Prediction of Rice Harvesting During the Rainy Season in Kabupaten Lamongan Using Stochastic Frontier Analysis

The agricultural sector plays a critical role in ensuring national food security, yet it faces challenges in achieving technical efficiency due to limited land and input resources. This study aims to model and predict the technical efficiency of rice production in Lamongan Regency during the rainy season using a data science-driven Stochastic Frontier Analysis (SFA) approach. The dataset includes key inputs such as land area, labor, fertilizer, and environmental variables. The methodology involved data preprocessing, feature selection based on Pearson correlation and VIF thresholds, and model validation using metrics like R-squared, MAPE, and log-likelihood. The SFA model demonstrated high predictive capability, with R² values exceeding 0.91 in cross-validation and MAPE under 15%. The low gamma value (? = 0.0100) indicates minimal yet consistent inefficiency. The results suggest that integrating SFA with data science techniques provides an effective framework for identifying inefficiencies and can serve as a decision-support system for evidence-based agricultural policy.