The finest utility sector is agriculture, especially in emerging nations like India. Utilizing historical data in agriculture can change the context of decision-making and increase farmer productivity. Approximately a part of India's population is employed in agriculture, however this sector contributes just 14% of the country's GDP. This can be explained in part by farmers not making sufficient decisions on yield forecast. By examining numerous climatic elements, such as rainfall, and land characteristics, such as soil type and ground water salinity, as well as historical records of crops cultivated, the suggested machine learning technique tries to estimate the agricultural yield for a certain location. Finally, we anticipate that our proposed Machine Learning Gradient Boosting Neural Network Regression (Grow Net) model was predicting the accurate yield. Finally our system is expected to predict the yield based on dataset we have taken. We were compared our proposed algorithm with various Machine Learning algorithms such as Random Forest, Support Vector Machine, KNN, Multi-layer Perceptron Regressor, Gradient Boosting Regressor and results shows that proposed was given best RMSE ,MAE and R2 value.