MODELLING OF SUSTAINABLE FINTECH FOR FORECASTING FINANCIAL CRISES USING TWO-TIER OPTIMIZATION ALGORITHM WITH DEEP LEARNING MODEL

Financial technology (FinTech) is one of the research topics at present, besides, being an area of main investment for most economic institutions. The FinTech released numerous novel tactical solutions for many financial issues. The essential approach of FinTech is financial crisis prediction (FCP), which states the financial position of an organization. To arrange for disaster, it is becoming gradually significant for business managers to utilize present economic data for temporary financial predicting. Investors and managers are progressively concerned with directly and accurately predicting firm financial crises utilizing a restricted quantity of financial data. Preceding research mainly concentrated on deep learning (DL), machine learning (ML), and statistical techniques to predict the economic well-being of a company. In this article, we focus on the Modelling of Sustainable FinTech for Forecasting Financial Crises Using a Two-tier Optimization Algorithm with Deep Learning Model (MSFFFC-TTODL). The main aim of the MSFFFC-TTODL method is to effectively predict and mitigate the risks of financial crises within sustainable FinTech. Initially, the MSFFFC-TTODL technique applies a min-max normalization-based data pre-processing model to ensure consistent scaling of financial indicators. For feature selection, the honey badger algorithm (HBA) is used to identify the most relevant features for crisis prediction by reducing dimensionality. For the classification of financial crises, the sparse graph auto-encoder (SGAE) technique is employed. At last, the Hyper parameter range of the SGAE model can be applied by the design of the simplified white shark optimizer (SWSO) algorithm. A wide range of simulation analyses are implemented to guarantee the enhanced performance of the MSFFFC-TTODL system. The comparative result analysis stated that the betterment of the MSFFFC-TTODL algorithm on recent approaches in terms of different evaluation measures.

Hali tarjima qilinmagan