An Alternative Credit Scoring System in China's Consumer Lending Market: A System Based on Digital Footprint Data

2020 ◽  
Author(s):  
Guanghong Fu ◽  
Minjuan Sun ◽  
Qing Xu
Keyword(s):  
Scoring System ◽  
Credit Scoring ◽  
Digital Footprint ◽  
Consumer Lending

Network-aware credit scoring system for telecom subscribers using machine learning and network analysis

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hongming Gao ◽  
Hongwei Liu ◽  
Haiying Ma ◽  
Cunjun Ye ◽  
Mingjun Zhan
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
Scoring System ◽  
Credit Scoring ◽  
Prediction Performance ◽  
Content Type ◽  
Connected Subgroup ◽  
Source Data ◽  
Credit Scores

PurposeA good decision support system for credit scoring enables telecom operators to measure the subscribers' creditworthiness in a fine-grained manner. This paper aims to propose a robust credit scoring system by leveraging latent information embedded in the telecom subscriber relation network based on multi-source data sources, including telecom inner data, online app usage, and offline consumption footprint.Design/methodology/approachRooting from network science, the relation network model and singular value decomposition are integrated to infer different subscriber subgroups. Employing the results of network inference, the paper proposed a network-aware credit scoring system to predict the continuous credit scores by implementing several state-of-art techniques, i.e. multivariate linear regression, random forest regression, support vector regression, multilayer perceptron, and a deep learning algorithm. The authors use a data set consisting of 926 users of a Chinese major telecom operator within one month of 2018 to verify the proposed approach.FindingsThe distribution of telecom subscriber relation network follows a power-law function instead of the Gaussian function previously thought. This network-aware inference divides the subscriber population into a connected subgroup and a discrete subgroup. Besides, the findings demonstrate that the network-aware decision support system achieves better and more accurate prediction performance. In particular, the results show that our approach considering stochastic equivalence reveals that the forecasting error of the connected-subgroup model is significantly reduced by 7.89–25.64% as compared to the benchmark. Deep learning performs the best which might indicate that a non-linear relationship exists between telecom subscribers' credit scores and their multi-channel behaviours.Originality/valueThis paper contributes to the existing literature on business intelligence analytics and continuous credit scoring by incorporating latent information of the relation network and external information from multi-source data (e.g. online app usage and offline consumption footprint). Also, the authors have proposed a power-law distribution-based network-aware decision support system to reinforce the prediction performance of individual telecom subscribers' credit scoring for the telecom marketing domain.

scholarly journals Мінімізація кредитних ризиків у діяльності сільських кредитних спілок із використанням систем скорингу

2015 ◽  
pp. 99-102
Author(s):  
О. В. Орлов
Keyword(s):  
Risk Assessment ◽  
Credit Risk ◽  
Scoring System ◽  
Scientific Method ◽  
Credit Scoring ◽  
Credit Unions ◽  
Single Model ◽  
Rural Credit ◽  
Effective System

У статті розглянуто проблему кредитних ризиківу роботі сільських кредитних спілок та запропонова-но ефективну систему оцінки таких ризиків з викорис-танням системи скорингу. Наведені теоретичніджерела скорингу, як наукового методу. Надані кон-кретні пропозиції щодо розвитку та застосуванняскорингу в роботі сільських кредитних спілок. Акцен-товано увагу на важливості та необхідності засто-сування зазначеного методу в практичній діяльностіданих організацій, доцільності розробки єдиної моде-лі автоматизованої системи кредитного скорингудля мінімізації кредитних ризиків в роботі сільсько-господарських кредитних спілок. The article deals with the problem of credit risk in the rural credit unions and we offer an effective system of risk assessment using the scoring system. Theoretical sources of scoring as the scientific method are adduced. Specific offers for the development and application of scoring in the rural credit unions are given. We emphasize the importance and the need to use this method in practical activities of these organizations, the feasibility of developing of a single model of an automated credit scoring system in order to minimization of credit risk in the rural credit unions.

Research on C2C Credit Evaluation Model Based on Perceived Credibility of the Buyer

2014 ◽  
Vol 687-691 ◽  
pp. 4984-4989
Author(s):  
Chen Xing Bai
Keyword(s):  
Consumer Protection ◽  
Scoring System ◽  
Evaluation Model ◽  
Credit Scoring ◽  
Credit Evaluation ◽  
Perceived Credibility ◽  
Model Based ◽  
Evaluation Time ◽  
Transaction Value

Focusing on the lack of credit scoring system and credit evaluation model, the paper builds <qualitative perception, quantitative perception> reputation tuple based on perceived credibility of the buyer. Qualitative perception is six indicators assembly, including shop image, customer communication, payment, whether to join the consumer protection service , whether to join the Commercial Union and feedback comment; Quantitative perception is three indicators assembly, including buyer credit , the transaction value of the goods and evaluation time. Through analyzing of the case, reputation tuple can be more objective, more scientific, more comprehensive response to the seller's real credibility.

Kueski: Revolutionizing Consumer Credit in Mexico

2017 ◽  
pp. 1-10
Author(s):  
Sarit Markovich ◽  
Nilima Achwal
Keyword(s):  
Financial Market ◽  
Financial Services ◽  
Scoring System ◽  
Credit Card ◽  
Consumer Credit ◽  
Credit Scoring ◽  
Loan Approval

This case asks students to step into the role of Adalberto Flores, co-founder and CEO of Kueski, one of the first companies to develop a proprietary algorithm for online loan approval in Mexico. Mexico lacks a standardized credit scoring system, making it difficult for many Mexicans to get approved for a loan or credit card. This, together with the fact that Mexicans generally do not trust traditional banks, makes Mexico an attractive opportunity for fintech companies. Growth, however, could require fintech companies to partner with traditional banks. Students assume the role of Flores to think about the benefits and risks associated with a partnership between Kueski and traditional banks. Students are also challenged to compare the structure of U.S. financial services markets with the Mexican structure and consider the implications on the sustainability of fintech companies in the two markets. The teaching note analyzes the Mexican financial market and the benefits and threats it holds for fintech companies, and outlines a framework for evaluating the risk associated with partnerships.

Survival Analysis and ROC Analysis in Analyzing Credit Risks

2018 ◽  
pp. 110-133
Author(s):  
Nan Hu ◽  
Haojie Cheng
Keyword(s):  
Competing Risks ◽  
Scoring System ◽  
Roc Analysis ◽  
Credit Scoring ◽  
Scoring Systems ◽  
Time Varying ◽  
Statistical Tool ◽  
Cross Sectional ◽  
Credit Risks ◽  
Over Time

As the aim of large banks has been changing to select customers of highest benefits, it is important for banks to know not only if but also when a customer will default. Survival analyses have been used to estimate over time risk of default or early payoff, two major risks for banks. The major benefit of this method is that it can easily handle censoring and competing risks. An ROC curve, as a statistical tool, was applied to evaluate credit scoring systems. Traditional ROC analyses allow banks to evaluate if a credit-scoring system can correctly classify customers based on their cross-sectional default status, but will fail when assessing a credit-scoring system at a series of future time points, especially when there are censorings or competing risks. The time-dependent ROC analysis was introduced by Hu and Zhou to evaluate credit-scoring systems in a time-varying fashion and it allows us to assess credit scoring systems for predicting default by any time within study periods.

scholarly journals 151. Comparing the Clinical Utility of Rapid Diagnostic Tests for Gram-Negative Bloodstream Infection Using a Desirability of Outcomes Ranking

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S102-S102
Author(s):  
Kimberly C Claeys ◽  
Kathryn Schlaffer ◽  
Zegbeh Kpadeh-Rogers ◽  
Yunyun Jiang ◽  
Scott R Evans ◽  
...  
Keyword(s):  
Clinical Outcomes ◽  
Scoring System ◽  
Clinical Utility ◽  
Medical Center ◽  
Credit Scoring ◽  
Small Sample ◽  
Clinical Microbiology Laboratory ◽  
Partial Credit ◽  
Gram Negative ◽  
Organism Identification

Abstract Background Rapid diagnostic testing (RDT) technology in bloodstream infections (BSI) has outpaced provider understanding of how to effectively use it. To optimize the use of RDT platforms and antibiotic therapy, decision makers must determine which RDTs to implement at their institutions. A thorough understanding of which platform to choose extends beyond simple analytic measures of sensitivities and specificities and should include a robust analysis of how these RDTs could impact clinical decisions. Methods Retrospective study of adult patients with Gram-negative (GN) BSI from at University of Maryland Medical Center. The clinical microbiology laboratory used Verigene® BC-GN in clinical practice. Discarded blood samples were run on BioFire® FilmArray BCID. Final organism identification/susceptibility, antibiotic exposures, and clinical outcomes were reviewed. DOOR was applied to theoretical therapy decisions based on both actual prescribing adherence to institutional algorithm recommendations; 1 being most and 6 being least desirable (Table 1). A partial credit scoring system was applied to DOOR from most (100) to least desirable (0) outcome. Comparisons were made in a paired manner. Results 77 patients met inclusion. The median age was 58 (IQR 47, 68), 44.2% were in the ICU, and 75.3% had ID consult within 24 hours of BSI. Organism identification included: E. coli (35.1%), K. pneumoniae (23.4%), P. mirabilis (10.4%), S. marcescens (10.4%), Enterobacter spp. (9.4%), P. aeruginosa (3.9%). The only resistance determinant was CTX-M (11.6%). An antibiotic change occurred in 26.2% of cases, divided between antibiotic escalation and de-escalation. Based on the actual utilization of RDT results, median DOOR was not different between BC-GN and BCID (3 [IQR 3.4] vs. 4 [IQR 3.4], P = 0.44). Using a partial credit scoring system, the mean score was not different between platforms (49.8 [SD 26.8] vs. 47.7 [SD 20.3], P = 0.44). Through pairwise comparisons, BC-GN would have resulted in an optimal outcome of 15.3% (95% CI 4.7% to 19.3%) more often than BCID. Conclusion Based on the actual use of RDTs for GN BSI there was no difference in potential clinical outcomes between platforms in this relatively small sample. DOOR is a novel mechanism to quantitate clinical utility and compare RDTs. Disclosures All authors: No reported disclosures.

Sign in / Sign up

Export Citation Format

Share Document