Response of Hydro-Meteorological Hazards to Environmental Degradation in Kohima District of Nagaland, North East India

Abstract

Big Marts, which are distribution centers for supermarket chains, now keep tabs on sales volume and revenue numbers for each product to anticipate domestic consumption and adjust inventory control. Examining the data warehouse's server database often reveals inconsistencies and overarching patterns. Companies like Big Mart can use the data with a variety of machine learning techniques to predict future product sales. Many different machine learning algorithms, including Linear Regression, Ridge Regression, Lasso Regression, Decision Tree Regression, Random Forest Regression, Support Vector Regressor, Adaboost Regressor, and XGBoost Regression, have been employed in this project to forecast Big Mart product sales. We find that XGBoost Regression performs the best in predicting sales volume among the listed algorithms. To this end, we have developed a model with XGBoost Regression and optimized it for maximum precision. This model is available through a flask application; users simply log in, specify the product's parameters, and receive sales forecasts.