Explainable Machine Learning for Food Vulnerability Prediction in Indonesia
DOI:
https://doi.org/10.30871/jaic.v10i2.12638Keywords:
Food Vulnerability, Indonesia, Machine Learning, Random Forest, SHAPAbstract
Food insecurity remains a strategic multidimensional issue in Indonesia, requiring precise and transparent predictive frameworks for evidence-based policy. This study develops an explainable machine learning framework to predict interregional food vulnerability using data from the Food Security Index (IKP) and the Food Security and Vulnerability Atlas (FSVA) for the 2022–2024 period, encompassing 514 districts. To ensure model optimality and respond to the need for robust comparison, seven algorithms were evaluated, including ensemble-boosting and neural network techniques. The Gradient Boosting model demonstrated the most superior and stable performance, achieving an R² of 0.9770, MAE of 1.5621, and RMSE of 2.1534, outperforming Random Forest and XGBoost. Model reliability was further validated through K-fold Cross-Validation (CV R² = 0.966), confirming high generalizability and the absence of significant overfitting. Model interpretability was achieved through SHapley Additive exPlanations (SHAP), identifying the Net Consumption to Production Ratio (NCPR) as the dominant global driver, followed by clean water access and poverty levels. Localized analysis reveals that in high-risk regions like Papua, infrastructure gaps and food supply dependence are the primary catalysts for vulnerability. This study provides a high-precision, validated predictive model that enables policymakers to implement targeted mitigation strategies according to regional disparities, supporting national goals for sustainable food sovereignty.
Downloads
References
[1] N. Anwar, “Indonesia’s Regional Food Security in Light Of The Impending Global Food Crisis,” vol. 21, no. 2, pp. 101–110, 2022.
[2] F. Agus, E. Surmaini, and H. Lina, “Strategies for Indonesia’s Agricultural Climate Change Adaptation and Mitigation,” Jurnal Sumberdaya Lahan, vol. 16, no. 2, p. 67, Jan. 2023, doi: 10.21082/jsdl.v16n2.2022.67-81.
[3] L. Moh Arsal Fadila and N. Arsyta Putri, “Analisis Perkembangan Ketahanan Pangan di Indonesia : Pendekatan Menggunakan Big Data dan Data Mining,” in Seminar Nasional Official Statistics, Jakarta: Badan Pusat Statistik, 2023.
[4] I. A. Juliannisa, H. Rahma, S. Mulatsih, and A. Fauzi, “Regional Vulnerability to Food Insecurity: The Case of Indonesia,” Sustainability (Switzerland), vol. 17, no. 11, Jun. 2025, doi: 10.3390/su17114800.
[5] W. W. Prastanika and A. W. Wijayanto, “Analisis Hard dan Soft Clustering Untuk Pengelompokan Indikator Ketahanan Pangan Indonesia 2021,” Jurnal Sistem dan Teknologi Informasi (JustIN), vol. 11, no. 4, p. 596, Oct. 2023, doi: 10.26418/justin.v11i4.68400.
[6] B. Susantyo et al., “Social Cash Assistance for Food Security During a Disaster: Lesson Learned from Indonesia,” in IOP Conference Series: Earth and Environmental Science, Institute of Physics, 2023. doi: 10.1088/1755-1315/1180/1/012047.
[7] Anak Agung Ngurah Mayun Wirajaya, Made Sri Yuliartini, and Anak Agung Made Semariyani, “PKM for Improving Food Security at PKK Bongan Village Tabanan District, Tabanan District-Bali Province,” Asian Journal of Community Services, vol. 2, no. 11, pp. 983–992, Nov. 2023, doi: 10.55927/ajcs.v2i11.7020.
[8] S. Saa, “Evaluation of the Policy Program for Strengthening Local Food Commodities for Sustainable Food Security in Papua,” JPPI (Jurnal Penelitian Pendidikan Indonesia), vol. 10, no. 2, p. 478, Jun. 2024, doi: 10.29210/020244167.
[9] R. Qasrawi et al., “Machine Learning Approach for Predicting the Impact of Food Insecurity on Nutrient Consumption and Malnutrition in Children Aged 6 Months to 5 Years,” Children, vol. 11, no. 7, Jul. 2024, doi: 10.3390/children11070810.
[10] A. H. Villacis, S. Badruddoza, A. K. Mishra, and J. Mayorga, “The Role of Recall Periods When Predicting Food Insecurity: 1 A Machine Learning Application in Nigeria 2 3,” pp. 1–29.
[11] M. Al Fachrozi and K. D. Tania, “Comparison of Naïve Bayes, SVM, K-NN, Decision Tree, and Random Forest in Sentiment Analysis Based on SeaBank Application Aspects,” JURTEKSI (jurnal Teknologi dan Sistem Informasi), vol. 12, no. 1, pp. 69–80, Dec. 2025, doi: 10.33330/jurteksi.v12i1.4189.
[12] D. N. Fahria, K. D. Tania, and R. D. Kurnia, “Analisis Komparatif Algoritma Random Forest, XGBoost, dan CatBoost untuk Klasifikasi Tingkat Stres Pengguna Media Sosial,” Rabit : Jurnal Teknologi dan Sistem Informasi Univrab, vol. 11, no. 1, pp. 1843–1853, Jan. 2026, doi: 10.36341/rabit.v11i1.7449.
[13] Z. B. P. Pratama and Y. P. Astuti, “Perbandingan Metode Machine Learning (Linear Regression, Random Forest, dan XGBoost) dalam Memprediksi Kemiskinan di Jawa Tengah Tahun 2024,” Sistemasi: Jurnal Sistem Informasi, vol. 14, no. 5, p. 2492, Jul. 2025, [Online]. Available: http://sistemasi.ftik.unisi.ac.id
[14] F. M. Saragih and W. C. Wibowo, “Analysis of Food Security Index Predictions in Indonesia Using Machine Learning Approach,” Agro Bali, vol. 8, no. 2, pp. 377–393, 2025, doi: 10.37637/ab.v8i2.2302.
[15] D. N. Handayani and S. Qutub, “Penerapan Random Forest Untuk Prediksi Dan Analisis Kemiskinan,” RIGGS: Journal of Artificial Intelligence and Digital Business, vol. 4, no. 2, pp. 405–412, May 2025, doi: 10.31004/riggs.v4i2.512.
[16] N. N. Sholihah and A. Hermawan, “Implementation of Random Forest and SMOTE Methods for Economic Status Classification in Cirebon City,” Jurnal Teknik Informatika (Jutif), vol. 4, no. 6, pp. 1387–1397, Dec. 2023, doi: 10.52436/1.jutif.2023.4.6.1135.
[17] X. Han, T. Yuan, D. Wang, Z. Zhao, and B. Gong, “How to Understand High Global Food Price? Using SHAP to Interpret Machine Learning Algorithm,” PLoS One, vol. 18, no. 8 August, Aug. 2023, doi: 10.1371/journal.pone.0290120.
[18] Y. Wang, S. Schaub, D. Wuepper, and R. Finger, “Interpreting the Global Food Security Index: A Machine Learning Approach with SHAP Values,” Food Policy, vol. 120, p. 102482, Oct. 2023, doi: 10.1016/j.foodpol.2023.102482.
[19] M. Usman and A. Hidayat, “Algoritma Shapley Additive Explanations untuk Analisis Kejadian Rawan Pangan Rumah Tangga di Kalimantan Barat,” in Prosiding Seminar Hasil Penelitian dan Pengabdian Kepada Masyarakat, 2024.
[20] Rais, A. M. Soleh, and B. Susetyo, “Rotation Double Random Forest Algorithm to Predict The Food Insecurity Status of Households,” Jurnal RESTI, vol. 8, no. 1, pp. 33–41, Feb. 2024, doi: 10.29207/resti.v8i1.5540.
[21] Z. Fu et al., “Global Critical Soil Moisture Thresholds of Plant Water Stress,” Nat. Commun., vol. 15, no. 1, Dec. 2024, doi: 10.1038/s41467-024-49244-7.
[22] D. Zhou, J. Zhang, F. Zou, Z. Li, and H. Huan, “Optimization and Driving Mechanisms of Agricultural Resilience Measurement Based on XGBoost-SHAP Model: Evidence from China,” Front. Sustain. Food Syst., vol. 10, 2026, doi: 10.3389/fsufs.2026.1767684.
[23] S. R. Machieu, F. H. Y. Akib, and M. Mukhtar, “Analisis Kinerja Pemerintah atas Indeks Ketahanan Pangan Berdasarkan Kebijakan Fiskal dalam Ekonomi Pertanian pada Kabupaten/Kota di Kawasan Teluk Tomini,” Mimbar Agribisnis: Jurnal Pemikiran Masyarakat Ilmiah Berwawasan Agribisnis, vol. 12, no. 1, pp. 901–916, Jan. 2026.
[24] M. Adith, P. Katti, and D. Gupta, “A Strategic Analysis of Food Demand Using Machine Learning and Explainable AI,” in 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), IEEE, Apr. 2024, pp. 1–7. doi: 10.1109/I2CT61223.2024.10543689.
[25] P. A. Dimara and A. Auri, “Effect of Landform on the Distribution of Metroxylon sagu Habitat in Yapen Islands, Papua Province, Indonesia,” Jurnal Sylva Lestari, vol. 11, no. 1, pp. 79–97, Jan. 2023, doi: 10.23960/jsl.v11i1.633.
[26] N. Putri, A. A. Rachmayanti, and Y. P. Pramesti, “A Narrative Review: How to Optimize Program Keluarga Harapan in Addressing Nutritional Issues in Indonesia,” Salus Cultura: Jurnal Pembangunan Manusia dan Kebudayaan, vol. 4, no. 1, Jun. 2024, doi: 10.55480/saluscultura.v4i1.203.
[27] N. Cahyadi, R. Hanna, B. A. Olken, R. A. Prima, E. Satriawan, and E. Syamsulhakim, “Cumulative Impacts of Conditional Cash Transfer Programs: Experimental Evidence from Indonesia,” Am. Econ. J. Econ. Policy, vol. 12, no. 4, pp. 88–110, 2020, doi: 10.1257/pol.20190245.
[28] L. A. D. Ambarini, E. Frimawaty, and H. Herdiansyah, “Sustainable Management Strategies for Degraded Subak Rice Fields in South Denpasar, Bali,” Journal of Degraded and Mining Lands Management, vol. 13, no. 1, pp. 9199–9209, Jan. 2026, doi: 10.15243/jdmlm.2026.131.9199.
[29] N. W. P. Rusadi, I. G. Pitana, I. N. Sunarta, and I. N. S. Arida, “Development of Subak Lestari as a Sustainable Tourism Attraction in Denpasar City,” International Journal of Green Tourism Research and Applications, vol. 5, no. 2, pp. 114–128, Dec. 2023, doi: 10.31940/ijogtra.v5i2.114-128.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Marizka Riffiy Alfiyah, Fadiah Tussholiha, Nyimas Princessa Syapeni, Halona Daffakhansa Nabila, Ken Ditha Tania, Allsela Meiriza, Ahmad Rifai
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
