Abstract
Accurate demand forecasting is essential for effective resource planning in organizations.In railway freight transportation, many factors can influence future volume and turnover, and traditional expert methods may no longer meet the requirements of the time.This article compares the accuracy of demand forecasts made using two different methods with the actual results.The theoretical research methods used are autoregressive integrated moving average (ARIMA) and expert methods.The results are compared using percentage mean absolute error (MAPE) and mean absolute error (MAE).The study found that time series analysis using ARIMA can significantly improve the accuracy of demand forecasts for railway freight transportation in Kazakhstan.The comparison of the results shows great promise for the use of time series analysis in improving demand forecasting quality.The implementation of time series analysis techniques can benefit the largest enterprises in Kazakhstan, including those in the transportation industry.By improving the efficiency of demand forecasting, organizations can better plan their operations, resulting in improved resource allocation and overall business success.Thus, this study suggests that time series analysis should be integrated into the practice of enterprises to improve their demand forecasting capabilities.