Deep learning models for the forecasting and regulation of global financial growth

Abstract

The worldwide economic and financial systems' development, growth, and expansion arecalled global financial growth. It refers to global, national, and regional economic growth, trade, and investment. One can assess the global economy by tracking Gross Domestic Product (GDP), international trade, employment, and other financial variables. In this research, investigate the deep learning (DL) models for forecasting and regulating global financial growth. Governments and economists consider a global financial growth as a sign of prosperity, stability, and rising living standards. Accurately predicting and controlling the expansion of the global financial system requires an awareness of these interconnections and their possible effects. Bank runs and stock market crashes are the two examples of the kinds of crises that pressure the international financial system. The capacity to anticipate and manage these crises is critical for sustained global financial expansion. In this study, we suggested a Distributed Sailfish Optimized Hybrid Improved Artificial Neural Network (DSO-HIANN), which has shown promise in tackling issues in global financial growth. The research collected financial data. Here the logistics data is collected and preprocessed using z-score normalization. We employed Principal Component Analysis (PCA) method to extract data features in financial data. Governments, financial institutions, investors, and a politician requires an accurate financial growth forecasts. Our suggested approach, DSO-HIANN, outperformed than other existing methods in the context of f1-score (98.70), recall (98.80%), precision (98.02%), and accuracy (97.90%).Financial analysis that employs a DL algorithms has the potential to enhance accuracy and sophisticated when applied to the challenge of anticipating and managing global financial growth.