APPLICATION OF SURVIVAL ANALYSIS METHODS FOR ASSESSING THE EFFICIENCY OF FINANCIAL MONITORING AND CYBER SECURITY SYSTEMS

Abstract

The article provides a rationale for the practicality and features of using classic basic survival analysis methods for evaluating the effectiveness of financial monitoring and cyber security systems. The need to study this problem is due to the inability of modern systems of financial monitoring and cyber security at the state level to counteract various types of threats, especially in martial law conditions and the decline of economic growth. It is proposed to determine the effectiveness level of financial monitoring and cyber security systems using an integral indicator, the calculation of which is based on two composite indicators – the critical index of the cyber security system development level and the system development level essential index, which is countering the criminal proceeds legalization. Five qualitative levels of financial monitoring and cyber security systems effectiveness are distinguished. The survival function is interpreted in terms of the subject area. In terms of survival analysis, a level's change of the financial monitoring and cyber security systems integral indicator or the impossibility of its calculation due to the unavailability of statistical data is chosen as a critical event considered as the "death" of the system. The expediency of using three primary methods – the method of life table analysis, the Kaplan–Meier method and Cox regression – for evaluating the effectiveness of financial monitoring and cyber security systems is substantiated. The main arguments in favour of practicality were the possibility of using censored data, which is especially relevant in the absence of the necessary statistical information; the ability of survival analysis methods not only to study the effectiveness of financial monitoring and cyber security systems in time's periods but also to assess the factors that influence it; availability of separate survival analysis modules in data analysis computer programs.