House loans decisive factors (or features) comparison: helping customers get loans
DOI:
https://doi.org/10.61173/pcwtt638Keywords:
decision tree, neural network, logic regres-sion, prediction, house loans, mortgage loans, consumersAbstract
This article provides a method, system, and related equipment for comparing decisive factors of house loans to assist consumers in securing loans. We chose the data that includes many factors about personal such as marriage/ single, income. The study was conducted applying decision tree, neural network, and logic regression. The method includes obtaining consumer financial data; segmenting this data into multiple overlapping financial facets; generating a preliminary financial profile from these facets; performing noise reduction on the preliminary profile to create a detailed financial model; slicing the detailed model into various financial segments; and analyzing these segments to derive a multidimensional understanding of key house loan factors. This approach minimizes both explicit and implicit risks, ensuring a precise alignment with consumer financial profiles. Additionally, converting three-dimensional financial data into two-dimensional segments reduces computational complexity and errors, ensuring overall accuracy in loan evaluation and decision-making. In the last, we use these models to compare which factor influence the risk of loan mostly, so we advise if customers do not have house or car, keep working in one field and carefully view different places’ loan policies still can be helpful for their loaning.
References
[1] What Is Logistic Regression? | IBM. (n.d.). https://www. ibm.com/topics/logistic-regression#:~:text=Logistic%20 regression%20estimates%20the%20probability,data%20set%20 of%20independent%20variables.
[2] Tolles, Juliana, and William J. Meurer. “Logistic regression: relating patient characteristics to outcomes.” Jama 316.5 (2016): 533-534.
[3] Cramer, Jan Salomon. “The origins of logistic regression.” (2002): 4.
[4] Maimon, Oded Z., and Lior Rokach. Data mining with decision trees: theory and applications. Vol. 81. World scientific, 2014.
[5] Quinlan, J. Ross. “Induction of decision trees.” Machine learning 1 (1986): 81-106.
[6] Hardesty L (14 April 2017). “Explained: Neural networks”. MIT News Office. Archived from the original on 18 March 2024. Retrieved 2 June 2022
[7] Bishop, Christopher M., and Nasser M. Nasrabadi. Pattern recognition and machine learning. Vol. 4. No. 4. New York: springer, 2006.
[8] Uddin, Nazim, et al. “An ensemble machine learning based bank loan approval predictions system with a smart application.” International Journal of Cognitive Computing in Engineering 4 (2023): 327-339.
[9] Li, Xingyun, et al. “Prediction of loan default based on multi-model fusion.” Procedia Computer Science 199 (2022): 757-764.
[10] Li, Huan, and Weixing Wu. “Loan default predictability Dean&Francis ISSN 2959-6130 with explainable machine learning.” Finance Research Letters 60 (2024): 104867.
[11] Ayberk, Idil, and Zeynep Önder. “House prices and bank loan portfolios in an emerging market: The role of bank ownership.” Economic Modelling 106 (2022): 105683.
[12] Cortés, David, and Pilar Soriano. “Analysis of macroeconomic determinants of non-performance in consumer and mortgage loans.” Finance Research Letters 61 (2024): 104939.
[13] Baumöhl, Eduard, Štefan Lyócsa, and Petra Vašaničová. “Macroeconomic environment and the future performance of loans: Evidence from three peer-to-peer platforms.” International Review of Financial Analysis 95 (2024): 103416.
[14] Zeng, Guoping. “A Comprehensive Study of Coefficient Signs in Weighted Logistic Regression.” Heliyon (2024).
[15] Alvarez Melis, David, and Tommi Jaakkola. “Towards robust interpretability with self-explaining neural networks.” Advances in neural information processing systems 31 (2018).
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
