<![CDATA[The advancement of information technology and artificial intelligence has created new opportunities to enhance efficiency and accuracy in the agricultural sector. One major challenge faced by farmers is determining the most suitable crop type based on environmental factors such as temperature, humidity, soil pH, rainfall, and light intensity. This study aims to develop a web-based crop prediction system using Decision Tree and Random Forest algorithms to support farmers in making data-driven decisions. The research methodology includes environmental data collection, data preprocessing, model training using both algorithms, performance evaluation based on accuracy metrics, and deployment of the best-performing model into a web application. The system allows users to input environmental parameters and obtain real-time crop predictions instantly. The novelty of this study lies in integrating both Decision Tree and Random Forest algorithms into a single interactive web platform, providing not only accurate predictions but also easy accessibility for users. Experimental results indicate that the Random Forest algorithm achieves higher accuracy than the DeciSsion Tree in crop classification. Therefore, this system can serve as an effective tool for farmers and researchers to identify suitable crops under specific environmental conditions..]]>
Copyrights © 2025
