Forecasting Time Series in the Banking Sector Using a Machine Learning Pipeline

This article is devoted to the applications of machine learning methods for solving optimization problems in the banking sector. The literature analysis on the application of methods for forecasting time series in economics and finance is presented. A universal scenario for forecasting a large number of non-stationary time series in automatic mode has been developed. The use of the developed scenario for solving specific banking tasks to improve business efficiency, including optimizing demand for ATMs, forecasting the load on the call center and cash center, is considered. This article will be helpful for specialists dealing with the problem of forecasting economic time series and students and researchers due to a large number of links to systematic literature reviews on this topic.