Big mart sales forecasting using categorical boosting algorithm.

Generating forecast is without doubt one of the most important zones in any industry. Consumers-oriented merchandise encounter undetermined demands, insufficiency of historical information and brief life cycle, these elements challenges the forecasting techniques to provide precise result. In this paper, the instance of Big Mart has been discussed to predict the sales of different items and for understanding the effects of different factors which effect the item‟s sales. We performed the statistical analysis on the dataset using statistical tool "SPSS". Predictive model is built using CatBoost which is applied for sales prediction. The proposed model achieved high level of accuracy as compared to other machine learning algorithms. [ABSTRACT FROM AUTHOR]