<![CDATA[The agricultural sector plays a vital role in supporting national food security. However, farmers in many regions, including Pagar Alam—one of the main vegetable production centers in South Sumatra—continue to face significant challenges due to unpredictable price fluctuations. This instability makes it difficult for farmers to determine the optimal timing for planting, harvesting, and distributing their produce, which often results in economic losses and inefficiencies within the supply chain. Such conditions directly impact farmers’ welfare and the stability of market supply. This study aims to identify patterns of vegetable price fluctuations through data analysis and the development of a prediction model using a deep learning approach, specifically the Long Short-Term Memory (LSTM) algorithm. Evaluation of the model’s performance is conducted to determine the best predictive model based on accuracy and result stability. The findings are expected to provide data-driven policy recommendations to support Smart Agriculture initiatives and strengthen food security at both local and national levels.The research adopts the CRISP-DM framework, which includes the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The expected outcome of this study is the development of a predictive model that can offer valuable insights and recommendations to stakeholders, ultimately contributing to the improvement of farmers’ welfare.]]>
