Contrasting Univariate and Multivariate Time Series Forecasting Methods for Sales: A Comparative Analysis

In commodity-based industries, accurate sales forecast is very important for effective inventory management and decision-making. Univariate multivariate time series forecasting methods have been widely used to predict commodity sales. The purpose of this study make a comprehensive comparative analysis these two under the background forecast. Firstly, concept prediction its significance in field are introduced. It emphasizes challenges related forecast, including demand fluctuation, seasonality external factors affecting model. univariate series, such as ARIMA, discussed detail, focusing on their ability capture correlation single variable. contrast, method considers relationship between multiple variables. Vector autoregressive extension ARIMA. These techniques combine interaction various factors, influences, improve accuracy prediction. order analysis, data set historical specific commodities used. Both models suitable future sales, performance indicators evaluated by MASE. results show that although easier implement explain, they often fail complex interdependence different affect On other hand, model shows excellent integrating variables dynamic relationships. However, need more additional modeling techniques. Finally, research gives practical suggestions choosing an appropriate based characteristics business environment. importance considering interpretability application.