Economic systems operating under high uncertainty, particularly during wartime disruptions, require robust analytical and forecasting instruments to support objective and timely resource allocation decisions within crisis management. This study aims to improve the methodological approaches and analytical toolkit for forecasting and analysing the dynamics of economic development in order to substantiate resource allocation decisions at the level of an economic entity. The research is based on statistical data describing the performance of the analysed object over the pre-war and wartime period of 2006–2024. The methodological framework integrates principles of systems analysis, multivariate statistical techniques for data collection, structuring and processing, expert judgement, and heuristic reasoning to establish the system–logical relationships among the parameters used to construct the initial analytical database. Expert assessments and a set of coefficients (indicators) were developed to operationalise the taxonomic method, enabling the calculation of an integral criterion of economic development. Furthermore, a correlation–regression forecasting model was developed to quantify the strength of relationships among factors and to rank their significance in explaining variations in the economic development index. The findings demonstrate that the proposed modelling framework provides a consistent analytical basis for forecasting economic development dynamics as a function of internal changes in liquidity, solvency, profitability and financial stability indicators, thereby increasing the objectivity and resilience of managerial decisions on resource allocation. The study contributes to the literature by advancing heuristic and data-driven approaches to modelling economic development dynamics under crisis conditions, with particular emphasis on the integration of taxonomic analysis, expert-based indicator construction, and econometric forecasting. The proposed tools may be applied in the practice of crisis management to enhance decision-making in resource distribution and may serve as a foundation for further research incorporating stochastic components and scenario-based analysis.
Kwilinski et al. (Mon,) studied this question.