Loan History Research Articles

Predicting Mortgage Loan Defaults Using Machine Learning Techniques

Mortgage default prediction is always on the table for financial institutions. Banks are interested in provision planning, while regulators monitor systemic risk, which this sector may possess. This research is focused on predicting defaults on a one-year horizon using data from the Ukrainian credit registry applying machine-learning methods. This research is useful for not only academia but also policymakers since it helps to assess the need for implementation of macroprudential instruments. We tested two data balancing techniques: weighting the original sample and synthetic minority oversampling technique and compared the results. It was found that random forest and extreme gradient-boosting decision trees are better classifiers regarding both accuracy and precision. These models provided an essential balance between actual default precision and minimizing false defaults. We also tested neural networks, linear discriminant analysis, support vector machines with linear kernels, and decision trees, but they showed similar results to logistic regression. The result suggested that real gross domestic product (GDP) growth and debt-service-to-income ratio (DSTI) were good predictors of default. This means that a realistic GDP forecast as well as a proper assessment of the borrower’s DSTI through the loan history can predict default on a one-year horizon. Adding other variables such as the borrower’s age and loan interest rate can also be beneficial. However, the residual maturity of mortgage loans does not contribute to default probability, which means that banks should treat both new borrowers equally and those who nearly repaid the loan.

Big five personality with fuzzy approach to feasibility assessment and loan determination for peer-to-peer lending

Bad credit is an uncollectible receivable because the debtor has difficulty repaying. In May 2023, the number of loans will increase by 3.36%. This is due to the inaccuracy of creditors in assessing prospective debtors. Several methods of valuation of prospective debtors have been widely used, but the use of the test big five personality (TBFP) method for the assessment of prospective debtors has not been found. This study will use TBFP as an input variable that will be calculated using fuzzy-Mamdani. The output of the system is in the form of a recommended percentage (%) of the loan amount. This research needs to be done to provide an assessment of prospective debtors to be more objective so that bad credit problems can be reduced. The results of this study are taken into consideration to be used as input in assessing prospective debtors that are more appropriate so that it has an impact on increasing income. For the community can increase business activities. For the government to help people’s economic activities. Our research still needs to be developed by adding variables such as the financial condition of prospective debtors, psychological values, and loan history. Apart from that, it is necessary to carry out an in-depth study regarding recommendations for loan amounts for bad credit

Subsidy-driven firm growth: Does loan history matter? Evidence from a European Union subsidy program

Subsidies should target firms with profitable opportunities and insufficient funding, but this is difficult due to information asymmetry between firms and the government. We study how credit history of firms can help design more efficient subsidies. To this end, we combine data on non-repayable firm subsidies and the credit registry from Hungary. Using subsidy winners and losers as treated and control groups and leveraging variation in access to loans, we identify the differential impact of subsidies. While subsidies lead to an incremental impact on assets of loan-deprived as compared to loan-acquiring firms, the impact is transitory and fades after a few years. The impact on profitability follows a similar pattern despite the higher expected marginal value of capital for loan-deprived firms. Thus, loan deprivation is likely caused by borrower shortcomings instead of credit rationing by banks. In such cases, subsidies need not target loan-deprived firms.

Financial Oracle: Unlocking Credit Scores

This paper provides individuals with a reliable tool for predicting their credit scores based on various financial attributes. Leveraging ML models, specifically a Random Forest classifier, our system analyzes features such as yearly income, salary, bank accounts, credit card usage, loan history, and payment behavior. Users can input their financial information, and the system generates a predicted credit score. This predictive tool empowers individuals to gain insights into their creditworthiness, enabling better financial planning and decision-making. By offering a user-friendly interface and accurate predictions, our project seeks to assist users in understanding the factors influencing their credit scores and ultimately improving their financial well-being. With the increasing importance of credit scores in financial transactions and lending decisions, our tool serves as a valuable resource for individuals seeking to manage their finances more effectively.

Fraud-Agents Detection in Online Microfinance: A Large-Scale Empirical Study

Online Microlending, a new financial service, focuses on small loans without any sort of collateral. It provides more flexible and quicker funding for borrowers, as well as higher interest rates of return. For platforms that provide such services, an essential task is to adequately evaluate each loan’s risk so as to minimize the possible financial loss. However, there exists a special group of borrowers, namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">fraud-agents</i> , who gain illegal profits from inciting other borrowers to cheat, i.e., they help the high-risk borrowers evade the risk evaluation by crafting fake personal information. The existence of fraud-agents poses a severe threat to the risk management systems and results in a huge financial loss for lending platforms. In this article, we present the first machine learning-based solution to detect fraud-agents in online microlending. The key challenge of this decade-long problem is that it is unclear how to construct effective features from multiple behavior logs such as phone call history, address book, loan history and activity logs of borrowers. To address this problem, we first conduct an empirical study on over 600K borrowers to gain some insights on the adversarial behaviors of fraud-agents comparing to normal borrowers and benign-agents. Based on the study, we are able to design a total of 26 features, falling into four groups, for fraud agent detection. Then, we propose a two-stage detection model to address the challenge of limited number of labeled fraud agent examples. The evaluation results show that our method can achieve a precision of 94.30%. We deploy our method on a real large online microlending platform with 11,953,273 borrowers, and we identify 29,727 fraud-agents from them. The domain experts from the platform confirm that 95.59% of them are real fraud-agents, and have added them to the platform’s internal blacklist. We further conduct a measurement study on those fraud-agents to share deeper insights on their adversarial behaviors.

Aplikasi Sistem Manajemen Aset Laboratorium Komputer Pada SMKN2 Kab.Tangerang Menggunakan Framework Laravel8

A computer laboratory with appropriate instruments is a crucial entity at the SMA and SMK levels because the laboratory is a facility and infrastructure that can provide tools thatare difficult to present in the classroom. So is the case with SMKN 2 Tangerang Regency. But in fact, the conventional computer laboratory asset management and the absence of a system to record room loan histories pose an obstacle for schools to obtain fast and detailed data. This research is intended to produce a web-based asset management application system model that can overcome the problems encountered. This study uses observation, interviews, and literature studies to collect relevant data for further analysis using the PIECES method for the system design and development process. The system is designed with UML and Laravel framework. Extreme Programming is used as an approach to develop the system. The conclusion of this study resulted in a web-based asset management application system that can quickly and detailedly present asset data and computer laboratory room loan history and the use of Laravel provides convenience in building and developing future applications for developers.

STRATEGI KOLABORASI MODEL PENILAIAN KREDIT ALTERNATIF DIGITAL PADA LEMBAGA KEUANGAN MIKRO

Microfinance Institution (MFI) is a type of financial institutions with its considerable potential to be developed, especially established to provide services in financing products for the micro and ultra-micro segments. However, many of the MFIs actually experience difficulties in evaluating the feasibility of prospective debtors due to the absence of loan history. In addition, at the aggregate level, MFIs have a high level of non-performing loans, considering that the management only relies on social relations and closeness with prospective debtors when conducting feasibility study for loan. On the other hand, a program has been initiated by OJK since 2021 in collaboration between Financial Service Institutions and Digital Financial Providers, one of which is for MFIs with the aim of increasing productivity and efficiency by digitizing business processes. Taking into consideration to the program that has been initiated by OJK and the challenges faced by MFI industry, the aim of this study is to develop a digital alternative credit scoring strategy design with a partnership scheme in microfinance institutions. In this study, several relevant theories were used to support the analysis process, including product development strategies, external analysis (PESTEL), and internal analysis (tangible and intangible resources). As for data collection techniques Included in-depth interview and document review. The results showed that the strategy is needed in the short term (less than 1 year), medium term (1-3 years), and long term (more than 3 years) starting from matching relevant services, preparing various provisions and supporting tools needed, to institutional strengthening from the MFIs that will make an optimal collaboration to increase the role and contribution of MFIs to the economic growth in the long run.

Determinants of credit risk at Vietnam bank for agriculture and rural developments in Can Tho City

The aim of this study is to investigate factors affecting credit risks of the borrowers (both corporate and individual customers) of Vietnam bank for agriculture and rural development's branch at Can Tho city (lender), thereby proposing several solutions to improve the bank’s operational efficiency in the upcoming years. Simultaneous qualitative and quantitative research methods are applied and secondary data from 102 corporate customers and 2100 individual clients are collected directly from the financial report of the Can Tho branch of Vietnam bank for agriculture and rural development (Agribank) until the end of 2018. A binary logistics model is employed to identify the determinant factors of the credit risk of bank customers. Estimation results reveal that the credit risk of corporate customers is affected by the factors of sales growth, return on sales ratio, Debt to equity ratio, collateral-to-outstanding loan balance ratio, and customer's loan history which are consistent with those of previous studies, whereas the credit risk of individual customers is influenced by the factors of age, educational level, loan purpose, loan maturity, type of collateral, customer income, and customer loan history, which are confirmed by previous studies. The empirical findings of the article imply that the Can Tho branch of Agribank should take precautions in order to limit the credit risk of bank customers. In addition, several governance recommendations are given for bank’s manager to improve the operational efficiency of bank.

Analisis Prosedur Pemberian Kredit Usaha Rakyat Pada BRI Palangka Raya Unit Yos Sudarso

People's Business Credit is one of the government programs that aims to help the Indonesian people who have small businesses to prosper the nation's economy which is carried out by certain banks, one of which is BRI. This study aims to analyze the procedures for granting public private loans as well as the supporting and inhibiting factors for distributing people's business loans at Bank BRI Palangka Raya Unit Yos Sudarso. In this study using qualitative analysis, qualitative analysis techniques are carried out by collecting, compiling and drawing conclusions about the procedure for granting People's Business Credit (KUR) at Bank BRI Palangka Raya unit Yos Sudarso. The techniques of data collection procedures in qualitative analysis are interviews, observation and documentation. Interviews were conducted with the Bank who understands the procedure for granting KUR and one of the customers of the BRI KUR Palangka Raya unit, Yos Sudarso. Based on the results of the research that has been carried out, it shows that the procedure for providing People's Business Credit (KUR) at Bank BRI Palangka Raya unit Yos Sudarso has been carried out quite well and in accordance with government regulations, namely the first stage of credit application, namely the process of collecting administrative data as the first requirement to apply KUR. The second stage is credit analysis, analyzing administrative files and making visits to prospective customers' places of business. The third stage is the credit decision, the head of the unit will provide the final result, namely the credit decision. The fourth stage is credit disbursement, which is filling out a credit agreement or credit agreement regarding the rights and obligations of the customer. The supporting factors for distributing people's business loans are data on business actors who received assistance from the president for MSMEs and data from the market office. The inhibiting factors for the distribution of people's business loans are business actors who do not and do not want to apply for loans and business actors who have businesses but have a bad loan history and some customers who apply for loans but do not own businesses.

Helicopter Money and Basic Income, or a Work-Based Society? : A Brief History of Wages, Benefits, Loans and Quantitative Easing

Following the coronavirus outbreak, and especially before infl ation became a key factor in this period, several crisis management proposals raised the possibility of a universal basic income, which could be backed by the central bank’s money creation. Th e following paper is an essay that seeks to grasp the political economic meaning and implications of the propositions related to helicopter money and basic income. We cannot avoid observing the essence of these proposals, presented fundamentally as a distribution-related issue, in the historical context of value, work and money creation. Helicopter money appears in this light as a new paradigm of extensive growth, which at fi rst glance comes off as a fi nancial innovation, but paradoxically rather bears a relationship with a pre-capitalist conception of value. Moreover, helicopter money is a wage-substitute transfer that does not respond to the social and symbolic void that has replaced work. It appears to be a welfare instrument, while it can only rest on the separation of production and consumption on a global scale. Helicopter money is an extension of quantitative easing by other means, which unveils the motives for money creation. It is an overture to the thought experiments of ‘value without work’ and ‘economy without people’.

Machine Learning (ML) Technologies for Digital Credit Scoring in Rural Finance: A Literature Review

Rural credit is one of the most critical inputs for farm production across the globe. Despite so many advances in digitalization in emerging and developing economies, still a large part of society like small farm holders, rural youth, and women farmers are untouched by the mainstream of banking transactions. Machine learning-based technology is giving a new hope to these individuals. However, it is the banking or non-banking institutions that decide how they will adopt this advanced technology, to have reduced human biases in loan decision making. Therefore, the scope of this study is to highlight the various AI-ML- based methods for credit scoring and their gaps currently in practice by banking or non-banking institutions. For this study, systematic literature review methods have been applied; existing research articles have been empirically reviewed with an attempt to identify and compare the best fit AI-ML-based model adopted by various financial institutions worldwide. The main purpose of this study is to present the various ML algorithms highlighted by earlier researchers that could be fit for a credit assessment of rural borrowers, particularly those who have no or inadequate loan history. However, it would be interesting to recognize further how the financial institutions could be able to blend the traditional and digital methods successfully without any ethical challenges.

Credit risk analysis using support vector machines algorithm

Credit risk or also known as bad credit risk is defined as the risk that occurs due to the inability of the customer to repay the loan and the interest within a certain period of time. Bad credit can be prevented by selecting proper customers during the loan application process so as not to give losses to the Bank. This research aims to analyze credit risk using machine learning methods. One of the machine learning algorithms that can be used for data classification is Support Vector Machine (SVM). The concept of SVM is to find optimal hyper plane with maximum margin to linearly separate the data set into two classes. The dataset were taken randomly from 2015 to 2018 at Bank XX, as many as 610 data. Dataset was divided into two parts along with percentage of the training data 80% and the testing data 20%. The variables used were gender, plafond, rate, term of time, job, income, face amount, warranty, and loan history as independent variable as well as credit status as dependent variable. The testing of SVM algorithm used linear, polynomial, Radial Basis Function (RBF), and sigmoid kernel obtained confusion matrices with accuracy respectively 0.9262, 0.9508, 0.8934, and 0.8361. Meanwhile, the AUC values were 0.9129, 0.9419, 0.9051, and 0.8285. The SVM model with polynomial kernel is the best model of the four models because it has the highest accuracy and AUC value. Thus, this model can be used to classify prospective customers into good credit or bad credit class with sufficiently high accuracy so as to help banks reduce the risk of bad credit.

RANCANG BANGUN SISTEM INFORMASI MANAJEMEN KOPERASI MENGGUNAKAN METODE WEB ENGINEERING (Studi Kasus : Primkop Kartika Gatam)

Koperasi Primkop Kartika Gatam is a state-owned cooperative agency that provides savings and loan services to members and has an address at Jl Teuku Umar, No 85, Penengah, Kedaton, Bandar Lampung and has a total of 300 cooperative members. Based on the results of interviews with the head of the cooperative, Mrs. Ollivia Febrojaya, S.H, there were problems in the management process of processing savings and loan data, which as a whole was carried out using manual or recording processes such as loan applications and member data recording, saving and loan data recording. As a result, the integration of data between divisions cannot be carried out easily and the process of reporting data on deposits and loans is carried out repeatedly resulting in frequent delays in submitting reports on deposits and loans to the leadership. The next problem is that the process of calculating savings data is still using a calculator so that the impact is an error in calculating total savings and loans. This of course requires innovation regarding information technology that can be operated via the internet network using a website.So that the researcher provides a proposal to develop a cooperative management system that has several features such as online loan applications and can view the history of savings and loans and provides convenience with the calculation of the total recap and the amount of savings and loans automatically based on the date and month of the printed report.

RETRACTED: Research on current status and cultivation approaches of college students’ financial literacy in China under the campus loan perspective

This paper first reviews the development history of campus loans in China and the scale of Internet finance consumption, then conducts a survey of the status of college students’ financial literacy by using universities and colleges in Hunan as an empirical study. Basing on the survey results, we can find the general lack of financial literacy among college students. Finally, it expounds the cultivation path of college students’ financial literacy from three aspects in China, namely, establishing financial information security awareness, cultivating financial risk prevention awareness and improving financial discrimination ability, so as to control campus loan risks.

“Buying on time”

Consumer credit has been central to the history of small loans since the late 19^th century. Debates over credit buying (or “buying on time”) reveal fundamental assumptions about imagined futures and pasts in modern economies. Credit buying often built on expectations of future growth and improved living standards. Still, debates over credit highlight social anxieties also invoked an imagined past of supposedly more frugal household financing. Taking the German debate as a vantage point, the article deconstructs both the myth of a prewar past built on cash buying and contemporary fears of an “Americanized” future of debt-based spending. It explores transatlantic differences in the temporal perception of consumer credit. The final section examines shifts in consumer lending since the 1970s.

The effect of loan granted factor on peer-to-peer lending (funded loan) in Indonesia

This study aims to determine whether the loan granted factor can affect peer-to-peer lending in Indonesia. The factors investigated in this research are the loan amount, loan period, interest rate, gender, and loan history using the data from registered and licensed peer-to-peer lending by the Financial Services Authority or Otoritas Jasa Keuangan (OJK) on November 2019. By examining 1,006 loans, the analytical method used is binary logistic regression with a significance level of alpha 0.05. The results of this research are loan amount, loan period, and loan history have the strongest impact on borrowers’ loan funding decision, suggesting that these loan characteristics can signal information that standard measures are used for loan funding. However, interest rate and gender have no significant effect on loan granted. Overall, loan funding decisions are based on proper and relevant signals given by loan characteristics.

Approval of Sharia Cooperative Customer Financing Using PSO-Based SVM Classification Algorithm

Credit financing approval is an important task for financial institutions. The accuracy of decision making in accepting or rejecting credit applications must be precise and accurate. Data mining techniques can help credit approval with a smaller risk of error. Previous research has been carried out to classify customer loan history data with the highest accuracy obtained by the Support Vector Machine (SVM) algorithm. This study aims to improve the accuracy of previous research in classifying loan history data based on smooth and stuck credit labels to predict credible prospective customers. The algorithm used in managing the data is Support Vector Machine with Particle Swarm Optimization (PSO). The dataset used was 869 records from January 2015 to September 2018, labeled 291 records and 578 records smoothly. The results of the study proved that the Support Vector Machine algorithm based on Particle Swarm Optimization produced the best performance with an accuracy of 90.91% compared to SVM without PSO of 89.86%.

Reinforcement learning and mortgage partial prepayment behavior

An agent can learn from previous experience to make decisions. Several important studies claim that reinforcement learning plays a key role in explaining the evolution of the individual learning process. This paper studies the likelihood of mortgage partial prepayments and the process through which mortgage borrowers learn from making partial prepayment decisions in the residential mortgage market in China. Learning dynamics are measured by studying the mortgage partial prepayment behavior of individual borrowers. A longitudinal discrete choice model of the choice of the mortgage payment is presented and estimated using a rich set of mortgage loan history data from a leading mortgage lender in China. The results indicate that path dependency and reinforcement learning arise whenever a borrower's “partial prepayment” decision depends not only on current-stage variables and his/her individual characteristics but also on the learning experience (both from himself/herself and others). Borrowers with more partial prepayment experience in previous stages have a higher probability of making the same decision in the future. Moreover, learning dynamics are not monotonic, and recent experience plays a larger role than distal experience in determining a partial prepayment decision.

China – Angola – Russia: Non-existing Triangle

This article contains the detailed comparative analysis of Russian and Chinese participation in the economic development of one of the most important African countries. The article highlights the history of credits and loans, foreign direct investments to Angola, dynamics of Russian and Chines trade turnover in the 21-st century. Main projects of Russia-Angola economic co-operation, activities of the biggest Chinese companies in Angola are in the scope of this research. Main economic interest of both powers – China and Russia – is to obtain access to the rich energy and mineral resources of Angola. However, any numerical indices of Russian and Chinese involvement into Angolan economics show that Russia cannot compete with China in this respect. Incomparable scale of trade turnover and economic cooperation make the hypotheses about possible “rivalry” between Russia and China in this region groundless. In spite of the fact that China has reduced loans volumes to Angola recently, the trade between the two countries shows increasing trend. For the time being Russia seems competitive to China in military cooperation with Angola though falls behind in humanitarian sphere.

Intelligent System for Credit Risk Management in Financial Institutions

Credit crunch is an alarming challenge facing financial institutions in Ghana due to their inability to manage credit risk. Failure to manage credit risk may lead to customers defaulting and institutions becoming bankrupt, making it a major concern for financial institutions and the government. The assessment and evaluation of loan applications based on a loan officer's subjective assessment and human judgment is inefficient, inconsistent, non-uniform, and time consuming. Therefore, a knowledge discovery tool is required to help in decision making regarding the approval of loan application. The aim of this project is to develop an intelligent system based on a decision tree model to manage credit risk. Data was obtained from the bank loan histories. The data is comprised of four hundred observations with seven variables: client age, amount requested, dependents, collateral value, employment sector, employment type, and results. The results of study suggest that the proposed system can be used to predict client eligibility for loans with an accuracy rate of 70%.