Loan Applications Research Articles

Mathematics of Machine Learning: An Introduction

Over the course of just a few decades, machine learning has grown into a force which shapes modern life perhaps as much as the combustion engine or wireless communication. As we drive to work, machine learning algorithms extract license plate numbers from images captured by automatic cameras at busy intersections. At work, they measure our productivity and govern our supply chains. In our personal lives, they power product recommendations on online shopping sites and suggestions on social media. In our homes and on our devices, they recognize our voices and our faces. They process our loan applications and evaluate our medical images. More globally, they stabilize power grids and assist in planning flight routes. There is not a space in our public and personal lives which machine learning has not at least begun to affect. For a field as ubiquitous, it is fairly poorly represented in our common knowledge. This article aims at giving a high level introduction to some core tasks, ideas and methods of machine learning for readers who are familiar with at least some undergraduate mathematics. Advanced readers may get more from certain sections, but our goal is to present a self-contained picture which requires little knowledge beyond calculus in multiple variables and elementary linear algebra. For readers who have not taken many of the advanced classes, this may also motivate why certain fields of study are of interest in applications. One big omission in this article are deep neural networks, i.e. the models which underly 'deep learning.' Due to their special importance, they will be discussed in a separate companion article.

Leveraging data quality analytics for enhanced loan application and performance insights: A comprehensive approach

Leveraging data quality analytics for enhanced loan application and performance insights: A comprehensive approach

A Behavioral Analysis of Online Loan Application Adoption: The Roles of Ease of Use, Risk, and Trust in Rural Bali

The rapid advancement of technology, particularly in digital financial services, has significantly facilitated various societal activities, wherein individual behaviors to adopt new technologies are crucial factors. This study analyses the influence of perceived ease of use, perceived risk, and trust on the intention to use online loan applications among residents of Bangli, a rural regency in Bali, who have not yet adopted such applications. Utilizing an explanatory research design and a quantitative approach, this study involved 96 respondents selected through a nonprobability sampling method with a purposive sampling technique. Several analytical methods were employed, including validity and reliability testing, classical assumption testing, and multiple linear regression analysis. The findings reveal that perceived ease of use, perceived risk, and trust significantly affect adoption intentions both partially and simultaneously, with ease of use and trust positively influencing these intentions, while perceived risk has a negative effect on adoption intentions. This study contributes to international marketing management by offering insights into user behavior and the elements that foster or hinder fintech adoption in rural settings. By focusing on the roles of ease of use, risk perception, and trust, it provides a renewed perspective for enhancing the global expansion of fintech services.

The Effect of AI-Enabled Credit Scoring on Financial Inclusion: Evidence from an Underserved Population of over One Million

We studied the effect of a major bank adopting an AI-enabled credit scoring model on financial inclusion as measured by changes to the approval rate, default rate, and utilization level of a personal loan product for an underserved population. The bank serves over 50 million customers and previously used a traditional rule-based model to evaluate the default risk of each loan application. It recently developed an AI model with a higher prediction accuracy of default risk and used the AI model and the traditional model together to assess loan applications for one of its personal loan products. Although the AI model may be more accurate in estimating default risk, little is known about its impact on financial inclusion. We investigated this question using a difference-in-differences approach by comparing changes in financial inclusion of the personal loan product that adopted the AI model to that of a similar personal loan product that did not adopt the AI model. We found that the AI model enhanced financial inclusion for the underserved population by simultaneously increasing the approval rate and reducing the default rate. Further analysis attributed the enhancement in financial inclusion to the use of weak signals (i.e., data not conventionally used to evaluate creditworthiness) by the AI model and its sophisticated machine learning algorithms. Our findings are consistent with statistical discrimination theory, as the use of weak signals and sophisticated machine learning algorithms improves prediction accuracy at the individual level, thus reducing the reliance on group characteristics that often lead to financial exclusion. We elaborated on the development process of the AI model to illustrate how and why the AI model can better evaluate members of underserved populations. We also found the impacts of the AI model to be heterogeneous across subgroups, and those with missing weak signals saw smaller improvements in the approval rate. A simulation-based analysis showed that simplified AI models were also able to increase the approval rate and reduce the default rate for this population. Our findings provide rich theoretical and practical implications for social justice by documenting how an AI model designed for improving prediction accuracy can enhance financial inclusion.

Integrating fintech and innovation in microfinance: Transforming credit accessibility for small businesses

The integration of fintech in microfinance is transforming credit accessibility for small businesses, especially those traditionally underserved by conventional financial institutions. Fintech solutions offer innovative pathways for microfinance institutions (MFIs) to streamline lending, reduce operational costs, and enhance credit risk assessment, making it easier and faster for small businesses to obtain funding. This review explores how digital lending platforms, blockchain technology, mobile wallets, and artificial intelligence (AI) are reshaping the microfinance landscape. By leveraging digital platforms, MFIs can simplify loan application processes and expand financial services to remote or unbanked areas, where small businesses often lack the collateral or credit history required by traditional lenders. Blockchain and smart contracts enhance transparency, security, and trust in transactions, while AI and machine learning provide advanced methods for assessing creditworthiness using alternative data. These innovations enable MFIs to adopt a more inclusive approach, reaching small businesses with customized financial solutions and enabling responsible lending practices. This review examines case studies from diverse regions to highlight the transformative effects of fintech integration on credit accessibility for small businesses, demonstrating tangible improvements in financial inclusion and economic resilience. Despite these advancements, challenges remain, including data privacy concerns, regulatory issues, and technological barriers in under-resourced areas. Addressing these issues through collaborative partnerships, regulatory frameworks, and digital literacy programs can maximize the impact of fintech-driven microfinance. Ultimately, integrating fintech into microfinance has the potential to drive sustainable economic growth, empowering small businesses to thrive and fostering a more inclusive financial ecosystem. This review advocates for continued innovation and supportive policies to strengthen fintech's role in advancing credit accessibility for small businesses globally.

LOAN ELIGIBILITY CHECKER

By automating eligibility evaluation based on preset criteria, the Loan Eligibility Checker technology is intended to expedite the loan application process. This project evaluates applicants based on important indicators, such as debt-to-income ratio, income, employment stability, and credit score, using data processing, machine learning, and rule-based algorithms. This solution saves time and resources for manual assessment, improves client satisfaction through prompt feedback, and increases the efficiency and accuracy of loan evaluations for financial institutions by offering an instant conclusion on loan eligibility. Because of its scalability, the system can process a large number of applications and offer reliable, impartial evaluations to a diverse pool of candidates. In the end, financial institutions benefit much from the Loan Eligibility Checker.

Enhanced Loan Risk Assessment: A Machine Learning Approach

This project develops a loan eligibility prediction system using machine learning, specifically the Random Forest Classifier. The system addresses the limitations of manual loan approval processes, which are time-consuming and prone to human error. A machine learning model is trained on a dataset of loan applications, incorporating features like gender, marital status, income, loan amount, and credit history. This model automatically predicts the eligibility of loan applicants, providing a faster and more objective assessment than traditional methods. The project also includes a user-friendly graphical user interface (GUI) built using Tkinter, allowing users to input applicant information and receive an immediate loan approval or rejection prediction. The model's performance is evaluated using various metrics to ensure accuracy and reliability. The high accuracy achieved by the k-nearest neighbor algorithm demonstrates the effectiveness of the proposed approach. Keywords: Loan Eligibility Prediction, Loan Risk Assessment, Credit Risk Modeling, Machine Learning, Classification, Random Forest, Ensemble Learning, Hyperparameter Tuning, Model Evaluation

Analysis of private funding and its accountability by financial companies - ICICI retail branch

This study analyses the role of private funding and its accountability within the retail banking branch of ICICI Bank. The research investigates the creditworthiness assessment of loan applicants, the accountability of funding provided, and the challenges faced by relationship managers in the Business Lending Group

Statistical Methods in Credit Risk Prediction: Analyzing Risk through Data Analytics

This study explores the factors influencing loan approval decisions by financial institutions using logistic regression analysis. By examining a dataset of loan applicants, we identify key predictors that significantly impact the likelihood of loan approval. The analysis reveals that higher income, larger family size, higher education levels, possession of a CD account, use of online banking, and having a credit card are positively associated with loan approval. Conversely, the presence of a securities account has a more complex relationship with loan approval likelihood. These findings suggest that financial institutions favor applicants with stable financial profiles and higher levels of financial engagement. Understanding these factors can help improve risk assessment models, ensuring more accurate and fair loan approval processes.

Social Penetration Analysis in Self-Disclosure of Online Loan Application Users to Their Partners

Abstract: This study aims to analyze the disclosure of online loan users to their partners through social penetration theory. Information technology-based money lending services are one of the innovations in the financial sector, utilizing technology to facilitate lending transactions without meeting in person. This transaction mechanism is carried out through a system provided by the Fintech Lending Organizer, either through an application or a website. Several problems arise because of the characteristics of online loans that often terrorize and intimidate people close to them without asking permission. This study is descriptive, using data collection techniques on ten pairs of online loan informants with their partners. Data analysis was carried out using interactive techniques involving interactions between data collection, data reduction, data presentation, and conclusions. Based on the social penetration analysis, five pairs of informants decided to separate/divorce, while five pairs did not divorce. The five pairs of informants who did not divorce were at stages 3 (affective exchange) and 4 (stable exchange). The five pairs who divorced were at stage 2 (exploration of affective exchange), which decreased the development of their relationship to deterioration. Couples who eventually divorce receive negative Feedback from their partners in the form of anger, annoyance, and regret. The perpetrators decide to get involved in online loans without discussing it with their partners but also have no desire to discuss it. The perpetrators' mindset, household economic problems, characteristics of online loans, and skills in communicating issues to their partners color the couple's interactions towards the end of the relationship. On the other hand, supportive Feedback, personality, and gender of the partner are factors that influence self-disclosure.

Financial Literacy Program in Introducing Online Loan Applications to University Students

The Covid-19 pandemic in 2021 impacted the increasing diversity of basic needs in society and accelerated digitalization, which has now become a lifestyle. Easy access to digital platforms for shopping, education, investment, payments, and loans has made wise financial management essential. According to data from the Financial Services Authority (OJK), the total distribution of online loans from Fintech Lending in Indonesia reached IDR 225.55 trillion in 2022, an increase of 44.6% from the previous year. Fintech simplifies loan access through peer-to-peer (P2P) lending products that are fast and without complicated requirements, attracting the interest of young generations. Therefore, financial literacy is crucial for Sampoerna University students to address the low level of financial understanding amid the proliferation of online loan applications. Knowledge of risk management is needed so that students can make wise and responsible financial decisions and manage their finances effectively.

Environmental Factors Affecting Growth of MSME’s Owned by Entrepreneurs with Disabilities in Rural Areas in Kenya: A Case of Meru County

Purpose: In the recent past, the government of Kenya has paid much attention to entrepreneurship primarily because of the positive relationship between entrepreneurship, job creation and economic growth. In Kenya, over 1.3 million Persons live with disabilities with most of them being generally economically deprived and over-represented among the poor. The aim of the study study was to investigate the external business factors affecting growth of MSME’s owned by entrepreneurs with disabilities in rural areas in Kenya: a case of Meru County. Methodology: The target population comprised of 2021 entrepreneurs with disabilities. The researcher used a combination of stratified sampling, census and purposive sampling method to select the respondents. Data was collected by administration of questionnaires designed based on the research objectives. The data collected was then coded, entered, and analyzed using Statistical Package for Social Sciences (SPSS). Findings: The findings showed that if all factors; political-legal environment, social –cultural environment and technological environment had a positive and significant effect on growth of MSME’s. Political –legal factors had the greatest effect at 0,882, followed technological at 0.799 while social factors had 0.633. Unique Contribution to Theory, Practice and Policy: The study recommended that the government should provide adequate and timely funding to vocational and technical training institutions. Government funding programs such as Women, Youth and Uwezo fund should increase the minimum loan amount, simplify loan application process and ensure timely disbursement of funds as well as establish strategies of lending to individuals. Finally, a mentorship office should be established in every constituency to offer sector specific programs including activities geared towards exposing EwD’s to successful entrepreneurs.

Effective Machine Learning Techniques for Dealing with Poor Credit Data

Credit risk is a crucial component of daily financial services operations; it measures the likelihood that a borrower will default on a loan, incurring an economic loss. By analysing historical data for assessment of the creditworthiness of a borrower, lenders can reduce credit risk. Data are vital at the core of the credit decision-making processes. Decision-making depends heavily on accurate, complete data, and failure to harness high-quality data would impact credit lenders when assessing the loan applicants’ risk profiles. In this paper, an empirical comparison of the robustness of seven machine learning algorithms to credit risk, namely support vector machines (SVMs), naïve base, decision trees (DT), random forest (RF), gradient boosting (GB), K-nearest neighbour (K-NN), and logistic regression (LR), is carried out using the Lending Club credit data from Kaggle. This task uses seven performance measures, including the F1 Score (recall, accuracy, and precision), ROC-AUC, and HL and MCC metrics. Then, the harnessing of generative adversarial networks (GANs) simulation to enhance the robustness of the single machine learning classifiers for predicting credit risk is proposed. The results show that when GANs imputation is incorporated, the decision tree is the best-performing classifier with an accuracy rate of 93.01%, followed by random forest (92.92%), gradient boosting (92.33%), support vector machine (90.83%), logistic regression (90.76%), and naïve Bayes (89.29%), respectively. The classifier is the worst-performing method with a k-NN (88.68%) accuracy rate. Subsequently, when GANs are optimised, the accuracy rate of the naïve Bayes classifier improves significantly to (90%) accuracy rate. Additionally, the average error rate for these classifiers is over 9%, which implies that the estimates are not far from the actual values. In summary, most individual classifiers are more robust to missing data when GANs are used as an imputation technique. The differences in performance of all seven machine learning algorithms are significant at the 95% level.

Personal Bankruptcy Prediction Using Logistic Regression Model

According to the Insolvency Department of Malaysia, as of December 2023, 233,483 Malaysians are currently involved in bankruptcy cases due to their defaults on hire purchase loans, credit card loans, personal loans, housing loans, and business loans. This is indeed a critical issue because the growing number of personal bankruptcy cases will hurt the Malaysian economy as well as society. From an individual's economic perspective, bankruptcy minimizes their chances of getting a job. Apart from that, their accounts will be frozen, they will lose control of their properties and assets, and they will not be allowed to start any business or be a part of any company's Board of Directors. Bankrupts also will be rejected from any loan application. This paper examines this problem by developing a personal bankruptcy prediction model using the logistic regression technique. This paper defines "bankrupt" as terminated members who failed to settle their loans. The sample comprised 24,546 cases with 17% settled cases and 83% terminated cases. The data included a dependent variable, i.e., bankruptcy status (Y=1(bankrupt), Y=0(non-bankrupt)), and 12 predictors. Upon completion, this paper succeeds in coming out with a reliable personal bankruptcy prediction model and significant variables of personal bankruptcy. The findings of this paper are very beneficial and significant to creditors, banks, the Malaysia Department of Insolvency, potential borrowers, members of AKPK, and society in general in raising awareness of personal bankruptcy risks and such information may help them to take preventive measures in minimizing the number of personal bankruptcy cases.

Access to finance and its impact on operational efficiency of MSMEs: mediating role of entrepreneurial personality and self-efficacy

PurposeThe present study aims to investigate the factors of loan access that affect entrepreneurial self-efficacy (ESE) and operating efficiency of Indian Micro, Small and Medium Enterprises (MSMEs). Furthermore, the study intended to investigate the influence of ESE on the operating efficiency of Indian MSMEs and its mediating role.Design/methodology/approachIn this study, exploratory research design is used. The study heavily relies on the primary data which has been collected by using the survey research method from a cross-section of 617 women-owned MSMEs, located in urban, rural, suburban and exurban areas of Haryana, Uttarakhand, Himachal Pradesh and NCR-Delhi. The partial least square structural equation modeling method version 3.3.3 has been used to evaluate.FindingsIn terms of the selected factors affecting access to finance, it has been established that the Loan Formalities, Banking Process, Loan Process, Staff Responsiveness and Incentive Scheme have a positive and significant influence in enhancing accessibility to finance and improving the self-efficacy and operating performance of firms. The findings also show that ESE mediates the relationship between various factors of loan access and the operating efficiency of MSMEs.Research limitations/implicationsThe study’s findings show that entrepreneurial capacity is significantly and favorably impacted by attitudes toward entrepreneurship, ESE, perceived access to findings and business operations. It has also been demonstrated that entrepreneurial intentions are strongly and favorably influenced by entrepreneurial ability to access commercial bank financing for small businesses and the impact of the same on the women-owned MSMEs in India. It also revealed unfavorable loan terms, limited collateral, fear of repaying of loan and intricate loan application were among the many reasons for loan denial.Originality/valueThe study offers a comprehensive approach that simultaneously considers financial accessibility and ESE. This all-encompassing method offers a thorough grasp of the variables affecting MSMEs' operational efficiency (OE). In contrast to earlier research that might have concentrated only on direct relationships, this study explores the mediating mechanisms involved. This study examines how ESE modulates the influence of financing availability on OE, providing a comprehensive understanding of the underlying mechanisms. By taking into account particular MSME sector characteristics like size, industry or regional variations, the study may provide a unique contextual lens. Understanding how these contextual factors interact with entrepreneurial attributes and access to finance adds depth to the analysis.

PPDNN-CRP: privacy-preserving deep neural network processing for credit risk prediction in cloud: a homomorphic encryption-based approach

This study proposes a Privacy-Preserving Deep Neural Network for Credit Risk Prediction (PPDNN-CRP) framework that leverages homomorphic encryption (HE) to ensure data privacy throughout the credit risk prediction process. The PPDNN-CRP framework employs the Paillier homomorphic encryption scheme to secure sensitive loan application data during both the training and inference phases. Implemented using TensorFlow for deep neural network operations and TenSEAL for HE, the framework uses the Kaggle loan dataset to evaluate its performance. The results show that PPDNN-CRP achieved an accuracy of 80.48%, demonstrating competitive performance compared to Privacy-Preserving Logistic Regression (PPLR) at 77.23% and a slight decrease from the non-private DNN-CRP model at 86.18%. The model exhibited strong metrics with a precision of 0.84, recall of 0.91, F1-score of 0.87, and an AUC of 0.74. Security analysis confirms that PPDNN-CRP effectively defends against various privacy attacks, including poisoning, evasion, membership inference, model inversion, and model extraction, through robust encryption techniques and privacy measures. This framework offers a promising approach for achieving high-quality credit risk prediction while maintaining data privacy and complying with legal and ethical standards.

Imperatives of Small-Scale Businesses and Employment Generation in Uyo Local Government Area, Akwa Ibom state

The study investigated the relationship between small scale enterprises and employments generation in Uyo Local Government Area, Akwa Ibom State. A cross-sectional survey research method was adopted for the study. A sample of 361 respondents was drawn from the population of 3725 using Taro Yamane’s scientific sampling formula. For the objectives of the study to be achieved, three hypotheses were formulated and tested. The study utilized structured questionnaire as a major instrument for data collection. 361 questionnaire were distributed and 334 were returned in useable form. Data collected were analyzed using simple percentage and regression. The results of the regression analysis indicated positive relationship between the variables of small scale enterprises and employment generation in Uyo, Akwa Ibom State. It was recommended that; there should be simplified loan application processes and reduced collateral requirements for small scale enterprises to encourage access to funding, there should be government policies that promote and ensure regular maintenance of existing infrastructure to prevent deterioration and reduce disruptions to business operations, and there should be development of entrepreneurship and business management training programs tailored for small scale enterprise owners, covering essential skills like book-keeping, marketing and customer service.

A submodular optimization approach to trustworthy loan approval automation

AbstractIn the field of finance, the underwriting process is an essential step in evaluating every loan application. During this stage, the borrowers' creditworthiness and ability to repay the loan are assessed to ultimately decide whether to approve the loan application. One of the core components of underwriting is credit scoring, in which the probability of default is estimated. As such, there has been significant progress in enhancing the predictive accuracy of credit scoring models through the use of machine learning, but there still exists a need to ultimately construct an approval rule that takes into consideration additional criteria beyond the score itself. This construction process is traditionally done manually to ensure that the approval rule remains interpretable to humans. In this paper, we outline an automated system for optimizing a rule‐based system for approving loan applications, which has been deployed at Hyundai Capital Services (HCS). The main challenge lays in creating a high‐quality rule base that is simultaneously simple enough to be interpretable by risk analysts as well as customers, since the approval decision should be easily understandable. We addressed this challenge through principled submodular optimization. The deployment of our system has led to a 14% annual growth in the volume of loan services at HCS, while maintaining the target bad rate, and has resulted in the approval of customers who might have otherwise been rejected.

Loan Eligibility Prediction Using Machine Learning

Technology has made many improvements, and the banking industry is no exception. Submission of loan applications by people are so many every day, making it more difficult for bank to approve loan. To choose an applicant for loan approval, Banks must consider other bank policies also. Based on a few factors, the bank must choose the proposal that has the best probability of getting granted. It would be time-consuming and unsafe to individually check each applicant before recommending them for loan approval. Based on the prior performance of the person to whom the loan amount was previously accredited, we utilize a machine learning technique in this study to forecast the person who is trustworthy for a loan. This will check the whether the applicant is eligible for the loan or not based upon the any previous loan or running loans whether the applicant is paying back the loan within the deadline or not and it will check many other factors to shortlist the applicant is genuinely eligible for loan or not.

Does Soft Information Mitigate Gender Bias in Corporate Lending?

AbstractGender bias in leadership and decision-making is a well-documented and pervasive topic that continues to garner significant attention in academic research and business literature. In this paper, by exploiting a unique proprietary dataset of 550 mid-corporate loan applications managed by a major European bank, we explore how the use of soft information influences lending decisions of female loan officers as compared to their male counterparts. We find that use of soft information reduces information asymmetry which helps female officers in making diligent lending decisions resulting in increased granted credit with a lower default probability. We also investigate gender affinity within the banking organisation and find that female loan approvers are more likely to be supportive of their subordinate female loan officers by approving more credit to the loan applications handled by female loan officers. Finally, we examine the possible mechanisms that can explain these results, and find that female loan officers are able to better collect and use soft information as they cultivate and maintain deeper firm-bank relationships with their clients due to higher threat of losing or being penalized in their jobs for any possible errors. We also rule out any other possible explanations such as differences in workload, work experience, loan officers’ optimism, managerial ability, and screening capabilities between female and male loan officers. Our findings carry important policy implications, reflected in the optimal allocation of capital in the economy and the reduction of gender-related exclusion, which is vital in creating an equitable society and fostering a more ethical and inclusive workplace.