— Cash management optimization is one of the most essential tasks for any bank, because it helps save a significant amount of money by reducing the cost of ATMs funding and encashment. This paper focuses on forecasting customer cash demand, which is one of the key components of the optimization system. Furthermore, for the first time, our research touches on the problem of nonstationarity, which is typical for real-world ATM data, and proposes a data preprocessing pipeline to tackle it. We proposed new forecasting methods in the paradigms of local and global models, proved their superiority over classical approaches to forecasting time series and approaches used specifically for the cash demand forecasting problem.

Open text data, such as financial news, are thought to be able to affect or to describe stock market behavior, however, there are no widely accepted algorithms for extracting the relationship between stock quotes time series and fast-growing textual representation of economic information. The field remains challenging and understudied. In particular, topic modeling as a powerful tool for interpretable dimensionality reduction has been hardly ever used for such tasks. We present a topic modeling framework for assessing the relationship between financial news stream and stock prices in order to maximize trader’s gain. To do so, we use a dataset of economic news sections of three Russian national media sources (Kommersant, Vedomosti, and RIA Novosti) containing 197,678 economic articles. They are used to predict 39 time series of the most liquid Russian stocks collected over eight years, from 2013 to 2021. Our approach shows the ability to detect significant return-predictive signals and outperforms 26 existing models in terms of Sharpe ratio and annual return of simple long strategy. In particular, it shows a significant Granger causal relationship for more than 70% of portfolio stocks. Furthermore, the approach produces highly interpretable results, requires no domain-specific dictionaries, and, unlike most existing industrial solutions, can be calibrated for individual time series. This makes it directly usable for trading strategies and analytical tasks. Finally, since topic modeling shows its efficiency for most European languages, our approach is expected to be transferrable to European stock markets as well.