Abstract
In the current economic environment, sales revenue from retailers is a key performance indicator. Forecasting this indicator in modern conditions is one of the priority tasks, the solution of which will optimize the enterprise’s activities, competently plan inventory, sales costs, the number of transactions and terms of a commodity loan, as well as make other informed management decisions. Achieving this goal was carried out on the basis of the application of general scientific research methods in the framework of comparative, logical and statistical analysis, as well as through the modeling method. In addition, a theoretical analysis of the scientific literature and a descriptive method were used in the work, allowing to convey the features of forecasting and the multiple regression dependence method. The objective of the research paper is to develop a regression model for predicting the revenue of the trading company. As a result of the study, a multivariate regression model was proposed for predicting the volume of revenues of retailers. For this, the factors that have the greatest impact on the turnover of the trading organization under study were identified, and the effect of each of the factors on the change in sales revenue was identified. The developed regression model was tested for significance and adequacy by calculating the Fisher criterion, the determination coefficient, the Darbin - Watson index, and the calculation of the average approximation error, etc. The developed model is universal and can be used to predict the volume of revenue of enterprises operating in the retail sector, provided that an individual approach is taken to determine the factors of the external and internal environment that affect revenue.