Abstract
Credit risk assessment is the most challenging issue in banks as bad loans apart from reducing profitability also possess risk to the economic growth. Traditional assessment models consider the static and demographic data to predict the likelihood of customer turning to bad debtors. This paper proposes a novel fog assisted IoT based three- tier framework for credit risk assessment that can be deployed for evaluating the risk of both existing borrowers and new applicants. The RFM (Recenecy, Frequency, Monetary) and behavioral data are captured through User Device layer. Real time behaviour score of existing borrowers is computed to find cluster of risky clients who are indulged in hefty spending and possess an unfavorable behaviour. Fog layer sends alert messages to high risky borrowers as well as to the dealing officers in banks. ASW (Average Silhouette Width) metric is utilized to assess quality of clusters. At the cloud layer, heat map analysis is performed to find risky geographical areas where majority of existing borrowers are prone to overspending propensity. The identified (risky/non-risky) region codes are augmented to the demographic details of new loan applicants to classify them as potential High risky/Moderate Risky/Low risky/No Risk. Experimental results reveal that the inclusion of region code enhances accuracy from 0.8867 to 0.9244. AUC (Area under curve) and other vital statistical measures are also elevated. Additionally, Gini Coefficient has been computed for measuring region wise disparity in income and expenditure.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abedinia O, Zareinejad M, Doranehgard MH, Fathi G, Ghadimi N (2019) Optimal offering and bidding strategies of renewable energy based large consumer using a novel hybrid robust-stochastic approach. J Clean Prod 215:878–889. https://doi.org/10.1016/j.jclepro.2019.01.085
Albuquerque P, Medina F, Silva A (2017) Geographically weighted logistic regression applied to credit scoring models*. Revista Contabilidade & Finanças. 28(73):93. https://doi.org/10.1590/1808-057x201703760
Alexiou A(2017) Putting ‘Geo’ into geodemographics: evaluating the performance of national classification systems within regional contexts. Ph.D. Thesis, University of Liverpool, Liverpool, UK
Anitha P, Patil MM (2019) RFM model for customer purchase using K-Means algorithm. J King Saud Univ. https://doi.org/10.1016/j.jksuci.2019.12.011
Arora N, Kaur PD (2020) A Bolasso based consistent feature selection enabled random forest classification algorithm: an application to credit risk assessment. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2019.105936
Ashby DI, Longley PA (2005) Geocomputation, geodemographics and resource allocation for local policing. Trans GIS 9:53–72
Bekhet HA, Eletter SFK (2014) Credit risk assessment model for Jordanian commercial banks: Neural scoring approach. Review of Development Finance 4(1):20–28. https://doi.org/10.1016/j.rdf.2014.03.002
Bellavista P, Berrocal J, Corradi A, Das SK, Foschini L, Zanni A (2019) A survey on fog computing for the Internet of Things. Pervasive Mob Comput 52:71–99. https://doi.org/10.1016/j.pmcj.2018.12.007
Bennouna G, Tkiouat M (2019) Scoring in microfinance: credit risk management tool –Case of Morocco-. Procedia Computer Science 148:522–531. https://doi.org/10.1016/j.procs.2019.01.025
Berkhin P (2006) A survey of clustering data mining techniques. In: Kogan J, Nicholas C, Teboulle M (eds) Grouping multidimensional data. Springer, Berlin, Heidelberg
Bhandari V (2020) https://qz.com/india/1819624/yes-bank-crisis-will-take-a-toll-on-indian-banking-economy/ Accessed 22 Dec 2021
Burns L, See L, Heppenstall A et al (2018) Developing an individual-level geodemographic classification. Appl Spatial Analysis 11:417–437. https://doi.org/10.1007/s12061-017-9233-7
Cabigiosu A (2020) An Overview of the luxury fashion industry. Digitalization in the Luxury Fashion Industry. Palgrave Advances in Luxury. Palgrave Macmillan, Cham
Cao H, Wachowicz M (2019) The design of an IoT-GIS platform for performing auto-mated analytical tasks.Computers. Environ Urban Syst 74:23–40
Chauhan V, Patel M, Tanwar S, Tyagi S, Kumar N (2020) IoT Enabled real-Time urban transport management system. Comput Electr Eng 86:106746. https://doi.org/10.1016/j.compeleceng.2020.106746
Cheng CH, Chen YS (2009) Classifying the segmentation of customer value via RFM model and RS theory. Expert Syst Appl 36(3):4176–4184. https://doi.org/10.1016/j.eswa.2008.04.003
Chiappero-Martinetti E (2014) Basic needs. In: Michalos AC (ed) Encyclopedia of quality of life and well-being research. Springer, Dordrecht
Costa P (2016). IoT for Efficient Data Collection from Real World Resources. In : FCT: DEE - Dissertações de Mestrado.Universidade Nova de Lisboa http://hdl.handle.net/10362/21531
Destek MA, Koksel B (2019) Income inequality and financial crises: evidence from the bootstrap rolling window. Financ Innov. https://doi.org/10.1186/s40854-019-0136-2
Dhanda SS, Singh B, Jindal P (2020) Lightweight cryptography: a solution to secure IoT. Wireless Pers Commun 112:1947–1980. https://doi.org/10.1007/s11277-020-07134-3
DiNardo J, Justin LT (2001) Nonparametric density and regression estimation. J Econ Persp 15(4):11–28
Djeundje VB, Crook J, Calabrese R, Hamid M (2020) Enhancing credit scoring with alternative data. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2020.113766
Dong X, Suhara Y, Bozkaya B, Singh VK, Lepri B, Pentland AS (2017) Social bridges in urban purchase behaviour. ACM Trans Intell Syst Technol 9(3):33. https://doi.org/10.1145/3149409
ESRI (2012) ArcGIS Release 10.1. Redlands, CA
Fernandes GB, Artes R (2015) Spatial dependence in credit risk and its improvement in credit scoring. Eur J Oper Res. https://doi.org/10.1016/j.ejor.2015.07.013
Flores FP (2017) v1.Fillipino family income and expenditure. https://www.kaggle.com/grosvenpaul/family-income-and-expenditure. Accessed 26 Dec 2021
Gao W, Darvishan A, Toghani M, Mohammadi M, Abedinia O, Ghadimi N (2019) Different states of multi-block based forecast engine for price and load prediction. Int J Electric Power Energy Syst 104:423–435
García F, Giménez V, Guijarro F (2013) Credit risk management: A multicriteria approach to assess creditworthiness. Math Comput Model 57(7–8):2009–2015. https://doi.org/10.1016/j.mcm.2012.03.005
Ghadimi N, Akbarimajd A, Shayeghi H, Abedinia O (2018) Two stage forecast engine with feature selection technique and improved meta-heuristic algorithm for electricity load forecasting. Energy 161:130–142. https://doi.org/10.1016/j.energy.2018.07.088
Grubesic TH, Miller JA, Murray AT (2014) Geospatial and geodemographic insights for diabetes in the United States. Appl Geograph 55:117–126. https://doi.org/10.1016/j.apgeog.2014.08.017
Hernández E, Hernández G, Gil AB, Rodríguez S, Corchado JM (2019) Fog computing architecture for personalized recommendation of banking products. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2019.112900
Hsieh NC (2004) An integrated data mining and behavioral scoring model for analyzing bank customers. Expert Syst Appl 27(4):623–633. https://doi.org/10.1016/j.eswa.2004.06.007
Huang JJ, Tzeng GH, Ong CS (2007) Marketing segmentation using support vector clustering. Expert Syst Appl 32(2):313–317. https://doi.org/10.1016/j.eswa.2005.11.028
Hughes AM (1994) Strategic database marketing. Porbus, Chicago
Kalmijn W (2014) Gini Coefficient. In: Michalos AC (ed) Encyclopedia of quality of life and well-being research. Springer, Dordrecht
Kaur J, Agrawal A, Khan RA (2020) Security issues in fog environment: a systematic literature review. Int J Wireless Inf Networks. https://doi.org/10.1007/s10776-020-00491-7
Kao LJ, Chiu CC, Chiu FY (2012) A Bayesian latent variable model with classification and regression tree approach for behaviour and credit scoring. Knowl-Based Syst 36:245–252. https://doi.org/10.1016/j.knosys.2012.07.004
Kennedy K, Namee BM, Delany SJ, Sullivan MO, Watson N (2013) A window of opportunity: assessing behavioral scoring. Expert Syst Appl 40(4):1372–1380. https://doi.org/10.1016/j.eswa.2012.08.052
Khodaei H, Hajiali M, Darvishan A, Sepehr M, Ghadimi N (2018) Fuzzy-based heat and power hub models for cost-emission operation of an industrial consumer using compromise programming. Appl Thermal Eng 137:395–405. https://doi.org/10.1016/j.applthermaleng.2018.04.008
Lappas PZ, Yannacopoulos AN (2021) A machine learning approach combining expert knowledge with genetic algorithms in feature selection for credit risk assessment. Appl Soft Comput 107:107391. https://doi.org/10.1016/j.asoc.2021.107391
Leung A, Yen BTH, Lohmann G (2016) Why passengers’ geo-demographic characteristics matter to airport marketing. J Travel Tour Mark 34:833–850
Leventhal B (2016) Geodemographics for marketers. Kogan, London
Mahajan P, Kaur PD (2020) Three-tier IoT-edge-cloud (3T-IEC) architectural paradigm for real-time event recommendation in event-based social networks. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02202-9
Mills JA, Zandvakili A (1997) Statistical inference via bootstrapping for measures of inequality. J Appl Economet 12:133–150
Moon G, Twigg L, Jones K, Aitken G, Taylor J (2018) The utility of geodemographic indicators in small area estimates of limiting long-term illness. Soc Sci Med. https://doi.org/10.1016/j.socscimed.2018.06.029
Mouradian C, Naboulsi D, Yangui S, Glitho RH, Morrow MJ, Polakos PA (2018) A comprehensive survey on fog computing: state-of-the-art and research challenges. IEEE Comm Surveys & Tutorials 20(1):416–464. https://doi.org/10.1109/comst.2017.2771153
Nétek R, Pour T, Slezakova R (2018) Implementation of Heat maps in geographical information system—exploratory study on traffic accident data. Open Geosci 10(1):367–384
Ning Z, Huang J, Wang X (2019) Vehicular fog computing: enabling real-time traffic management for smart cities. IEEE Wirel Commun 26(1):87–93. https://doi.org/10.1109/mwc.2019.1700441
O’Donovan P, Gallagher C, Bruton K, O’Sullivan DT (2018) A fog computing industrial cyber-physical system for embedded low-latency machine learning industry 4.0 ap-plications. Manuf Lett 15:139–142. https://doi.org/10.1016/j.mfglet.2018.01.005
Ojo AA (2011) Geodemographic classification systems for the developing world : the case of Nigeria and the Philippines. PhD thesis, University of Sheffield
Oreski S, Oreski G (2013) Genetic Algorithm based heuristic for feature selection in credit risk assessment. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2013.09.004
Óskarsdóttir M, Bravo C, Sarraute C, Vanthienen J, Baesens B (2019) The value of big data for credit scoring: enhancing financial inclusion using mobile phone data and social network analytics. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2018.10.004
Patil C, Baidari I (2019) Estimating the optimal number of clusters k in a dataset using data depth. Data Sci Eng 4:132–140. https://doi.org/10.1007/s41019-019-0091-y
Petersen J, Gibin M, Longley P et al (2011) Geodemographics as a tool for targeting neighbourhoods in public health campaigns. J Geogr Syst 13:173–192. https://doi.org/10.1007/s10109-010-0113-9
RBI Reports (2019) Benchmarking India’s Payment system. Reserve Bank Of India Reports https://m.rbi.org.in/Scripts/PublicationReportDetails.aspx?UrlPage=&ID=923. Accessed 26 Dec 2021
Sadri AA, Rahmani AM, Saberikamarposhti M, Hosseinzadeh M (2021) Fog data management: a vision, challenges, and future directions. J Netw Comput Appl 174:102882. https://doi.org/10.1016/j.jnca.2020.102882
Saeedi M, Moradi M, Hosseini M, Emamifar A, Ghadimi N (2018) Robust optimization based optimal chiller loading under cooling demand uncertainty. Appl Therm Eng 148:1081–1091. https://doi.org/10.1016/j.applthermaleng.2018.11.122
Shahapure KR, Nicholas C (2020) Cluster quality analysis using silhouette score. In: 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), pp 747–748 https://doi.org/10.1109/DSAA49011.2020.00096
Signorell A et al (2020) DescTools: Tools for descriptive statistics. R package version 0.99.34
Silverman BW (1986) Density estimation for statistics and data analysis. Chapman and Hall, London
Singh VK, Bozkaya B, Pentland A (2015) Money walks: implicit mobility behaviour and financial well-being. PLoS ONE 10(8):0136628. https://doi.org/10.1371/journal.pone.0136628
Singleton AD (2010) The geodemographics of educational progression and their implications for widening participation in higher education. Environ Plann A 42:2560–2580
Singleton A, Alexiou A, Savani R (2020) Mapping the geodemographics of digital inequality in Great Britain: an integration of machine learning into small area estimation. Comput Environ Urban Syst 82:101486. https://doi.org/10.1016/j.compenvurbsys.2020.101486
Stine R (2011) Spatial temporal models for retail credit. In: Credit Scoring and Credit Control Conference 2011, Edinburgh, UK
Sood SK, Mahajan I (2018) A fog-based healthcare framework for Chikungunya. IEEE Internet Things J 5(2):794–801. https://doi.org/10.1109/jiot.2017.2768407
Tawalbeh L, Muheidat F, Tawalbeh M, Quwaider M (2020) IoT privacy and security: challenges and solutions. Appl Sci 10(12):4102. https://doi.org/10.3390/app10124102
Thomas LC, Ho J, Scherer WT (2001) Time will tell: behavioral scoring and the dynamics of consumer credit assessment. IMA J Manag Math 12(1):89–103. https://doi.org/10.1093/imaman/12.1.89
Tomasi LD(2019) v1. Income classification https://www.kaggle.com/lodetomasi1995/income-classification/data. Accessed 26 Dec 2021
Verma P, Sood SK (2018) Fog assisted-IoT enabled patient health monitoring in smart homes. IEEE Internet Things J 5(3):1789–1796. https://doi.org/10.1109/jiot.2018.2803201
Vlasselaer VV, Bravo C, Caelen O, Eliassi-Rad T, Akoglu L, Snoeck M, Baesens B (2015) APATE: a novel approach for automated credit card transaction fraud detection using network-based extensions. Decision Support Syst 75:38–48. https://doi.org/10.1016/j.dss.2015.04.013
Wagner J, Neitzke-Spruill L, O’Connell D, Highberger J, Martin S, Walker R, Anderson TL (2018) Understanding geographic and neighborhood variations in overdose death rates. J Community Health. https://doi.org/10.1007/s10900-018-0583-0
Walker KE, Crotty SM (2015) Classifying high-prevalence neighborhoods for cardiovascular disease in Texas. Appl Geogr 57:22–31. https://doi.org/10.1016/j.apgeog.2014.11.011
Wang D, Zhang Z, Bai R, Mao Y (2018a) A hybrid system with filter approach and multiple population genetic algorithm for feature selection in credit scoring. J Comput Appl Math 329:307–321. https://doi.org/10.1016/j.cam.2017.04.036
Wang Z, Jiang C, Ding Y, Lyu X, Liu Y (2018b) A Novel behavioral scoring model for estimating probability of default over time in peer-to-peer lending. Electron Commer Res Appl 27:74–82. https://doi.org/10.1016/j.elerap.2017.12.006
Willis I, Gibin M, Barros J, Webber R (2014) Applying neighbourhood classification systems to natural hazards: a case study of Mt Vesuvius. Nat Hazards 70:1–22
Win S (2018) What are the possible future research directions for bank’s credit risk assessment research? A systematic review of literature. Int Econ Econ Policy 15:743–759. https://doi.org/10.1007/s10368-018-0412-z
Yousefpour A, Fung C, Nguyen T, Kadiyala K, Jalali F, Niakanlahiji A, Jue JP (2019) All one needs to know about fog computing and related edge computing paradigms. J Syst Architect. https://doi.org/10.1016/j.sysarc.2019.02.009
Zhang T, Zhang W, Xu W, Hao H (2018) Multiple instance learning for credit risk assessment with transaction data. Knowledge-Based Syst. https://doi.org/10.1016/j.knosys.2018.07.030
Zhou Y, Uddin MS, Habib T, Chi G, Yuan K (2021) Feature selection in credit risk modeling: an international evidence. Econ Res. https://doi.org/10.1080/1331677x.2020.1867
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Arora, N., Kaur, P.D. GeoCredit: a novel fog assisted IoT based framework for credit risk assessment with behaviour scoring and geodemographic analysis. J Ambient Intell Human Comput 14, 10363–10387 (2023). https://doi.org/10.1007/s12652-022-03695-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-022-03695-2