| Abstract [eng] |
This paper analyzes the possibilities and challenges of integrating Big Data and expert insights into artificial intelligence-based financial forecasting solutions. The relevance of the topic is driven by the rapid growth of data volumes, the increasing complexity of financial processes, and the expanding application of artificial intelligence in financial analytics. Although artificial intelligence models enable efficient processing of large amounts of data and identification of complex patterns, financial forecasting still heavily relies on expert knowledge and managerial decision-making. The aim of the study is to substantiate a model for integrating Big Data and expert insights into artificial intelligence-based financial forecasting solutions. The research revealed that traditional financial forecasting methods face challenges related to non-stationarity, regime shifts, nonlinear relationships, and the limited ability to integrate contextual information. In addition, issues related to data quality, forecast explainability, and the systematic integration of expert knowledge were identified. The theoretical part of the paper analyzes the principles of integrating Big Data, artificial intelligence, and expert knowledge, and develops an integrated financial forecasting model combining the AI 2.0 conceptual framework proposed by Zhuang et al. (2017) and the adaptive expert knowledge integration mechanism proposed by Park et al. (2023). In the model, artificial intelligence generates the baseline forecast, while the weight of expert knowledge depends on how representative the current situation is within historical data. A semi-structured expert interview method was selected for the empirical research, enabling an indepth analysis of finance professionals’ perspectives on the application of artificial intelligence in financial forecasting. The research results revealed that financial forecasts in organizations are primarily based on historical data and statistical models, while expert adjustments and managerial insights continue to play a significant role. It was found that artificial intelligence helps automate analysis and identify complex patterns; however, issues related to trust, forecast explainability, and data quality remain significant. The findings of the study suggest that effective financial forecasting in the future will be based on hybrid solutions integrating Big Data, expert knowledge, and explainable artificial intelligence models. |
