<![CDATA[The production of Nile tilapia fingerlings plays a crucial role in ensuring the sustainability of freshwater aquaculture systems, particularly in Indonesia, where tilapia is a major source of protein and livelihood. Accurate prediction of fingerling output can significantly enhance resource efficiency, reduce operational costs, and support economic sustainability in hatchery operations. This study aims to predict fingerling production based on environmental factors and feed quantity, using data from the Center for Freshwater Aquaculture Development (BBPBAT) in Sukabumi, Indonesia. Multiple Linear Regression (MLR) was chosen for its interpretability and suitability for modeling linear relationships in moderate-sized datasets. MLR was applied to model the relationship between water temperature, pH, dissolved oxygen (DO), ammonia concentration, and feed quantity with fingerling production. The dataset consisted of 147 historical records, and model performance was evaluated using R² = 0.836, Mean Absolute Error (MAE) = 35,664, Mean Squared Error (MSE) = 2,014,982,858, and Root Mean Squared Error (RMSE) = 44,852. These results indicate a strong predictive capability. Compared to baseline mean-based predictions, the model significantly reduces forecast error and captures the production variability more effectively. Furthermore, the model was deployed via an interactive web-based tool using the Streamlit framework. This application allows hatchery staff to input current environmental conditions and feed data to generate real-time production forecasts, facilitating proactive management and better resource planning. Overall, this study demonstrates that MLR is a practical and effective tool for supporting decision-making in aquaculture production systems.]]>
