This paper presents a smart crop prediction system that integrates IoT and machine learning to help farmers make informed decisions about which crops to grow. The system collects real-time data on temperature, moisture, and rainfall, and uses machine learning algorithms to predict the most suitable crop for a given area. The system also recommends the appropriate fertilizer for the crop based on soil conditions and other factors. The proposed system uses a combination of supervised and unsupervised machine learning algorithms, including decision trees, K-NN, and support vector machines, to achieve high accuracy in crop prediction. The system is designed to provide farmers with accurate and timely information to optimize crop yields and improve agricultural productivity. The system is implemented using IoT devices, such as the DHT22 sensor, which measures temperature and humidity, and an ESP8266 Wi-Fi module for data transmission. The system also uses a Flask-based web interface for user interaction and data visualization. The results show that the proposed system achieves high accuracy in predicting suitable crops and recommends the appropriate fertilizer for the crop. The system is expected to improve agricultural productivity and sustainability by providing farmers with data-driven insights and decision support tools. The study highlights the potential of IoT and machine learning in transforming the agricultural sector by enabling smart farming practices that enhance crop yields and reduce environmental impact.This paper presents a smart crop prediction system that integrates IoT and machine learning to help farmers make informed decisions about which crops to grow. The system collects real-time data on temperature, moisture, and rainfall, and uses machine learning algorithms to predict the most suitable crop for a given area. The system also recommends the appropriate fertilizer for the crop based on soil conditions and other factors. The proposed system uses a combination of supervised and unsupervised machine learning algorithms, including decision trees, K-NN, and support vector machines, to achieve high accuracy in crop prediction. The system is designed to provide farmers with accurate and timely information to optimize crop yields and improve agricultural productivity. The system is implemented using IoT devices, such as the DHT22 sensor, which measures temperature and humidity, and an ESP8266 Wi-Fi module for data transmission. The system also uses a Flask-based web interface for user interaction and data visualization. The results show that the proposed system achieves high accuracy in predicting suitable crops and recommends the appropriate fertilizer for the crop. The system is expected to improve agricultural productivity and sustainability by providing farmers with data-driven insights and decision support tools. The study highlights the potential of IoT and machine learning in transforming the agricultural sector by enabling smart farming practices that enhance crop yields and reduce environmental impact.