Bangladeshi Agricultural Product Forecasting Approach Using Permutation Driven Machine Learning Algorithm

In Bangladesh, where a huge number of people live and many of them work directly in the agricultural sector. Here, farmers often make plans for the growing process in light of their prior knowledge. They end up growing undesirable crops as a result of their lack of precision farming skills. This research demonstrates the most effective method for crop prediction by utilizing the Catboost Regressor Algorithm, a machine learning algorithm. Gradient Boosting Regression, Kernel Ridge Regression, Elastic Net Regression, Bayesian Ridge Regression, Linear Regression, LGBM Regressor, XGBoost Regressor, Stochastic Gradient Descent Regression, and Support Vector Machine are also taken into consideration in this study for comparing the performance and error rate to get better output and prediction. We are considering about three major crops: Aus rice, Aman rice, and potato, to get these results. Additionally, we took into account seven environmental factors, including monthly averages for Bangladesh's highest and lowest temperatures, yearly rainfall, relative humidity, wind speed, cloud cover, and bright sunshine. In this research, we suggested the Catboost Regressor Algorithm for predicting agricultural crops.