Fintech Platform Energy Efficiency Optimization based on Green Computing Model
Year: 2025
Type: conference-paper
Abstract: In view of the limitations of traditional financial risk(FR) assessment methods in dealing with complex financial market environments, intelligent decision-making technology is introduced to improve the accuracy and real-time performance of financial risk assessment. This method combines big data, genetic algorithm (GA) and random forest (RF) optimization algorithm to more efficiently identify and quantify risk factors and provide more reliable decision support for financial institutions. First, big data(BD) technology is used to collect and integrate multi-dimensional market information, including historical transaction data of financial products, macroeconomic indicators, industry trends, etc., and data quality and availability are improved through data cleaning and preprocessing. Then, the random forest algorithm is used to train historical data to establish a FR assessment model, and the model is used to predict potential risks under different scenarios. Finally, the parameters of the assessment model are tuned through genetic algorithms to achieve the optimal decision result. Through the above steps, accurate prediction and management of FR can be achieved. Results: After abnormal event detection using intelligent decision-making technology, the impact of the event on January 2, 2010 is 4.94, and the corresponding abnormal event label is 0, indicating that not all events will cause significant market anomalies. The FR assessment and management method based on intelligent decision-making technology can fully utilize the advantages of BD and machine learning, optimize the traditional FR assessment system, and improve the risk identification and response capabilities of financial institutions in complex market environments.
Source: Procedia Computer Science
Authors: Qing Sha, Xiaohui Li, Ruifang Zhang
Institution: Weifang Engineering Vocational College
Language: English
Subfield: Accounting
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4411175580