<![CDATA[Rice is an important commodity in Indonesia and the main source of food for most of the population. However, various challenges such as production distribution inequality, supply chain inefficiency, and price fluctuations still pose a threat to national food security. This research aims to develop a Big Data Management Model for rice commodity, which integrates descriptive, diagnostic, predictive and prescriptive analysis to improve the effectiveness of national food policy. This research uses data from the Central Bureau of Statistics (BPS) and the Ministry of Agriculture, covering rice production from 1993 to 2018. Analysis was conducted with K-Means clustering for descriptive analysis, Decision Tree and Random Forest for diagnostic analysis, Linear Regression and Recurrent Neural Network (RNN) for predictive analysis, and the application of Blockchain Logistics 4.0 for prescriptive recommendations. This approach enables a comprehensive assessment of production trends, factors affecting yields, and data-driven policy strategies. The results show that rice production is highly concentrated in Java, which accounts for 44.47% of total national production, while eastern regions such as Papua and Maluku have low production levels due to limited land and agricultural infrastructure. The main factors affecting rice productivity are land availability, irrigation systems, and labor access. The prediction model shows that several provinces, including DKI Jakarta, Kalimantan, and Riau, are expected to experience a decline in production in the next five years if there is no appropriate policy intervention. In addition, artificial intelligence-based decision support systems and the application of blockchain in the rice supply chain can be a solution to improve logistics efficiency, stabilize prices, and reduce distribution bottlenecks. These findings confirm that Big Data and AI technologies have the potential to improve national food security through improved prediction accuracy and optimization of supply chain networks. However, successful implementation is highly dependent on strengthening digital infrastructure, standardizing agricultural data, and increasing technology adoption among farmers and policy makers. This research contributes to the development of data-driven food policy, by providing a framework that can be adapted for long-term food security planning in developing countries. Future studies are recommended to explore models that are more adaptive to environmental changes, climate variability, and global market dynamics that affect rice production and distribution.]]>
