Sales Prediction in the Retail Industry Using Machine Learning: A Case Study of BigMart

This research paper presents a machine learning-based approach for sales prediction in the retail industry. The study was conducted using data collected from the BigMart retail chain. The research aimed to develop an accurate predictive model to forecast different products' sales in various BigMart stores. The study involved the implementation of several machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting, support vector machine, convolutional neural network, and long short-term memory. The models were trained and evaluated using a dataset comprising of over 8,000 entries of sales data from different BigMart stores. The results showed that the convolutional neural network and long short-term memory models outperformed the other algorithms in terms of accuracy, with an R-squared value of 0.68 and 0.69, respectively. The study also identified the most significant features affecting sales, including item weight, store location, and promotional activities. The findings of this research have significant implications for the retail industry, as accurate sales prediction can help businesses optimize their inventory management and marketing strategies. The study also highlights the potential of machine learning algorithms for sales forecasting in the retail sector. In conclusion, this research demonstrates the effectiveness of machine learning in predicting sales and highlights the importance of leveraging advanced analytical techniques for improving business performance in the retail industry.