CropTap: A Crop Recommender System Using Data-Driven Algorithm

This study developed and fully implemented CropTAP, a comprehensive and data-driven crop recommender system created to support more informed and practical agricultural decision-making in the municipalities of Tagoloan and Misamis Oriental. The system integrates soil characteristics, climate information, and historical crop performance, and it combines these datasets with machine learning algorithms to produce accurate and science-based crop recommendations, fertilizer suggestions, and planting insights that are easier for users to understand. Following the Agile SDLC approach, CropTAP was built using Python Flask for the recommendation engine, Laravel MySQL for backend operations and data management, and React for the user interface, which allows centralized data handling along with improved accessibility for agricultural officers. The results of the implementation show that the system effectively addressed long-standing issues involving fragmented records, inconsistent evaluation methods, and inefficient crop selection. It achieved this by providing tailored recommendations, clear dashboards, and practical guides that support better productivity and more efficient use of resources. Usability evaluations indicated generally positive acceptance from users, emphasizing the platform’s helpful functionality and strong alignment with real-world agricultural workflows. Overall, CropTAP modernizes traditional farming practices by delivering a reliable decision support tool that strengthens sustainable and evidence-based crop planning at the municipal level.