EV Sales Price Forecasting using Machine Learning

Sales forecasting is crucial in the retail industry for effective supply chain management and operations coordination between retailers and manufacturers. The surge in digital data has transformed traditional forecasting methods. Accurate sales predictions are vital for inventory management, marketing, customer service, and financial planning. This study conducts a predictive analysis of retail sales using the Citadel POS dataset from 2013 to 2018. Various machine learning techniques, including Linear Regression, Random Forest Regression, Gradient Boosting Regression, ARIMA, and LSTM, were applied. The Citadel POS dataset, a cloud-based system, helps retail stores manage transactions, inventories, customers, vendors, and sales data. The findings indicate that XGBoost outperformed both time series and other regression models, delivering superior sales forecasting performance.