Sistem Manajemen Marketing dan Promosi dengan Integrasi Large Language Model berbasis Privacy-Preserving Architecture
Abstract
Unit Marketing dan Promosi (Markprom) Universitas Muhammadiyah Metro menghadapi sejumlah permasalahan operasional yang berdampak pada efektivitas rekrutmen mahasiswa baru, di antaranya pencatatan data calon mahasiswa baru (camaba) yang masih konvensional, minimnya komunikasi dengan program studi, tidak tersedianya dokumen resmi bagi prodi, serta tidak adanya platform digital khusus untuk pengelolaan event dan publikasi kegiatan. Penelitian ini bertujuan untuk mengembangkan sistem informasi manajemen terintegrasi untuk unit Markprom yang mencakup modul pendataan camaba, sistem antrean digital, manajemen event, portal laporan program studi, serta integrasi kecerdasan buatan berbasis Large Language Model (LLM). Metode pengembangan yang digunakan adalah model Waterfall Software Development Life Cycle (SDLC). Integrasi LLM diimplementasikan menggunakan pendekatan snapshot-based privacy-preserving, di mana sistem mengambil data agregat dari database, membuang kolom sensitif, kemudian mengirimkan snapshot bersama pertanyaan pengguna ke API Gemini Flash Lite atau model via OpenRouter untuk dianalisis. Prompt engineering diterapkan untuk membatasi respons AI hanya pada domain fungsi unit Markprom. Pengujian sistem dilakukan menggunakan Black Box Testing. Hasil penelitian menunjukkan seluruh fitur berjalan sesuai skenario yang diharapkan, dan fitur AI mampu menghasilkan analisis strategis berbasis data camaba yang dapat diunduh dalam format PDF. Sistem ini diharapkan meningkatkan efisiensi operasional unit Markprom dan mendukung pengambilan keputusan berbasis data dalam strategi pemasaran perguruan tinggi.
References
[2]. Alahmari, S. S., Hall, L., Mouton, P. R., & Goldgof, D. (2026). Large language models robustness against perturbation. Scientific Reports, 16(1), 1–10. https://doi.org/10.1038/s41598-025-29770-0
[3]. ALazzawi, A., Yas, Q. M., & Rahmatullah, B. (2023). A Comprehensive Review of Software Development Life Cycle methodologies: Pros, Cons, and Future Directions. Iraqi Journal for Computer Science and Mathematics, 4(4), 173–190. https://doi.org/10.52866/ijcsm.2023.04.04.014
[4]. Bang, B., Yoon, J., Chang, D.-J., Park, S., & Lee, Y. O. (2026). Retrieval augmented large language model system for comprehensive drug contraindications. Health Information Science and Systems, 14(1), 1–26. https://doi.org/10.1007/s13755-025-00420-z
[5]. Belhachem, H., & Chikh, A. (2026). Trust-Enhanced Socialization, Externalization, Combination, and Internalization Model for Quantitative Requirements Elicitation: Longitudinal Validation in Higher Education Projects. Ingenierie Des Systemes d’Information, 31(4), 1069–1085. https://doi.org/10.18280/isi.310405
[6]. Berini, A. D. E., Jamil, N., Benrazek, A. E., Lakas, A., Ismail, L., Ferrag, M. A., & Lam, K. Y. (2026). Security and privacy in LLMs: A comprehensive survey of threats and mitigation strategies. Information Fusion, 132(3), 104241. https://doi.org/10.1016/j.inffus.2026.104241
[7]. Choi, J., Jung, Y. A., & Ko, H. (2025). Comparative Analysis of SQL Injection Defense Mechanisms Based on Three Approaches: PDO, PVT, and ART. Applied Sciences (Switzerland), 15(23), 1–22. https://doi.org/10.3390/app152312351
[8]. Ernawati, Baharin, S. S. K., B, & Kasmin, F. (2022). Target Market Determination for Information Distribution and Student Recruitment Using an Extended RFM Model with Spatial Analysis. Journal of Distribution Science, 20(6), 1–10.
[9]. Ernawati, Baharin, S. S. K., Kasmin, F., & Purwanugraha, H. A. (2022). Geo-marketing Promotional Target Selection using Modified RFM with Spatial and Temporal Analysis: A Case Study. Journal of System and Management Sciences, 12(3), 156–180. https://doi.org/10.33168/JSMS.2022.0309
[10]. Gao, Y., Yiu, T. W., Shen, X., & Tam, V. W. Y. (2026). Large language models in smart construction: a systematic review of implementation strategies, applications and future directions. Engineering, Construction and Architectural Management, 33(15), 159–181. https://doi.org/10.1108/ECAM-10-2025-1668
[11]. Ji, Y., Sun, Y., Li, J., Wang, Z., Li, P., Wang, Z., & Zheng, Y. (2026). Semantic-aware pruning of large language models via neuron importance explanation. Expert Systems with Applications, 331(2), 133192. https://doi.org/10.1016/j.eswa.2026.133192
[12]. Marcinkevage, C., & Kumar, A. (2025). Generative AI in Higher Education Constituent Relationship Management (CRM): Opportunities, Challenges, and Implementation Strategies. Computers, 14(3), 1–23. https://doi.org/10.3390/computers14030101
[13]. Nafez Jalal, H., Alhroob, A., Shaheen, A., & Alzyadat, W. (2026). Exploring diverse perspectives: enhancing black box testing through machine learning techniques. International Journal of Informatics and Communication Technology (IJ-ICT), 15(1), 238. https://doi.org/10.11591/ijict.v15i1.pp238-246
[14]. Reusens, M., Goethals, S., Calders, T., & Martens, D. (2026). Would a large language model pay extra for a view? Inferring willingness to pay from subjective choices. Expert Systems with Applications, 331(2), 133279. https://doi.org/10.1016/j.eswa.2026.133279
[15]. Sahu, P. K., & Kumar, R. V. (2026). Navigating the digital landscape: The impact of social media on higher education enrolment and beyond. Knowledge Management and E-Learning, 18(2), 254–280. https://doi.org/10.34105/j.kmel.2026.18.012
[16]. Sasongko, C. D., Isnanto, R. R., & Widodo, A. P. (2026). Sentiment analysis on social media using VADER and LSTM to optimise the marketing strategy for SOE energy products. International Journal of Data and Network Science, 10(1), 87–96. https://doi.org/10.5267/j.ijdns.2025.10.011
[17]. Surjawan, D. J., Langi, A. Z. R., & Imbar, R. V. (2025). Digital Transformation for Institution Operations in Higher Education: A Literature Review. IEEE Access, 13(1), 61457–61468. https://doi.org/10.1109/ACCESS.2025.3557446
[18]. Tahar, K., Verbuecheln, R., Martin, T., Graessner, H., Biergans, S., & Krefting, D. (2026). Sharing EHR data of patients with rare diseases for research - The role of quality assessments in a national federated research data infrastructure. BMC Medical Informatics and Decision Making, 26(1), 1–14. https://doi.org/10.1186/s12911-025-03153-x
[19]. Tarafder, M. T. R., Ansari, M. E., Alam, M. A., Shil, S. K., Islam, R., & Ahmed, K. R. (2025). Leveraging artificial intelligence in management information systems for sustainable supply chain optimization and environmental impact analysis. Discover Artificial Intelligence, 6(56), 1–31. https://doi.org/10.1007/s44163-025-00737-4
[20]. Villegas-Ch, W., Maldonado Navarro, A., Govea, J., Garcia-Ortiz, J., & Buenaño-Fernandez, D. (2026). Federated and explainable learning analytics for privacy-preserving academic risk modeling across heterogeneous educational institutions. Computers and Education: Artificial Intelligence, 11(1), 1–14. https://doi.org/10.1016/j.caeai.2026.100629
[21]. Zanghì, A., Di Filippo, P. S., Rutigliano, C., Moretti, M. C., Avolio, C., & D’Amico, E. (2026). Transitioning from intravenous to subcutaneous ocrelizumab in a high-volume infusion center: A time-and-motion–informed capacity and service-flow analysis. Multiple Sclerosis and Related Disorders, 112(2), 107267. https://doi.org/10.1016/j.msard.2026.107267
[22]. Zhang, T., Patterson, L., Webb, B., Jin, Z., & Beiting-Parrish, M. (2026). Evaluating generative AI chatbots for large-scale assessment data: comparing LLM-as-a-judge and human ratings. Large-Scale Assessments in Education, 14(1), 1–22. https://doi.org/10.1186/s40536-026-00287-w
[23]. Zhao, Q., Yang, H., Song, Q., & Li, X. (2026). KnowPath: leveraging large language model prior reasoning paths for dynamic self-reflective reasoning via knowledge graph subgraph exploration. Expert Systems with Applications, 331(2), 133255. https://doi.org/10.1016/j.eswa.2026.133255



_.png)


.png)
