Application of AdaBound-Optimized XGBoost-LSTM Model for Consumer Credit Assessment in Banking Industries

Application of AdaBound-Optimized XGBoost-LSTM Model for Consumer Credit Assessment in Banking Industries

Lijuan Fan, Changlin Wang, Zhonghua Lu
Copyright: © 2024 |Pages: 24
DOI: 10.4018/JOEUC.343256
Article PDF Download
Open access articles are freely available for download

Abstract

Consumer credit assessment has always been a crucial concern in the financial industry. It involves evaluating an individual's credit history and their ability to repay loans, playing a pivotal role in the risk management and lending decisions made by credit institutions. In the present landscape, traditional credit assessment methods confront various shortcomings. Firstly, they typically only consider static features and are unable to capture the dynamic changes in an individual's credit profile over time. Secondly, traditional methods struggle with processing complex time series data, failing to fully exploit the importance of time-related information. To address these challenges, we propose an innovative solution – the XGBoost-LSTM model optimized with the AdaBound algorithm. This hybrid model combines two powerful machine learning techniques, XGBoost and LSTM, to leverage both static and dynamic features effectively.
Article Preview
Top

Research on Time Series Analysis in Credit Evaluation

Research on time series analysis in credit evaluation is committed to making full use of the time information in personal credit history data to more accurately understand credit trends, predict future credit performance and identify credit default risks (Talaat et al., 2023; Yuan et al., 2022). Researchers use time series analysis methods, such as trend modeling and feature extraction, to capture time series characteristics in individual credit histories. This analysis helps financial institutions better understand customers' credit behavior, develop more precise credit strategies, and improve the efficiency of risk management. At the same time, time series analysis also provides an important data mining tool for the field of credit evaluation, which is expected to improve the performance and prediction capabilities of credit evaluation models (Zhao & Chen, 2022; Zeng & Zhong, 2022).

Machine Learning and Integrated Learning Methods Applied to Credit Assessment

Machine learning and comprehensive learning methods applied to credit assessment represent a multi-domain technology collection, and their application in the financial field provides financial institutions with powerful and diverse credit assessment tools. Deep learning methods, such as neural networks and LSTM, have gained prominence in credit assessment (Ba et al., 2022). These methods are not only able to handle complex feature extraction but also capture nonlinear relationships and process time series data, thereby significantly improving the accuracy of credit assessment models (Shi et al., 2022). At the same time, comprehensive learning methods also play a key role, using ensemble learning strategies to combine the predictions of multiple base models (Singh et al., 2022). This method not only helps reduce the variance of the model and improves the generalization performance of the model but also performs well in the face of challenges such as data imbalance. By combining deep learning and comprehensive learning methods, financial institutions can better manage credit risks and provide more accurate, explainable, and comprehensive credit assessments, further improving the efficiency and decision-making quality of financial operations (Lenka et al., 2022). The integration of these methods brings new possibilities to the field of credit assessment and provides a solid foundation for future financial innovation. Deep learning methods give the model the ability to handle complex data and relationships, while comprehensive learning methods enhance the stability and reliability of the model. The combination of the two will further promote technological innovation in the financial field and provide financial institutions with more tools and methods to better respond to the changing credit market and risks. The development of this comprehensive approach will also help improve the stability of the financial system and provide borrowers and lenders with fairer, more transparent, and more sustainable credit assessment services.

Big Data Driven Credit Assessment

Big data driven credit assessment is a method that utilizes huge and diverse data resources to improve the accuracy and efficiency of personal credit assessment through data collection, preprocessing, feature engineering, and advanced machine learning technology (Roeder et al., 2022). This method not only includes financial historical data but also covers customers’ consumption behavior, social media activities, and other aspects to gain a more comprehensive understanding of customer credit risks (Lin, 2022; Ye & Zhao, 2023). The real-time nature of big data allows financial institutions to respond more quickly to customers' credit needs, while also strengthening fraud detection capabilities and improving the quality of financial decisions and customer experience. By leveraging big data resources, big data driven credit assessment represents an important step toward smarter and more comprehensive credit risk assessment methods in the financial sector.

Complete Article List

Search this Journal:
Reset
Volume 36: 1 Issue (2024)
Volume 35: 3 Issues (2023)
Volume 34: 10 Issues (2022)
Volume 33: 6 Issues (2021)
Volume 32: 4 Issues (2020)
Volume 31: 4 Issues (2019)
Volume 30: 4 Issues (2018)
Volume 29: 4 Issues (2017)
Volume 28: 4 Issues (2016)
Volume 27: 4 Issues (2015)
Volume 26: 4 Issues (2014)
Volume 25: 4 Issues (2013)
Volume 24: 4 Issues (2012)
Volume 23: 4 Issues (2011)
Volume 22: 4 Issues (2010)
Volume 21: 4 Issues (2009)
Volume 20: 4 Issues (2008)
Volume 19: 4 Issues (2007)
Volume 18: 4 Issues (2006)
Volume 17: 4 Issues (2005)
Volume 16: 4 Issues (2004)
Volume 15: 4 Issues (2003)
Volume 14: 4 Issues (2002)
Volume 13: 4 Issues (2001)
Volume 12: 4 Issues (2000)
Volume 11: 4 Issues (1999)
Volume 10: 4 Issues (1998)
Volume 9: 4 Issues (1997)
Volume 8: 4 Issues (1996)
Volume 7: 4 Issues (1995)
Volume 6: 4 Issues (1994)
Volume 5: 4 Issues (1993)
Volume 4: 4 Issues (1992)
Volume 3: 4 Issues (1991)
Volume 2: 4 Issues (1990)
Volume 1: 3 Issues (1989)
View Complete Journal Contents Listing