This paper discusses a crop suggestion system based on machine learning that assists farmers in selecting appropriate crops with the help of soil and weather information. The system considers factors such as soil nutrients (N, P, K), pH, temperature, humidity, and rainfall. We experimented with various models such as Random Forest, Support Vector Machine, Decision Tree, Naive Bayes, and K-Nearest Neighbors. Among them, Random Forest performed best, with achieving an accuracy of 95%. This paper provides an overview of the way the system is developed, the methodologies applied, information regarding the data, and how every model worked. As a whole, this system has the goal to increase farming efficiency and facilitate more accurate farming practices.
Crop Recommendation, Machine Learning, Random Forest, Agriculture, Predictive Analytics.