Over 50% of India's population depends on agriculture for existence, making it the foundation of the country's economy. Variations in weather, climate, and other environmental factors are now a significant threat to the continued success of agriculture. The decision support tool for Crop Yield Prediction (CYP), which includes assisting decisions on which crops to plant and what to do during the growth season of the crops, is where machine learning (ML) plays a vital role. The goal of the current study is to conduct a systematic review that extracts and synthesises the CYP traits. In addition, a number of methodologies have been created to analyse agricultural yield prediction utilising artificial intelligence techniques. Reduction in relative error and lower crop yield prediction accuracy are the Neural Network's main drawbacks. Similar to this, supervised learning algorithms failed to recognise the nonlinear relationship between input and output variables, which presented a challenge during the selection, grading, or sorting of fruits. To establish an accurate and effective model for crop classification, including crop yield estimation based on weather, crop disease, classification of crops based on the growing phase, etc., numerous investigations were advised. This study examines various machine learning (ML) approaches applied to agricultural yield estimation and provides a thorough review of the strategies' accuracy.