Fisheries have an important part in the Philippine economy, significantly contributing to food security and livelihoods. Predicting fisheries productivity accurately is critical for effective resource management and policy planning. This study looked at the volume of aquaculture Production in the Philippines, focusing on four species: carp, catfish, grouper, and milkfish. Over a three-year period, the investigation found considerable changes in production levels among different locations. Aquaculture production in Central Luzon and CALABARZON has increased consistently, showing successful operations and excellent market circumstances. However, certain locations saw production variations or reductions, emphasizing the need for targeted interventions. In addition, Machine Learning techniques were used to forecast future aquaculture productivity. In terms of accuracy and dependability, Linear Regression, Support Vector Machine, and Multi-Layer Perceptron surpassed k-Nearest Neighbors and Decision Tree. These algorithms can help policymakers and resource managers make sound judgments for long-term fisheries management. The findings highlight the significance of identifying successful strategies in regions with steady development and tackling issues in places with fluctuating output. Furthermore, incorporating machine learning algorithms can improve prediction models, allowing for more effective planning and decision-making. The study provides useful information for policymakers, researchers, and aquaculture stakeholders, encouraging sustainable development and growth in the Philippine fisheries industry.

The post A Machine Learning Prediction of the fisheries production in the Philippines using WEKA appeared first on International Network for Natural Sciences | Research Journal.