Estimating Probability of Default on Peer to Peer Market – Survival Analysis Approach

Đurović, Andrija

doi:10.1515/jcbtp-2017-0017

Cited by 10 publications

(8 citation statements)

References 10 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Many researchers examine the risk related to the marketplace lending (see, e.g. K€ afer, 2016;Durovi c, 2017;Lenz, 2017;Setyaningsih et al, 2019). Suryono et al (2019) mention six core problems associated to P2P lending, namely information asymmetry, determination of borrower credit scores, moral hazard, investment decisions, platform feasibility and immature regulations.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Emekter et al (2015) indicates that credit score, debt-to-income (DTI) ratio and FICO score play an important role in loan defaults. Durovi c (2017) analyzes two loan characteristics, loan term length and loan purpose and finds that longer term loans are more risky than the shorter term ones and the least risky loans are those used for credit card payoff. Polena and Regner (2018) define four loan risk classes (based on the assigned credit grade) and find that the borrower's and loan's information that identified as determinants for default in previous studies are only significant in specific loan classes.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Many researchers examine the risk related to the marketplace lending (see, e.g. Käfer, 2016; Durović, 2017; Lenz, 2017; Setyaningsih et al. , 2019).…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Factors determining default in P2P lending

Avgeri,

Psillaki

2023

JES

View full text Add to dashboard Cite

PurposeThe research documented in this paper aims to examine multiple factors related to borrowers' default in peer-to-peer (P2P) lending in the USA. This study is motivated by the hypothesis that both P2P loan characteristics and macroeconomic variables have influence on loan performance. The authors define a set of loan characteristics, borrower characteristics and macroeconomic variables that are significant in determining the probability of default and should be taken into consideration when assessing credit risk.Design/methodology/approachThe research question in this study is to find the significant explanatory variables that are essential in determining the probability of default for LendingClub loans. The empirical study is based on a total number of 1,863,491 loan records issued through LendingClub from 2007 to 2020Q3 and a logistic regression model is developed to predict loan defaults.FindingsThe results, in line with prior research, show that a number of borrower and contractual loan characteristics predict loan defaults. The innovation of this study is the introduction of specific macroeconomic indicators. The study indicates that macroeconomic variables assessed alongside loan data can significantly improve the forecasting performance of default model. The general finding demonstrates that higher percentage change in House Price Index, Consumer Sentiment Index and S&P500 Index is associated with a lower probability of delinquency. The empirical results also exhibit significant positive effect of unemployment rate and GDP growth rate on P2P loan default rates.Practical implicationsThe results have important implications for investors for whom it is of great importance to know the determinants of borrowers' creditworthiness and loan performance when estimating the investment in a certain P2P loan. In addition, the forecasting performance of the model could be applied by authorities in order to deal with the credit risk in P2P lending and to prevent the effects of increasing defaults on the economy.Originality/valueThis paper fulfills an identified need to shed light on the association between specific macroeconomic indicators and the default risk from P2P lending within an economy, while the majority of the existing literature investigate loan and borrower information to evaluate credit risk of P2P loans and predict the likelihood of default.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Factors determining default in P2P lending

Avgeri,

Psillaki

2023

JES

View full text Add to dashboard Cite

show abstract

“…El estudio, análisis y modelación del riesgo de crédito poseen importancia académica y práctica relacionada con la aplicabilidad en la búsqueda de un modelo de pronosticación de la probabilidad de incumplimiento que logre reducir el nivel de pérdida esperada en cualquier tipo de cartera correspondiente a una institución financiera. Chen et al (2016), Durovic (2017), Támara, Villegas y De Andrés (2019) y Assef y Steiner (2020) han encontrado a través de sus trabajos, que la técnica estadística más utilizada en relación al riesgo de crédito entorno a la probabilidad de incumplimiento es la regresión logística, razón por la cual en este trabajo se utiliza dicha técnica.…”

Section: Introductionunclassified

Modelación de la probabilidad de incumplimiento y cálculo de la perdida catastrófica en una institución financiera en Colombia

Ayús

Ramos

Arrieta³

2021

Revista Económicas CUC

View full text Add to dashboard Cite

La pérdida esperada en una institución financiera es el monto de capital que se perdería producto de la exposición que tienen la deuda en el tiempo. Este trabajo se enfoca en modelar la probabilidad de incumplimiento para una cartera de crédito bajo dos escenarios de estudio, uno con nivel de mora normal y otro con un nivel de mora restringido. Se toma como referencia una base de datos perteneciente a una cartera de crédito de consumo, con una muestra de 5.000 obligaciones analizadas en el período de enero a diciembre del 2019. El método estadístico utilizado es la regresión logística basado en las variables financieras de liquidez y endeudamiento, más una variable no financiera como es la edad. Los resultados muestran un modelo con un nivel de ajuste global mayor al 85% en los dos escenarios de estudio, donde, la variable ingreso es la que más influencia posee sobre el modelo de regresión logística. Finalmente, se ratifica la aplicabilidad de la regresión logística como una herramienta estadística en la búsqueda de modelos de pronosticación, con lo cual se logra reducir la perdida esperada en una cartera de crédito sin aumentar la exposición al riesgo.

show abstract

“…. (2019);Bastani et al (2019);Boiko Ferreira et al (2017);Byanjankar et al (2015);;Cai and Zhang (2020);Calabrese et al (2019);Canfield (2018);;Chen et al (2019);Chen et al (2016);Cho et al (2019);Ding et al (2017);;Durovic (2017);Emekter et al (2015);Gao et al (2017);Ge et al (2017);Giudici et al (2020);Gourieroux and Lu (2019);Guo et al (2016);Herzenstein et al (2011);Jiang et al (2018);Jiang et al (2019);; A Kim and Cho (2019)Kim and Cho (2019a);Kim and Cho (2019b);Kumar et al (2016);Li et al (2016);Li, Ding, et al (2018);Li et al (2020);Lin et al (2017);Liu et al (2018);Ma, Sha, et al (2018);Ma, Zhao, et al (2018);Malekipirbazari and Aksakalli (2015); Hadji-Misheva et al (2018); Namvar et al (2018); Nguyen Truong et al (2019); Niu et al (2019); Rodrigues et al (2018); Serrano-Cinca et al (2015); Serrano-Cinca and Gutierrez-Nieto (2016); Stofa (2017); Tan et al (2017); Tao et al (2017); Uddin et al (2018); Van-Sang et al (2019); Wang et al (2016); Wang et al (2019); Wang et al (2020); Wang, Jiang, et al (2018); Wang, Kou, et al (2018); Xia (2019); Xia et al (2017); Xia et al (2018); Xia et al (2019); Xinmin et al (2019); Xu and Chau (2018); Yang et al (2019); Ye et al (2018); Yuan et al (2018); Zang et al (2015); Zhang, Jia, et al (2016); Zhang, Wang, Chen, Shang, et al (2017); Zhang, Wang, Chen, Zhao et al, (2017); Zhou et al (2019); Zhu (2018); Zh...…”

mentioning

confidence: 99%

Risk-return modelling in the p2p lending market: Trends, gaps, recommendations and future directions

Garzón

Miñano

Vargas

et al. 2021

Electronic Commerce Research and Applications

View full text Add to dashboard Cite

The proposal for new financial products has been accompanied by new tools for risk management and profit in the Peer-to-Peer (P2P) lending market, one market in evolution, as an alternative for traditional investment and financing. For understanding this development, a systematic literature review and a bibliometric analysis of 104 papers published in the Web of Science database in the last decade are carried out using Scimat software. Our aim is to identify methodological elements, modelling components, analysis of variables and business aspects that generate opportunities for deepening its development and application. Developments of algorithms of artificial intelligence (AI) and machine learning (ML) support most of new proposals. Regulators, supervisors and users tend to increasingly seek these new alternatives in a natural project of financial digitalization demanded by technological advances, innovation and market development. Based on this study, recommendations in future research directions are provided for researchers.

show abstract

Estimating Probability of Default on Peer to Peer Market – Survival Analysis Approach

Cited by 10 publications

References 10 publications

Factors determining default in P2P lending

Factors determining default in P2P lending

Modelación de la probabilidad de incumplimiento y cálculo de la perdida catastrófica en una institución financiera en Colombia

Risk-return modelling in the p2p lending market: Trends, gaps, recommendations and future directions

Contact Info

Product

Resources

About