Construction of Budget Management System Based on Financial Risk Prevention

Abstract

Optimizing resource allocation to reduce potential hazards is a key component of budget management in financial risk prediction. For the purpose of reducing financial vulnerabilities, it comprises evaluating past data, projecting potential hazards, and strategically allocating cash. Safeguarding against possible losses, effective budget management guarantees that the best risk reduction techniques are in place. In this manuscript, Construction of Budget Management System Based on Financial Risk Prevention (CTN-BMS-FRP) is proposed. Initially input datas are gathered from S&P 500 Companies with Financial Information Dataset. To execute this, input data is pre-processed using Distributed Minimum Error Entropy Kalman Filter (DMEEKF)and it is used to restore the missing data, redundant data, and inconsistent data, from the dataset. Then the pre-processed datas are given to Child Drawing Development Optimization (CDDO)for selecting the features such as sector, prize, symbol, name, Week High, EBITDA, Price/Sales, Week Low, Price/Earnings, Market Cap, Dividend Yield, Earnings/Share, SEC Filings and Price/Book. Then the selected features are fed to Hierarchical Message-Passing Graph Neural Networks (HMGNN)for the prediction of financial risk. In general, HMGNN does not express adapting optimization strategies to determine optimal parameters to ensure accurate financial risk prediction. Hence, the Elk Herd Optimizer (EHO) to optimize HMGNN which accurately predicted the financial risk. Then the proposed CTN-BMS-FRP is implemented in Python and the performance metrics like Accuracy, Precision, Recall F1-Score, and ROC are analysed. Performance of the CTN-BMS-FRP method attains 18.75%, 26.89% and 32.57% higher accuracy; 16.87%, 24.57% and 32.94% higher Precision and 18.43%, 25.64% and 31.40% higher Recall when analysed through existing techniques like discussing the Construction of a Budget Management System Combining Multimedia Technology and Financial Risk Management(BMS-MT-FRM-SVM), Research on Deep Learning-Based Financial Risk Prediction (RSH-FRP-LSTM), Internet Financial Risk Management Under the development of Deep Learning(ITN-FRM-DL) methods respectively.