An Adaptive Machine Learning model for Walmart sales prediction

Presently, with the quantity of data developing dramatically, the judicious utilization of large data has become the focal point of ventures to serve the future and settle on better choices. Utilizing Machine Leaning (ML) models to anticipate the sales of items and wares has become a rising area for analysts in present time. This article presents the XGBoost sales expectation model which consolidates XGBoost algorithm and careful element designing handling for anticipating Walmart's sales issue. The proposed technique can adequately mine credits of various measurements to make forecasts well. This article assesses the XGBoost sales estimation model on the sales data of Walmart stores datasets given by the Kaggle. Empirical results show our strategy accomplishes better execution over the other ML techniques.