FORECASTING MODELS AND TIME SERIES ANALYSIS ALGORITHMS FOR BUSINESS PROCESS MANAGEMENT IN RETAIL SALES

Shibichenko Mikhail Ivanovich, Pavlov Valery Anatolyevich

Retail enterprises strive to use their resources most effectively and make informed strategic decisions in order to survive and increase their income in today's conditions of ever-increasing competition. However, as is known, forecasts are characterized by a certain degree of uncertainty, therefore, in order to obtain the most reliable and accurate data, retailers need to use methods that will minimize this uncertainty. To date, a wide range of approaches has been developed for forecasting the activities of retailers, both using traditional mathematical and static apparatus, and based on modern technologies and capabilities of intelligent data processing. In this regard, the article presents the results of a comparative analysis of forecasting models and time series analysis algorithms for managing business processes in the field of retail sales. In addition, data obtained during a comparison of the accuracy of forecasting some models using the metric of the average absolute percentage error are presented.

Keywords:retail sales, forecasting, model, data, machine learning, statistics, error.