Loan Applications Research Articles

Machine Learning Based Classification Model for Prediction of Bank Loan Approval

Abstract: In this paper we creating and testing a smart loan prediction system using a special type of classifier called gradient boosting. Our methodology is meticulously laid out, covering a spectrum of essential stages including data pre-processing methodologies, in-depth exploratory analysis, and rigorous model training leveraging a dataset meticulously curated from Kaggle. Our model, with 300 estimators, a learning rate of 0.05, and a maximum of six features, achieves an astounding 98.03% accuracy. We utilize the pickle module to serialize our trained model, consequently deploying it as a web application. This application, which is powered by React for the front end and Flask for the back end, offers users a simple interface for entering loan application details and receiving real-time forecasts on loan acceptance or denial. Our research shows that gradient boosting classified the well in predicting the loans to the users.

FACTORS INFLUENCING SMALL AND MEDIUM ENTERPRISES' DECISION TO APPLY FOR BANK LOANS: A QUANTITATIVE ANALYSIS IN VIETNAM

This study investigates the determinants influencing the decision of Small and Medium Enterprises (SMEs) to apply for bank loans. Drawing upon a theoretical framework encompassing human capital, firm attributes, business strategy, and information asymmetry, we develop a model to predict SMEs' propensity to seek bank financing. Employing a quantitative methodology in Vietnam, we utilize a hypothetical-deductive testing approach on primary data collected through questionnaires focusing on loan applications. Our findings reveal several significant factors influencing SMEs' inclination towards bank loans. Contrary to expectations, the business experience of a firm's owner exhibits no significant correlation with the likelihood of applying for a bank loan. However, variables such as the educational background of the firm's owner, firm size, collateral availability, and interest rates on loans exhibit negative associations with loan application propensity. Conversely, factors including the presence of comprehensive business plans and establishment of relationships with bankers during start-up phases demonstrate positive relationships with SMEs' inclination to apply for bank loans. This study contributes to the understanding of SMEs' financing decisions and provides valuable insights for financial institutions in designing tailored lending strategies to meet the diverse needs of SMEs.

Comparison of Machine Learning Algorithms for Predicting Financial Risk in Cash Flow Statements

Nowadays, making financial decisions and evaluating loan applications is a complex and sensitive process. Cash flow data, which shows the financial risk status of businesses, plays a key role in evaluating loan applications. Cash flow data, which shows the financial risk status of businesses, plays a key role in evaluating loan applications. Guiding business managers in making strategic decisions and managing financial risks, quarterly data provides a detailed timeline of business performance and helps identify seasonal changes. A detailed analysis using machine learning algorithms evaluates the performance of different models built to compare businesses quarters in the loan classification process and highlights the role of cash flow data in the process. It was aimed to create effective algorithms by taking into account the suitability of the quarterly data between 2018 and 2022 of the 282 companies used in the study, and to provide a unique approach in the field of evaluating these algorithms with information criteria. The model performances of the quarters are very close to each other and a high success rate is obtained. Therefore, it was observed that quarterly periods did not make a significant difference in model performance. The model created for the 2nd quarter of 2019 was selected as the best model with 99% accuracy and 99% F1 value. It was also determined that the selection of variables with high accuracy rates in the models established for each quarter is important in terms of predicting financial risk.

A Submodular Optimization Approach to Accountable Loan Approval

In 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 lay 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 accountable. 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.

Promoting Counterfactual Robustness through Diversity

Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e.g., when a loan application has been rejected). However, as noted recently, counterfactual explainers may lack robustness in the sense that a minor change in the input can cause a major change in the explanation. This can cause confusion on the user side and open the door for adversarial attacks. In this paper, we study some sources of non-robustness. While there are fundamental reasons for why an explainer that returns a single counterfactual cannot be robust in all instances, we show that some interesting robustness guarantees can be given by reporting multiple rather than a single counterfactual. Unfortunately, the number of counterfactuals that need to be reported for the theoretical guarantees to hold can be prohibitively large. We therefore propose an approximation algorithm that uses a diversity criterion to select a feasible number of most relevant explanations and study its robustness empirically. Our experiments indicate that our method improves the state-of-the-art in generating robust explanations, while maintaining other desirable properties and providing competitive computational performance.

Goal Orientation for Fair Machine Learning Algorithms

A key challenge facing the use of machine learning (ML) in organizational selection settings (e.g., the processing of loan or job applications) is the potential bias against (racial and gender) minorities. To address this challenge, a rich literature of Fairness-Aware ML (FAML) algorithms has emerged, attempting to ameliorate biases while maintaining the predictive accuracy of ML algorithms. Almost all existing FAML algorithms define their optimization goals according to a selection task, meaning that ML outputs are assumed to be the final selection outcome. In practice, though, ML outputs are rarely used as-is. In personnel selection, for example, ML often serves a support role to human resource managers, allowing them to more easily exclude unqualified applicants. This effectively assigns to ML a screening rather than a selection task. It might be tempting to treat selection and screening as two variations of the same task that differ only quantitatively on the admission rate. This paper, however, reveals a qualitative difference between the two in terms of fairness. Specifically, we demonstrate through conceptual development and mathematical analysis that miscategorizing a screening task as a selection one could not only degrade final selection quality but also result in fairness problems such as selection biases within the minority group. After validating our findings with experimental studies on simulated and real-world data, we discuss several business and policy implications, highlighting the need for firms and policymakers to properly categorize the task assigned to ML in assessing and correcting algorithmic biases.

Improved playstore review sentiment classification accuracy with stacking ensemble

In today's digital era, user reviews on the Playstore platform are an invaluable source of information for developers, offering insights that are critical for service improvement. Previous research has explored the application of stacking ensemble methods, such as in the context of predicting depression among university students, to enhance prediction accuracy. However, these studies often do not explicitly detail the data acquisition process, leaving a gap in understanding the applicability of these methods to different domains. This research aims to bridge this gap by applying the stacking ensemble approach to improve the accuracy of sentiment classification in Playstore reviews, with a clear exposition of the data collection method. Utilizing Logistic Regression as the meta classifier, this methodology is executed in several stages. Initially, data was collected from user reviews of online loan applications on Google Playstore, ensuring transparency in the data acquisition process. The data is then classified using three basic models: Random Forest, Naive Bayes, and SVM. The outputs of these models serve as inputs to the Logistic Regression meta model. A comparison of each base model output with the meta model was subsequently carried out. The test results on the Playstore review dataset demonstrated an increase in accuracy, precision, recall, and F1 score compared to using a single model, achieving an accuracy of 87.05%, which surpasses Random Forest (85.6%), Naive Bayes (85.55%), and SVM (86.5%). This indicates the effectiveness of the stacking ensemble method in providing deeper and more accurate insights into user sentiment, overcoming the limitations of single models and previous research by explicitly addressing data acquisition methods.

Machine Learning Classifiers for Credit Risk Analysis

The modern world is a place of global commerce. Since globalization became popular, entrepreneurs of small and medium enterprises to large ones have looked up to banks, which have existed in various forms since antiquity, as their pillars of support. The risk of granting loans in various forms has significantly increased as a consequence of this, the businesses face financing difficulties. Credit Risk Analysis is a major aspect of approving the loan application that is done by analyzing different types of data. The goal is to minimize the risk of approving the loan for the Individuals or businesses who might not pay back on time. This research paper addresses this challenge by applying various machine learning classifiers to the German credit risk dataset. By evaluating and comparing the accuracy of these models to identify the most effective classifier for credit risk analysis. Furthermore, it proposes a contributory approach that combines the strengths of multiple classifiers to enhance the decision-making process for loan approvals. By leveraging ensemble learning techniques, such as the Voting Ensemble model, the aim is to improve the accuracy and reliability of credit risk analysis. Additionally, it explores tailored feature engineering techniques that focus on selecting and engineering informative features specific to credit risk analysis.

The Impact of Loan Apps on Students: Exploring Financial Access, Risks, and Implications

This article explores the influence of loan applications on students, investigating the impact of these apps on their financial behavior, academic performance, and overall well-being. With the rapid proliferation of loan apps in recent years, it is crucial to understand the consequences they may have on student borrowers. The study examines the experiences of students who utilize loan apps, providing insights into the potential advantages and drawbacks associated with these financial tools. By analyzing the data collected from surveys and interviews, the research highlights the significance of responsible borrowing, financial literacy, and regulatory measures in mitigating the negative effects and maximizing the benefits of loan apps. The findings contribute to the existing literature on financial behaviors and offer recommendations for policymakers, educational institutions, and students to navigate this evolving landscape effectively. Loan apps have gained significant popularity among students, offering quick and convenient access to financial resources. These apps provide students with a platform to obtain loans with minimal paperwork and faster processing times compared to traditional lending institutions. While these apps offer benefits such as easy accessibility, they also raise concerns about potential negative consequences. This article aims to delve into the impact of loan apps on students, shedding light on their financial behaviors, academic performance, and overall well-being. The widespread use of loan apps among students has brought forth a variety of issues that warrant examination. Firstly, these apps can influence the financial behaviors of students, shaping their attitudes towards borrowing, spending, and saving. Understanding the impact of loan apps on students is of significant importance for various stakeholders. Firstly, policymakers can benefit from this research by gaining insights into the implications of loan app usage among students. This knowledge can inform the development of regulations and policies to safeguard students' financial well-being and prevent predatory lending practices. It can also aid in implementing initiatives to promote financial literacy and responsible borrowing among students. Educational institutions can utilize the findings to better support their students in managing their finances. By understanding the challenges and potential risks associated with loan apps, institutions can provide targeted resources, workshops, and counseling services to help s. From the result it is seen that Rate your internet accessibility after loan lending entered market got the first rank Rate your internet usage per day where as is the having the lowest rank

Human-AI collaboration to mitigate decision noise in financial underwriting: A study on FinTech innovation in a lending firm

Financial institutions have recognized the value of collaborating human expertise and AI to create high-performance augmented decision-support systems. Stakeholders at lending firms have increasingly acknowledged that plugging data into AI algorithms and eliminating the role of human underwriters by automation, with the expectation of immediate returns on investment from business process automation, is a flawed strategy. This research emphasizes the necessity of auditing the consistency of decisions (or professional judgment) made by human underwriters and monitoring the ability of data to capture the lending policies of a firm to lay a strong foundation for a legitimate system before investing millions in AI projects. The judgments made by experts in the past re-emerge in the future as outcomes or labels in the data used to train and evaluate algorithms. This paper presents Evidential Reasoning-eXplainer, a methodology to estimate probability mass as an extent of support for a given decision on a loan application by jointly assessing multiple independent and conflicting pieces of evidence. It quantifies variability in past decisions by comparing the subjective judgments of underwriters during manual financial underwriting with outcomes estimated from data. The consistency analysis improves decision quality by bridging the gap between past inconsistent decisions and desired ultimate-true decisions. A case study on a specialist lending firm demonstrates the strategic work plan adapted to configure underwriters and developers to capture the correct data and audit the quality of decisions.

Reimagining Peer-to-Peer Lending Sustainability: Unveiling Predictive Insights with Innovative Machine Learning Approaches for Loan Default Anticipation

Peer-to-peer lending, a novel element of Internet finance that links lenders and borrowers via online platforms, has generated large profits for investors. However, borrowers’ missed payments have negatively impacted the industry’s sustainable growth. It is imperative to create a system that can correctly predict loan defaults to lessen the damage brought on by defaulters. The goal of this study is to fill the gap in the literature by exploring the feasibility of developing prediction models for P2P loan defaults without relying heavily on personal data while also focusing on identifying key variables influencing borrowers’ repayment capacity through systematic feature selection and exploratory data analysis. Given this, this study aims to create a computational model that aids lenders in determining the approval or rejection of a loan application, relying on the financial data provided by applicants. The selected dataset, sourced from an open database, contains 8578 transaction records and includes 14 attributes related to financial information, with no personal data included. A loan dataset is first subjected to an in-depth exploratory data analysis to find behaviors connected to loan defaults. Subsequently, diverse and noteworthy machine learning classification algorithms, including Random Forest, Support Vector Machine, Decision Tree, Logistic Regression, Naïve Bayes, and XGBoost, were employed to build models capable of discerning borrowers who repay their loans from those who do not. Our findings indicate that borrowers who fail to comply with their lenders’ credit policies, pay elevated interest rates, and possess low FICO ratings are at a higher likelihood of defaulting. Furthermore, elevated risk is observed among clients who obtain loans for small businesses. All classification models, including XGBoost and Random Forest, successfully developed and performed satisfactorily and achieved an accuracy of over 80%. When the decision threshold is set to 0.4, the best performance for predicting loan defaulters is achieved using logistic regression, which accurately identifies 83% of the defaulted loans, with a recall of 83%, precision of 21% and f1 score of 33%.

LOAN STATUS PREDICTION USING DECISION TREE CLASSIFIER

This paper investigates the effectiveness of the Decision Tree Classifier in predicting loan status, a critical task in the financial sector. The study utilizes a dataset containing various attributes of loan applicants such as income, credit score, employment status, and loan amount. The dataset is preprocessed to handle missing values and categorical variables. Feature importance is analyzed to understand the key factors influencing loan approval decisions. A Decision Tree Classifier model is trained and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The results demonstrate the feasibility of using Decision Trees for loan status prediction and provide insights into the decision-making process of loan approval.

SISTEM INFORMASI PENGELOLAAN SIMPAN PINJAM KOPERASI KARYAWAN BERBASIS WEB PADA PT. SINAR ABADI GAS

PT. Sinar Abadi Gas Cooperative is currently developing a web-based information system to expedite and facilitate savings and loan transactions. In this research, the team is using the research and development (R&D) method to develop a savings and loan application that will utilize PHP programming language and MySQL database. The team will create three types of users within this system, namely the admin, chairman, and members. They will have access to several prepared forms, including login forms for the admin, chairman, and members. Additionally, there will be customized main pages based on each user's role. The staff and member data forms will be used to manage cooperative member information. Furthermore, there will be a transaction form for savings and loans. These data will be used to generate member reports and loan reports. Cooperative members will also be able to apply for loans through the loan application form. After the application is submitted, the admin or chairman can utilize the confirmation form to follow up on the request. With this web-based cooperative data processing system, PT. Sinar Abadi Gas aims to enhance speed, accuracy, and precision in conducting savings and loan transactions.

A Comparative Study on Loan Status: Utilizing Machine Learning Algorithms for Predictive Analysis

This research delves into a comprehensive comparative study focused on predicting loan status through the application of various machine learning (ML) algorithms. The objective is to assess and compare the effectiveness of Decision Trees, Random Forest, Support Vector Machines (SVM), and Gradient Boosting models in determining the likelihood of loan approval or denial. Leveraging a dataset comprising historical loan application data, including applicant demographics, financial history, and loan characteristics, the study conducts rigorous analysis and interpretation of the models' performance. The results provide valuable insights into the strengths and weaknesses of each algorithm, offering a nuanced understanding of their predictive capabilities in the context of loan status determination. This research contributes to the growing body of knowledge in the application of ML algorithms in the financial sector, presenting practical implications for institutions seeking to enhance their loan approval processes. Key words: Predictive Analysis, Machine Learning Algorithms, Loan Status, Comparative Study, Utilization

NUMERICAL ANALYSIS OF HOME OWNERSHIP LOANS BANK INTEREST RATES IN INDONESIA WITH NEWTON'S INTERPOLATION METHOD

The demand of the Indonesian society to own homes and properties is increasing along with the growth of Indonesia's population. This has led to an increase in population density, causing property prices to rise. The way to own property or a house in accordance with monthly income is by using bank housing loans. Three Indonesian banks renowned for housing loan applications, namely BTN, Mandiri, and BSI, were selected as samples in this study. These three banks have their own advantages and different bank interest rates. Therefore, this research was created as a tool for consumers to make decisions by considering the advantages obtained when applying for a loan at one of the three banks. This study employs the Newton's interpolation method to generate formulas that can help solve consumer problems. The results of this study generally indicate that Mandiri bank has an advantage in terms of lower installment costs compared to BTN and BSI.

Economic Empowerment of Tanzanian Women Through Ownership of Tourism Micro, Small, and Medium Enterprises (MSMEs)

This paper examines how Tanzanian women are empowered through the ownership of tourism micro, small and medium enterprises (MSMEs); evaluates the effects of economic empowerment on their welfare; and discusses the challenges they face when running them. Using data on 475 women in Mainland Tanzania and Zanzibar, the empirical method used compares selected empowerment indicators before and after the women started their businesses. To determine the significance of the difference in monthly income earned and percentage contribution to household income, we use a non-parametric test. We find that owning tourism MSMEs empowers women by increasing their monthly income and contribution to household income, decision making in the enterprise and household, and allowing them to own assets. Women face challenges in obtaining inputs and accessing credit when starting and operating tourism MSMEs, lack capital to start and expand their businesses, and business management skills. Other constraints include high interest rates and difficult loan application procedures. Providing information on government funding opportunities, incorporating training in bank financial schemes, and simplifying loan application procedures to encourage women to apply for loans are the suggested measures to increase the empowerment effects of tourism MSMEs.

Design and implementation of a loan default prediction system using random forest algorithm

Loan default prediction is a crucial task in the lending industry; it helps financial institutions make informed decisions about granting loans. It is usually a daunting task for the bank or financial institution to predict customers who will default on a loan especially when there are thousands of applicants. This loan default prediction system aimed to improve the Area Under the Curve (AUC) score. This loan default prediction system used various data sources, such as demographic information, credit history, and financial performance to predict the likelihood of a loan being defaulted. The system used a random forest (RF) machine learning algorithm to analyze the data and build predictive models. The model was then used to make predictions about new loan applicants and existing borrowers who may default in the future. The system can be customized to meet the specific requirements of different lending institutions. The system enables lenders to make better decisions on loan approval, interest rate determination, and credit risk, management. The loan default prediction system also provides insights into risk factors that contribute to loan default and helps lenders develop effective strategies to mitigate these risks, making it an indispensable tool for lenders. The resultant system achieved an improved AUC score of 98%.

Lender Automation and Racial Disparities in Credit Access

ABSTRACTProcess automation reduces racial disparities in credit access by enabling smaller loans, broadening banks' geographic reach, and removing human biases from decision making. We document these findings in the context of the Paycheck Protection Program (PPP), where private lenders faced no credit risk but decided which firms to serve. Black‐owned firms obtained PPP loans primarily from automated fintech lenders, especially in areas with high racial animus. After traditional banks automated their loan processing procedures, their PPP lending to Black‐owned firms increased. Our findings cannot be fully explained by racial differences in loan application behaviors, preexisting banking relationships, firm performance, or fraud rates.

Digital empowerment and innovation in risk control strategies for fishery supply chain finance—a case study of Puhui agriculture and animal husbandry financing guarantee company limited

To examine how to innovate the model of financing a fishery supply chain and develop risk control strategies for seafood and aquaculture enterprises in the digital empowerment scenario, this study conducts field research on a leading agricultural enterprise, New Hope Liuhe Company Limited (hereinafter referred to as ‘New Hope Liuhe’) and its subsidiary Puhui Agriculture and Animal Husbandry Financing Guarantee Company Limited (hereinafter referred to as ‘Agriculture and Animal Husbandry Guarantee Co.’), based on business and financial risks from three phases of loan application, loan use, and loan recovery. The study found that New Hope Liuhe optimizes the division of functions among core enterprises in supply chain finance and develops innovative digital risk control strategies using ‘online big data + offline visits’ to effectively control business and financial risks in fishery supply chain finance. Accordingly, this study suggests that seafood and aquaculture enterprises that implement supply chain finance should innovate the model of supply chain finance from the perspective of differentiation of core enterprise functions and continuously innovate the risk control strategies using digital empowerment and big data in fishery operation.

ANALISIS KUALITAS SUMBER DAYA MANUSIA DALAM PERILAKU KEUANGAN IBU RUMAH TANGGA LINGKUNGAN PERUMNAS PATRANG KOTA JEMBER DI ERA DIGITALISASI

The quality of human resources in the financial behavior of housewives in the era of digitalization, the existence of digital media (market place) and free online loan applications, makes housewives unable to control their household's financial behavior which leads to various problems such as money running out prematurely. , do not have regular savings in the form of saving money or in financial institutions, and do not have an emergency fund. In fact, it is not uncommon to find many family members who are in debt or borrow money from banks, neighbors or from agents where money is borrowed. The aim of this research is to determine and analyze the management of the quality of human resources in the financial behavior of housewives in the Perumnas Patrang Environment, Jember City. The method in this research uses a qualitative approach with a survey type. Data collection in research uses observation and interviews. The findings obtained from the lack of knowledge about financial management among housewives will have an impact on the economy of the perpetrators, especially in the current era of digitalization.