Natural Language Query Hybrid Architecture for Cross-Sectoral Analytics Dashboards on Public Statistical Data

Yusuf Fadlila Rahcman; Puput Suryaningtyas; Masbahah Masbahah; Nur Azizul Haqimi; Ahmad Faisal Sani

doi:10.59261/jequi.v8i4.430

Authors

Yusuf Fadlila Rahcman Universitas Sebelas Maret
Puput Suryaningtyas Universitas Sebelas Maret
Masbahah Masbahah Universitas Sebelas Maret
Nur Azizul Haqimi Universitas Sebelas Maret
Ahmad Faisal Sani Universitas Sebelas Maret

DOI:

https://doi.org/10.59261/jequi.v8i4.430

Keywords:

Analytics Dashboard, Apriori, Natural Language Query, Public Statistical Data, Text-to-SQL

Abstract

Background: Public statistical data are essential for evidence-based policymaking, yet the complexity of cross-sectoral indicators often limits accessibility for nontechnical users. This challenge is particularly relevant in East Java, where regional development disparities require integrated analytical tools.

Objective: This study aims to develop a cross-sectoral analytics dashboard integrating Natural Language Query (NLQ), Apriori association-rule mining, and a supporting local large language model (LLM).

Methods: The system was developed using the SDLC Waterfall model and utilized more than 50 Statistics Indonesia (BPS) indicators covering 38 districts/cities in East Java from 2016 to 2026. A deterministic, rule- and regular-expression (regex)-based Text-to-SQL mechanism processed natural-language queries, while Apriori identified cross-sectoral association patterns. A local LLM (Ollama, llama3.2:1b) generated supporting narratives. Evaluation included black-box testing, 50-query intent classification, association-rule metrics, and an exploratory LLM assessment.

Results: The NLQ module achieved 96.00% accuracy (48/50 queries). Apriori generated 55,480 high-level rules with an average confidence of 0.909 and lift of 15.44. The exploratory LLM evaluation achieved a composite score of 4.35/5.00, a 2.5% hallucination rate, a 26.07-second P95 latency, and a 100% fallback success rate.

Conclusion: The hybrid architecture effectively supports accessible statistical-data retrieval and cross-sectoral pattern discovery, while the LLM remains a supporting narrative component that requires further formal validation.

Downloads

Download data is not yet available.

References

Adhitya, B., Prabawa, A., & Kencana, H. (2022). Analisis Pengaruh Pendidikan, Kesehatan, Sanitasi dan Rata-Rata Jumlah Anggota Keluarga Per Rumah Tangga terhadap Kemiskinan di Indonesia. Ekonomis: Journal of Economics and Business, 6(1), 288–295. https://doi.org/10.33087/ekonomis.v6i1.501

Agrawal, R., & Srikant, R. (1994). Fast Algorithms for Mining Association Rules in Large Databases. Proc. of the 20th International Conference on Very Large Data Bases (VLDB’94).

Asparosa, N. (2026). Visualisasi Data Kinerja Dinas Kesehatan Daerah Menggunakan Power BI. Teknofile: Jurnal Sistem Informasi, 4(3), 210–219.

Ay, B., & Demirdağ, Y. E. (2026). Benchmarking Ollama and vLLM for Concurrent LLM Serving: A Multi-Scenario Evaluation of Performance and Scalability. Applied Sciences (Switzerland), 16(11). https://doi.org/10.3390/app16115435

Fernandez-Basso, C., Ruiz, M. D., & Martin-Bautista, M. J. (2024). New Spark solutions for distributed frequent itemset and association rule mining algorithms. Cluster Computing, 27(2). https://doi.org/10.1007/s10586-023-04014-w

Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., Yang, A., Fan, A., Goyal, A., Hartshorn, A., Yang, A., Mitra, A., Sravankumar, A., Korenev, A., Hinsvark, A., … Ma, Z. (2024). The Llama 3 Herd of Models.

Han, J., Kamber, M., & Pei, J. (2012). Data Mining: Concepts and Techniques (3rd ed.). Morgan Kaufmann. https://www.sciencedirect.com/book/9780123814791/data-mining-concepts-and-techniques

Ifath, M. A., & Haque, I. (2026). Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 10(1). https://doi.org/10.1145/3788089

Khoirunnisa, S., Nabila, H. H., Fauziah, S., Birawa, M., Syakur, R. A., & Rahayu, S. (2025). Penerapan Algoritma K-Means dan Apriori untuk Analisis Klasterisasi Kemiskinan dan Pola Asosiasi Kepemilikan Bidang Tanah serta Karakteristik Wilayah di Indonesia. RIGGS: Journal of Artificial Intelligence and Digital Business, 4(2), 4911–4917. https://journal.ilmudata.co.id/index.php/RIGGS/article/view/1364

Lubis, H., Komara, M. A., Meidelfi, D., Arsyah, U. I., Santoso, K. I., Sukma, F., Sulistyohati, A., Hasan, F. N., Ismanto, E., & Trisnawan, A. B. (2026). Large Language Models: Konsep, Teknik, dan Aplikasi dalam AI Generatif. PT Penerbit Qriset Indonesia.

Muis, A., Syafwan, H., Arfianto, A. Z., Simanjuntak, M. S., Riyandi, A., Trisnawan, A. B., Ramdhan, W., Triana, H., Saputra, M. H., Handoko, W., Naswin, A., & Suhadi. (2025). DATA MINING: Konsep, Metode, dan Aplikasi. PT. Faaslib Serambi Media. https://faaslibsmedia.com/Buku

Putri, W. C., & Supriyadi, M. E. (2024). Visualisasi Dashboard Trend Kemiskinan Kota Depok Tahun 2021-2022 Dengan Menggunakan Microsoft Power Business Intelligence Dan Metode UAT (User Acceptance). Jurnal Teknik Dan Science, 3(3), 50–55. https://journal.admi.or.id/index.php/JTS/article/download/1897/1853/5587

Sari, A. N., & Darmanto, E. (2025). Implementasi Sistem Visualisasi Data Statistik pada Badan Pusat Statistik Kabupaten Pati untuk Peningkatan Pelayanan Masyarakat. Jurnal Pengabdian Masyarakat Bhinneka, 4(2), 1733–1741. https://doi.org/10.58266/jpmb.v4i2.690

Solimun, Fernandes, A. A. R., Nurjannah, Erwinda, E. G., Hardianti, R., & Arini, L. H. Y. (2023). Metodologi Penelitian: Variabel Mining berbasis Big Data dalam Pemodelan Sistem untuk Mengungkap Research Novelty. Universitas Brawijaya Press. https://doi.org/10.11594/ubpress9786232967052

Team, L., & Meta, A. @. (2024). The Llama 3 Tech report. ArXiv Preprint.

Wang, B., Shin, R., Liu, X., Polozov, O., & Richardson, M. (2020). RAT-SQL: Relation-aware schema encoding and linking for text-to-SQL parsers. Proceedings of the Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.677

Wong, A., Pham, L., Lee, Y., Chan, S., Sadaya, R., Khmelevsky, Y., Clement, M., Yau Cheng, F. W., Mahony, J., & Ferri, M. (2024). Translating Natural Language Queries to SQL Using the T5 Model. SysCon 2024 - 18th Annual IEEE International Systems Conference, Proceedings. https://doi.org/10.1109/SysCon61195.2024.10553509

Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., Zhang, Z., & Radev, D. R. (2018). Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. https://doi.org/10.18653/v1/d18-1425

Zhang, S., Dong, L., Li, X., Zhang, S., Sun, X., Wang, S., Li, J., Hu, R., Zhang, T., Wang, G., & Wu, F. (2026). Instruction Tuning for Large Language Models: A Survey. ACM Computing Surveys, 58(7). https://doi.org/10.1145/3777411

Zhong, V., Xiong, C., & Socher, R. (2017). Seq2sql: Generating structured queries from natural language using reinforcement learning. ArXiv Preprint ArXiv:1709.00103.