Crop yield prediction and recommendation systems are important for farmers to decide the correct crop for their land. This paper proposed a yield prediction and crop recommendation system that leverages deep learning and machine learning methods. The system aims to assist farmers in the decision of crop selection, planting, and harvesting. The system takes into account various factors, such as conditions of weather, soil quality, and historical yield data, to predict the yield of a particular crop. The proposed system was evaluated on a dataset of crop yield data from several regions of Maharashtra state, and the results show that it can accurately predict crop yields and provide useful recommendations for farmers. The dataset is trained using a combined machine learning and deep learning methods, in which initially it predicts the crop for the current season. Then the predicted crop is used as input to a deep learning model, which recommends its respective yield for that season. The proposed system has been tested on historical crop yield data and weather data for two seasons, and the results show its own accuracy and efficiency for traditional crop management methods. The future scope is to assist farmers by recommending fertilizer and irrigation requirements and pest control measures.