) dan Large Language Model (LLM) untuk otomatisasi penjualan end-to-end pada bisnis retail. Sistem dikembangkan dengan mengintegrasikan pendekatan Retrieval-Augmented Generation (RAG), knowledge base bisnis, dan Sales State Machine untuk menghasilkan interaksi penjualan yang kontekstual dan konsisten. Metode SDLC diterapkan melalui enam tahapan: planning, analysis, design, implementation, testing, dan maintenance. Pengujian dilakukan menggunakan Black Box Testing dan Scenario-Based Evaluation terhadap tujuh requirement fungsional dan non-fungsional. Hasil pengujian menunjukkan kecepatan respon rata-rata 4,2 detik, akurasi rekomendasi dengan cosine similarity 0,96, context understanding 100%, retrieval relevance Precision@K 0.90, task completion rate 90%, skalabilitas 20 percakapan simultan, dan ketersediaan sistem 24/7. Sistem berhasil mengotomatisasi proses penjualan melalui WhatsApp secara kontekstual, konsisten, dan skalabel.
References
[1] G. McLean and A. Wilson, "Shopping in the digital world: Examining customer engagement through conversational commerce," J. Bus. Res., 2022.
[2] T. Davenport, A. Guha, D. Grewal, and T. Bressgott, "How artificial intelligence will change the future of marketing," J. Acad. Mark. Sci., 2023.
[3] T. Y. Lin, Y. X. Wang, X. Y. Liu, and X. P. Qiu, "A survey of transformers," AI Open, vol. 3, pp. 111-132, 2022.
[4] W. X. Zhao et al., "A survey of large language models," ACM Comput. Surv., vol. 55, no. 13, pp. 1-40, 2023.
[5] N. T. K. Le, N. Hadiprodjo, H. El-Alfy, and A. Kerimzhanov, "The recent large language models in NLP," in Proc. 22nd Int. Symp. Commun. Inf. Technol. (ISCIT), 2023.
[6] K. Shuster et al., "Language models that seek for knowledge: Modular search & generation for dialogue," in Proc. ACL Conf., 2021.
[7] Y. Gao, Y. Xiong, X. Gao, et al., "Retrieval-augmented generation for large language models: A survey," arXiv preprint arXiv:2312.10997, 2023.
[8] J. Deriu, A. Rodrigo, A. Otegi, G. Echegoyen, S. Rosset, and J. Gonzalvo, "Survey on evaluation methods for dialogue systems," Artif. Intell. Rev., vol. 54, pp. 755-810, 2021.
[9] I. Inayat, S. Salim, S. Marczak, M. Daneva, and S. Shamshirband, "A systematic literature review on agile requirements engineering practices and challenges," Comput. Hum. Behav., vol. 51, pp. 915-929, 2021.
[10] M. Kassab, J. DeFranco, and P. Laplante, "A systematic literature review on the role of stakeholders in requirements engineering," J. Syst. Softw., vol. 188, 2022.
[11] A. Følstad and P. B. Brandtzaeg, "Chatbots and the new world of HCI," Interactions, vol. 28, no. 4, pp. 38-42, 2021.
[12] J. Huang and R. T. Rust, "Artificial intelligence in service," J. Serv. Res., 2023.
[13] R. Stair and G. Reynolds, Principles of Information Systems, 14th ed. Boston, MA: Cengage Learning, 2021.
[14] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Upper Saddle River, NJ: Pearson, 2021.
[15] I. Sommerville, Software Engineering, 10th ed. London, UK: Pearson, 2021.
[16] C. Ebert and C. Pampus, "Requirements engineering: Foundation for software quality," IEEE Softw., vol. 39, no. 1, pp. 15-22, 2022.
[17] S. Al-Fedaghi and A. Al-Otiabi, "Traceability in software engineering: A conceptual model," Int. J. Adv. Comput. Sci. Appl. (IJACSA), vol. 12, no. 5, pp. 73-81, 2021.
[18] A. Neelakantan et al., "Text and code embeddings by contrastive pre-training," arXiv preprint arXiv:2201.10005, 2022.
[19] Y. Feng et al., "A survey on dialog management: Recent advances and challenges," IEEE Trans. Knowl. Data Eng., vol. 35, no. 8, pp. 8213-8232, 2023.
[20] T. Schick et al., "Toolformer: Language models can teach themselves to use tools," in Proc. NeurIPS, vol. 36, pp. 68539-68551, 2023.
[21] Object Management Group, OMG Unified Modeling Language (OMG UML) Specification Version 2.5.1, Object Management Group, 2021.
[22] Meta Platforms Inc., "WhatsApp Business Platform Documentation," 2023. [Online]. Available: https://developers.facebook.com/docs/whatsapp
[23] Y. K. Dwivedi et al., "So what if ChatGPT wrote it? Multidisciplinary perspectives on AI," Int. J. Inf. Manage., 2023.
[24] C. Zhang et al., "A survey on evaluation methods for conversational agents," ACM Comput. Surv., 2023.
[25] G. McLean and K. Osei-Frimpong, "Conversational commerce: Opportunities and challenges," J. Bus. Res., 2022.
