Lending Institutions Research Articles

Survey on Mortgage-Backed Securities Prepayment Risk Using Machine Learning Models

Mortgages allow for partial or complete prepayment at any time prior to the loan's maturity date. A mortgage prepayment is risky for the lending institution because it eliminates the borrower's obligation to pay future interest and complicates the steps required for refinancing the mortgage loan. Prepayment risk is a threat to mortgage-backed securities (MBS) that arises when borrowers pay down their mortgage principal more quickly than expected. For MBS investors, this means lower cash flows. A negative impact on cash flows and exposure to extension risk could result from actual prepayment rates being higher or lower than expected.

Historical Diversity in Credit Intermediation: Cosignatory Lending Institutions in Europe and North America, 1700s–1960s

AbstractThrough a close reading of scattered, disparate, and largely unconnected secondary sources, supplemented with the analysis of primary sources, and backed by economic theory, this paper explores the origins, development, and socio-economic impact of so-called cosignatory lending institutions. These historical institutions were designed to issue small loans to small businesses and households and shared a reliance on cosigners to secure loans and on weekly instalments to repay them. Their shared lending format was flexible enough to display regional variations and this enabled cosignatory lending institutions to operate in societies characterized by notable differences in wealth and economic structure. It also allowed cosignatory lending institutions to fare better in a more urbanized, heterogeneous context than the more well-known credit cooperatives. As such, this systematic overview helps us better understand how credit markets were made more inclusive in urban contexts, which historical circumstances played a role in this, and perhaps even whether and how the success of cosignatory lending institutions may be replicated in present-day developed and less-developed economies.

Portrait of Debt Accounting Based on Feeling and Faith: a Study of Islamic Ethnomethodology

This study aims to construct debt accounting based on feelings and faith. This study uses an Islamic paradigm with an Islamic ethnomethodological approach. There are five data analysis stages: charity, knowledge, faith, revelation information, and good deeds. The study's results found that the source of household debt came from parents and lending institutions. Debt obtained through parents is more flexible regarding time and nominal repayment. This is different from debt obtained from lending institutions. The informants carried out the method of recording debt accounting both in memory and on paper. The practice of debt accounting is conditioned by the feeling of being uneasy, unpleasant, and depressed, even the fear that God will take a life while still in debt. The findings from this study reinforce that, in essence debt accounting is not limited to material (money) but conditions with a sense of and faith in the Creator

Automated credit assessment framework using ETL process and machine learning.

In the current business scenario, real-time analysis of enterprise data through Business Intelligence (BI) is crucial for supporting operational activities and taking any strategic decision. The automated ETL (extraction, transformation, and load) process ensures data ingestion into the data warehouse in near real-time, and insights are generated through the BI process based on real-time data. In this paper, we have concentrated on automated credit risk assessment in the financial domain based on the machine learning approach. The machine learning-based classification techniques can furnish a self-regulating process to categorize data. Establishing an automated credit decision-making system helps the lending institution to manage the risks, increase operational efficiency and comply with regulators. In this paper, an empirical approach is taken for credit risk assessment using logistic regression and neural network classification method in compliance with Basel II standards. Here, Basel II standards are adopted to calculate the expected loss. The required data integration for building machine learning models is done through an automated ETL process. We have concluded this research work by evaluating this new methodology for credit risk assessment.

Default Prediction for Loan Lenders Using Machine Learning Algorithms

Credit loans are considered most essential aspect of most financial institutions. All loan mortgagees or lenders are demanding to identify out effective commercial and business approaches to encourage customers to apply their credit loans. There are numerous business patrons who act negatively after their requests got approval. To avert this condition, lenders have to discover some techniques to forecast customer’s behaviors. This resulted to the usage of machine learning algorithms by the financial lending institutions for accessing loan applicants. Despite advancements in automating decision-based loan systems, most existing models do not consider the “early loan repayment” attribute as a factor in resolving this prediction error. In reality, the amendment for preliminary loan reimbursement in model building is obligatory, since a larger numbers of timely loan reimbursement observed during the loan period, reduces default rate. For effective model’s comparison based on accuracy and minimum errors of prediction, six supervised machine learning algorithms i.e. Random Forest, Artificial Neural Network, Classification and Regression Tree, Support Vector Machine, Logistic Regression, and Naïve Bayes were adopted to develop a default prediction models which include the early loan repayment attribute. The models were trained and tested on a loan dataset consisting of attributes with, and without early loan repayment attribute and were evaluated using five performance metrics. The results of the performance evaluation show that models that account for early loan repayment have higher accuracy, recall, precision, Root Mean Square Error and Receiver Operative Characteristics curve values than models trained without the early loan repayment attribute. The Random forest model proofed to be the best predictive model having 93% accuracy, 11% RMSE, 90% precision, 89% recall and 81% ROC value over others models.

Impact of SMEs’ financial reporting practices on their creditworthiness in Zimbabwe.

The purpose of this paper was to investigate and analyse how the financial reporting practices of the SMEs influence their ability to get funds from lending institutions. The study was grounded upon the mixed methods methodology. This methodology enabled the identification of both numerical and non-numerical consequences of the lack of financial reporting as a barrier to finance for SMEs. Explanatory Sequential design was used. Forty (40) owners representing different SMEs in diverse economic areas made up the studys population. A sample had to be chosen after the study population was chosen. Purposive or judgmental sampling was employed in this study. To obtain first-hand knowledge from the respondents, primary data was gathered through interviews, and questionnaires. Questionnaires were used to gather quantitative data while interviews were used for qualitative data. It was found out that most SMEs in Zimbabwe are failing to access credit facilities since they are not producing standard financial reports. Most respondents alluded that preparation of the financial statements is costly and would surely eat up upon the working capital of SMEs. As a recommendation, SMEs are encouraged to try to engage qualified Accountants who can interpret the IFRs for SMEs. More so the IASB should simplify the IFRs for SMEs such that the SMEs manage to make use of this crucial framework. The current position with financiers is that SMEs are failing to provide them the information they require. Therefore, there is need to upgrade the information systems and close the information gap that exists between the SMEs and the financiers.

Estimating farmers' intention towards institutional credit adoption by using extended theory of planned behavior

AbstractThe role of socio‐psychological factors on farmers' institutional credit adoption intention is rarely studied in the context of developing nations. This study estimates the direct and mediating association of various socio‐psychological factors with farmers' institutional credit adoption intention. An extended theory of planned behavior (TPB) was adopted and empirically tested using the cross‐sectional data from 384 farmers from West Bengal. The study used structural equation model for the mediation analysis. Results showed that primary TPB constructs like attitude, subjective norm, and perceived behavioral control were positively and significantly associated with the intention of institutional credit adoption. Besides direct effect, the primary TPB constructs mediated the relationship between institutional credit adoption intention and other explanatory constructs used in this study. Findings predicted a positive partial mediation between trusted information sources, formal education level, coping appraisal, risk perception, and farmers' formal credit borrowing intention. Risk perception displayed a direct and mediated, however, negative, association with farmers' institutional credit adoption intention. These findings provide a clear understanding of factors predicting farmers' intention to adopt institutional credit and comprehensive insight into establishing policies for effective institutional lending at the ground level. The study delivers a paramount scientific perspective to the policymaker of developing countries suffering from insufficient institutional credit penetration in the farming community to design practicable frameworks and incentivize policies to motivate farmers in institutional credit borrowing.

Residential property evaluation and climate change modelling

Climate change poses a first-order threat to human civilisation and governments across the world, their agencies and big and small corporations have announced climate emergencies and made commitments towards net zero emissions across a range of target dates. Regulators have tasked financial institutions in the insurance and banking sectors to expose their existing portfolios and lending practices to scrutiny as to resilience levels, preparedness and knowledge base relating to property risk level impacts from existing and emerging climate-driven property perils. The scope of these investigations has mobilised a range of consultancies and emerging climate service providers (CSPs) to support regulatory oversight and provide modelling input relative to expertise in a range of environmental issues driven by climate change. The combination of global emission scenarios and general circulation models (GCMs) with existing expertise in modelling real-world problems such as flooding, coastal erosion, storm and subsidence has produced forward-facing forecasts across the natural physical and societal risks. The regulatory results at portfolio levels have necessitated financial institutions scenario planning down to property address levels to assess overall scale of impacts and the possible provisioning requirements against multiple probabilities over decadal horizons out to 2100. These high-level assessments will in the next few years feed directly into valuation and property investigation for origination loans and the cash buyer. CSPs will inevitably seek to monetise a return on their investment in modelling for financial institutions and their unique exposure to portfolio-level provisioning as consultants to these organisations reporting to the regulator. How this data at a property level is interpreted spatially and temporally will be a unique new challenge for chartered surveyors and other property professionals within lending institutions and within the conveyancing sector. This paper looks at the development of portfolio-level climate change reporting, the scientific basis for decisioning and the real risks of assuming that scenario precision produces accurate climate outcomes at the property level. A range of evolving rule sets are proposed for lenders, valuation specialists and conveyancers to ensure reporting is fit for intended purpose.

Loan repayment performance of micro and small-scale enterprise: evidence from North Wollo Zone, Ethiopia

Loan defaulting is a prominent challenge to financial institutions' outreach and sustainability. As it has been increasing and become a critical problem in the study area, this study aimed to analyze the loan repayment performance of Micro and Small-scale Enterprise (MSEs) in North Wollo Zone, Amhara Region, Ethiopia. The study used a multi-stage sampling technique to select 336 sample enterprises (181 non-defaulter and 155 defaulters). Both qualitative and quantitative data were collected from primary and secondary data sources. The descriptive statistics result showed that non-defaulting was higher in trade (29.28%) and manufacturing (21.55%) MSEs, while high defaulting pertains to MSEs engaged in agriculture (24.52%) and construction (21.93%) sectors, respectively. The findings of financial ratios revealed that the average current ratio, debt ratio, and debt-to-equity ratio were 0.65, 0.72 and 7.95, respectively. The logit regression result showed that enterprise manager education level, collateral security, and financial literacy positively and significantly affected loan repayment performance while distance to lending institutions, repayment period, and loan diversion negatively affected it. Therefore, this study recommends that lending institutions and other concerned organizations organize warranties for the loan, align repayment schedules with the production period of enterprises, inclusive monitoring and supervision, and provide financial and basic business training to enterprises.

Peer to peer lending risk analysis based on embedded technique and stacking ensemble learning

Peer to peer lending is famous for easy and fast loans from complicated traditional lending institutions. Therefore, big data and machine learning are needed for credit risk analysis, especially for potential defaulters. However, data imbalance and high computation have a terrible effect on machine learning prediction performance. This paper proposes a stacking ensemble learning with features selection based on embedded techniques (gradient boosted trees (GBDT), random forest (RF), adaptive boosting (AdaBoost), extra gradient boosting (XGBoost), light gradient boosting machine (LGBM), and decision tree (DT)) to predict the credit risk of individual borrowers on peer to peer (P2P) lending. The stacking ensemble model is created from a stack of meta-learners used in feature selection. The feature selection+ stacking model produces an average of 94.54% accuracy and 69.10 s execution time. RF meta-learner+Stacking ensemble is the best classification model, and the LGBM meta-learner+stacking ensemble is the fastest execution time. Based on experimental results, this paper showed that the credit risk prediction for P2P lending could be improved using the stacking ensemble model in addition to proper feature selection.

Credit Card Fraud Detection Using Ml Algorithms

Bank credit card default rates are (as predicted by S&P dow Jones index) at all time high for the past few months. This possess a real challenge for banks and other lending financial institutions, as they are now more than ever are in need of a robust risk prediction model to generalize the economic behavior of their current and potential future clients. In real world massive stream of payment requests are coming in every second which is huge challenge to monitor. Machine Learning algorithms help in solving these huge challenges to an extent. These predictive models would not only benefit the lending institutions but also the customer as it would make them more aware of their potential defaulting rate. The goal of this project is to resolve this problem by building and comparing predictive risk models using supervised learning algorithms. We use python libraries to perform various Machine learning algorithms on the credit card dataset and data diagrams to have better visualization of data. Here the credit card fraud detection is done on the basis of some attributes in the dataset like the time factor and the amount factor. The accuracy of the algorithms is also being determined and the most efficient one is said with the highest accuracy obtained..

ANALYSIS OF FACTORS AFFECTING THE APPROVAL OF MICRO, SMALL AND MEDIUM ENTERPRISES CREDIT APPLICATIONS AT PEER TO PEER LENDING FINANCING INSTITUTIONS DURING THE COVID-19 PERIOD

MSMEs are one of the boosters of the Indonesian economy because they are considered to have a large contribution to economic growth. However, since the emergence of the COVID-19 virus, of course, it has an impact on MSMEs, in 2020 the economic growth figure shows a figure of minus 5.3 percent and there are 37,000 MSMEs affected by COVID-19, so the obstacle faced by MSMEs is the need for capital to rise in the midst of the COVID-19 pandemic. The purpose of this study is to find out what factors influence the approval of MSMEcredit applications to peer to peer lending institutions during the COVID-19 period. The method used is probit regression analysis with the IBM SPSS Statistics 25 application. The independent variables used in the study were the amount of loan, length of business andcredit period.The results of this study found that the loan amount and credit period have a negative and insignificant influence on the approval of credit applications, while the length of business has a positive and significant influence on the approval of credit applications.

Influence of joint liability on enterprise development of rural women in Nyamache Sub-County

Group lending has received a great attention from economists and policymakers for its successful delivery of credit to poor borrowers and its role in alleviating poverty in the developing countries. The success of group lending in providing credit to poor borrowers has been attributed to its ability to mitigate the asymmetry of information and enforcement problems in credit markets. The ability of group lending institutions to overcome the asymmetry of information and enforcement problems has been theorized to be the driving force behind their outreach to the poor, their sustainability, and their repayment performance. While there is a host of theoretical models explaining the success of group lending, empirical research has lagged behind. The focus of this study was to explore the determinants of group lending mechanism on enterprise development of rural women in Nyamache sub-county, Kenya. The questionnaires were edited first for accuracy, and completeness. The study used frequency distribution and percentages, and computer software-Statistical Package for Social Scientists version 22 (SPSS v 22) as a tool of analyzing data, and to establish relationships between variables. The study established that, joint liability, training, group representation and loan size positively and significantly influenced enterprise development. The study recommends that; women groups should be strengthened so that they can be in position to jointly access loan for the development of their enterprises, the women groups lending group should organize effectively trainings so as to equip the members with capacity to efficiently manage their business enterprises, the women lending group should share the lending policies with members to understand them foe easy of operation and to minimize misunderstanding and any arising conflict and that the women lending groups should effectively vet group members to enable them access maximum qualified amounts so as they could invest in their businesses for survival and growth.

Factors Affecting the Performance of Women Entrepreneurs in Micro and Small Enterprises in ADDIS ABABA

The purpose of this study is to look into the elements that influence how well women entrepreneurs do in MSEs and the difficulties they encounter while trying to get technical and business training support from training colleges or institutions. A descriptive study design using a variety of research methods was used to reach the goal. Using probability and non-probability selection techniques, including simple random and purposeful sampling procedures, a sample of 238 female entrepreneurs working in three sectors was selected for the study. To respond to the fundamental interview questions (purposive approach), questionnaires were created using close-ended and Likert scales, and they included questions about how women entrepreneurs perform in MSEs and the difficulties they encounter during technical training. After the data was gathered, it was examined using simple statistical methods (tables and percentages) and descriptive statistics (mean and standard deviations). Inferential analysis such as regression analysis tests the relationship between the three explanatory variables and the explained variable. The study's adjusted R square yielded a result of 75.1%. 75.1% of women's entrepreneurial performance is explained by economic, sociocultural, legal, and administrative issues, while the remaining 24.9% is explained by other factors that are not the focus of this study. The key economic issues that affected how well women entrepreneurs performed in micro and small businesses were their lack of company space (land), financial access from microfinance or other lending institutions, poor access to business training, fierce market rivalry, access to technology, and availability of raw materials. Conflicting gender roles or domestic responsibilities, networks with outsiders, and social acceptability are the main social elements that have an impact on these entrepreneurs, according to the study. According to the researcher, wereda 10 in the Lideta sub-city has a minimal socio-cultural influence, but there are still significant economic and administrative difficulties. Keywords: Factors, performance, women entrepreneurs, micro and small enterprises, Impact, major, characteristics, Factors affecting. DOI: 10.7176/JESD/13-21-01 Publication date: November 30 th 2022

A review of microfinance and women empowerment in Ethiopia

Microfinance has a positive impact on the living standard of the poor people in particular and alleviates poverty in their households in general. It is not only undermining poverty in the city but also empowering women through surviving and making their life prosperous with dignity and self-reliance by providing financial services. This study aims to provide information for a better understanding of the constraints of women to access microfinance institutions (MFIs) in Ethiopia and establishes a knowledge base that helps to make a sound decision by providing information for policymakers and identifying research gaps, MFIs, and other lending institutions, and stakeholders. The study uses the literature review methods. From the findings of the study, Ethiopian Microfinance is facing different challenges in empowerment such as lack of collateral assets, lack of information, work burden, production failures, verbal abuse, lack of infrastructure and low institutional capacity. Keywords: Collateral, empowering women, microfinance, poverty eradication

An Innovative Framework for Integrated Loan Management with QR Code Enhancement

This research paper aims at design of an innovative framework scalable and integrated loan management with Quick Response Code enhancement, which will guarantee easy and better-secured loan validation and processing in microfinance banks and other lending institutions. As the number of microfinance bank customers in need of personal loans rises on a daily basis, especially in the post COVID-19 era, management is faced with the complex job of loan application verification in order to correctly determine eligibility for a loan. There is the challenge of coping with fraudulent customers who make false claims with their loan application documentations, sometimes seeking to access multiple loans from more than one microfinance banks and using single collateral security. There is need for a central regulatory agency that links up major lending institutions in a collaborative effort to forestall incidences of multiple loan access using single loan security. Our new model will also forestall activities of some fraudulent bank officials who go as far as granting credit facilities to their friends and family members without following due process and using their privileged positions to obtain unsecured loans for themselves and their relations, sometimes in excess of bank’s statutory lending limits, and in total violation of the provisions of policy of microfinance banking sector. Our new model was designed using the Rapid Application Development (RAD) methodology following its high involvement and concentration on user’s viewpoint as well as its ability to change system design on the go based on user demands. Implementation of the new system was done using such development tools as PHP, JavaScript, MySQL, and Visual Studio. Basic functionality testing was carried out on the system to make sure all the buttons on every screen works as desired, and to ascertain that the system could forestallincidences of “insider abuse” and that loan approvals are done according to internal and external regulations.

Which Curve Fits Best: Fitting ROC Curve Models to Empirical Credit-Scoring Data

In the practice of credit-risk management, the models for receiver operating characteristic (ROC) curves are helpful in describing the shape of an ROC curve, estimating the discriminatory power of a scorecard, and generating ROC curves without underlying data. The primary purpose of this study is to review the ROC curve models proposed in the literature, primarily in biostatistics, and to fit them to actual credit-scoring ROC data in order to determine which models could be used in credit-risk-management practice. We list several theoretical models for an ROC curve and describe them in the credit-scoring context. The model list includes the binormal, bigamma, bibeta, bilogistic, power, and bifractal curves. The models are then tested against empirical credit-scoring ROC data from publicly available presentations and papers, as well as from European retail lending institutions. Except for the power curve, all the presented models fit the data quite well. However, based on the results and other favourable properties, it is suggested that the binormal curve is the preferred choice for modelling credit-scoring ROC curves.

Prediction of Car Loan Default Results Based on Multi Model Fusion

With the prosperity and development of the asset management industry and various financial derivatives, many micro-loans and online loans have gradually entered the public view. How to predict the default probability of customer loans is a hot topic in the market. Therefore, in this paper, by collecting the data profile of more than 10 thousand car loan borrowers and fitting the fusion model of 4 methods: logistic model, decision model, Random Forest, and KNN model to the data, the author examines the behavioral data of borrowers to predict whether the borrowers will default in the future and find the best threshold to reach the lowest cost. The findings indicate that our final prediction can reduce costs by 38.9%. The excellent result shows that this model can be applied to the real market to help lending institutions predict default results and formulate strategies to avoid default risks in the process of borrowers' evaluation according to the model coefficient.

Online Loan Default Prediction Model Based on Deep Learning Neural Network.

With the rapid development of Internet loans and the demand for Internet loans, Internet-based loan default prediction is particularly important. P2P online lending is based on Internet technology. With the popularization of personal PCs and mobile terminals, the borrower's financing cost has been reduced to a large extent, and the efficiency of the borrower's capital utilization has also been improved to a considerable level. Making full use of the existing data of the online lending platform, integrating third-party data, and predicting the default behavior of users are the major directions of future development. This paper mainly studies the network loan default prediction model based on DPNN. This paper first analyzes the problems and risks of the P2P online lending platform, then introduces the principle and characteristics of BPNN in detail, and determines the credit risk rating process for online lending based on BPNN. With the help of data analysis and processing software, after cleaning and variable selection of credit customer data provided by lending clubs, a set of corresponding online lending default risk assessment models are established through BPNN. This paper simulates the network loan default assessment model of the BPNN model and compares it with the support vector machine and regression model. The experimental results show that the highest accuracy rate of the BPNN model is 98.01% and the highest recall rate is 99.82%, which is better than the other two models; the AUC value of BPNN is 0.79, which is significantly higher than that of support vector machine and regression model. The above results show that the online loan default prediction model based on DPNN has high application value in practice. Predicting the probability of customer default risk in advance will help reduce the risk of P2P companies and lenders, improve the competitiveness of P2P lending institutions, and promote the development of domestic P2P platforms to be more stable.

Tackling the Global Environmental Problem of Climate Change through COVID-19 Economic Recovery Stimulus Packages: Some Suggested Legal Strategies

The effects of the COVID-19 are both immediate and dreadful. But another profound emergency is the planet's unfolding environmental crisis of climate change. Climate change disruption is getting to the point of no return. We must act decisively to protect our planet from both the COVID-19 and the existential problem of climate interruption. We need to turn the COVID-19 economic recovery process into a real opportunity to do things right for the future. The economic and social devastation caused by climate disruption will be many times greater than the current COVID-19 pandemic. COVID-19 pandemic-which is resulting in significant economic and political shifts worldwide, should be the international community's unique window of opportunity in which recovery plans can be instrumental in creating a more sustainable and resilient future through ambitious climate mitigation, adaptation, and financing aimed at building back better. This article, which adopted the doctrinal research methodology, examines how the global environmental problem of climate change can be tackled through COVID-19 economic recovery stimulus packages. The paper finds that focusing COVID-19 economic recovery stimulus packages on greener economy, renewable energies, circular economy, and reforestation can help tackle the global environmental problem of climate change. Further, the paper finds that there is a need for legal frameworks that guarantee investments in the suggested strategic areas taking insights from the European Commission Green Deal policy framework. This paper recommends that national governments and international financial lending institutions should focus their COVID-19 economic recovery stimulus packages on investments that tackle the global environmental problem of climate change. Keywords: Global environmental problem, climate change, COVID-19, economic recovery, stimulus packages, legal strategies, European Commission Green Deal DOI: 10.7176/JLPG/123-06 Publication date: August 31 st 2022