MACHINE LEARNING ALGORITHMS FOR FORECASTING DEMAND FOR GOODS AND SERVICE
Anton V. Bondar
Student, Department of Information Systems and Computer Modeling,
Volgograd State University
This email address is being protected from spambots. You need JavaScript enabled to view it.
Prosp. Universitetsky, 100, 400062 Volgograd, Russian Federation
Alexander S. Astakhov
Senior Lecturer, Department of Information Systems and Computer Modeling,
Volgograd State University
This email address is being protected from spambots. You need JavaScript enabled to view it.
Prosp. Universitetsky, 100, 400062 Volgograd, Russian Federation
Abstract. The article discusses the main algorithms for forecasting time series using machine learning methods, in particular, forecasting sales of goods based on various indicators. The forecasting task requires the staff to have excellent knowledge of mathematical and statistical tools, as well as the ability to analyze large amounts of data. Automating this task will allow you to shift most of the work of employees to software. This will help to increase the volume of information processed, reduce logistics and storage costs, and minimize the risks of loss of profit because of a zero-stock balance. The article analyzes the criteria that affect the demand for goods; classical algorithms and neural networks for forecasting time series are considered. The work also highlights the process of designing, developing, and testing software.
Key words: time series, time series forecasting, linear regression, ARIMA, XGBoost, neural networks, recurrent neural networks, LSTM, web technologies.
This work is licensed under a Creative Commons Attribution 4.0 International License. 1_Bondar, Astakhov.pdfURL: https://ti.jvolsu.com/index.php/en/component/attachments/download/934 | 1 Download |  |