Who cares about your Facebook friends? Credit scoring for microfinance

Microfinance has known a large increase in popularity, yet the scoring of such credit still remains a difficult challenge. In general, retail credit scoring uses socio-demographic and credit data. We complement such data with social network data in an innovative manner i.e. with fine-grained interest and social network data from Facebook. Using a unique dataset of 4,985 microfinance loans from the Philippines, we show how the different data types can predict creditworthiness. A distinction is made between the relationships that the available data imply: (1) look-a-likes are persons who resemble one another in some manner, be it liking the same pages, having the same education, etc. (2) friends have a clearly articulated friendship relationship on Facebook, and finally (3) the \Best Friends Forever" (BFFs) are friends that interact with one another. Our analyses show two interesting conclusions for this emerging application. Firstly, applying relational learners on BFF data yields better results than considering only the friends data. Secondly, the interest-based data that defines look-a-likes, is more predictive than the friendship or BFF data. Moreover, the model built on interest data is not significantly worse than the model that uses all available data, including the friendship data. Hence begging the question: who cares about your Facebook friends when your interest data is available?

[1]  Bart Baesens,et al.  Social network analysis for customer churn prediction , 2014, Appl. Soft Comput..

[2]  Alan Murray,et al.  Finding Similar Mobile Consumers with a Privacy-Friendly Geosocial Design , 2015, Inf. Syst. Res..

[3]  Chrysanthos Dellarocas,et al.  Credit Scoring with Social Network Data , 2014 .

[4]  David Martens,et al.  Wallenius Naive Bayes , 2013 .

[5]  Jonathan Crook,et al.  Sample selection bias in credit scoring models , 2003, J. Oper. Res. Soc..

[6]  Ahmet Burak Emel,et al.  A credit scoring approach for the commercial banking sector , 2003 .

[7]  Foster Provost,et al.  A Simple Relational Classifier , 2003 .

[8]  J. Copestake.  Mainstreaming Microfinance: Social Performance Management or Mission Drift? , 2007 .

[9]  Lise Getoor,et al.  Link-Based Classification , 2003, Encyclopedia of Machine Learning and Data Mining.

[10]  Foster J. Provost,et al.  Explaining Data-Driven Document Classifications , 2013, MIS Q..

[11]  N. Hermes,et al.  The Empirics of Microfinance: What Do We Know? , 2007 .

[12]  Bart Baesens,et al.  Comprehensible Credit Scoring Models Using Rule Extraction from Support Vector Machines , 2007, Eur. J. Oper. Res..

[13]  J. Morduch.  The microfinance promise , 1999 .

[14]  Chris Volinsky,et al.  Network-Based Marketing: Identifying Likely Adopters Via Consumer Networks , 2006, math/0606278.

[15]  David Martens,et al.  Pseudo-Social Network Targeting from Consumer Transaction Data , 2011 .

[16]  Hua Li,et al.  Demographic prediction based on user's browsing behavior , 2007, WWW '07.

[17]  David Martens,et al.  Including high-cardinality attributes in predictive models: A case study in churn prediction in the energy sector , 2015, Decis. Support Syst..

[18]  Foster J. Provost,et al.  Design principles of massive, robust prediction systems , 2012, KDD.

[19]  Manfred Zeller,et al.  Repayment performance in group-based credit programs in Bangladesh , 1997 .

[20]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[21]  Sharad Goel,et al.  Who Does What on the Web: A Large-Scale Study of Browsing Behavior , 2012, ICWSM.

[22]  David J. Hand,et al.  Optimal bipartite scorecards , 2005, Expert Syst. Appl..

[23]  Chulwoo Jeong,et al.  A binary classification method for bankruptcy prediction , 2009, Expert Syst. Appl..

[24]  T. Graepel,et al.  Private traits and attributes are predictable from digital records of human behavior , 2013, Proceedings of the National Academy of Sciences.

[25]  David Martens,et al.  DEPARTMENT OF ENGINEERING MANAGEMENT Classification over bipartite graphs through projection , 2015 .

[26]  Lars Backstrom,et al.  The Anatomy of the Facebook Social Graph , 2011, ArXiv.

[27]  Manfred Zeller,et al.  Determinants of Repayment Performance in Credit Groups: The Role of Program Design, Intragroup Risk Pooling, and Social Cohesion , 1998, Economic Development and Cultural Change.

[28]  Mark Schreiner,et al.  Scoring : the next breakthrough in microcredit ? , 2003 .

[29]  Bart Baesens,et al.  Credit scoring for microfinance: is it worth it? , 2012 .

[30]  Pedro M. Domingos.  Mining Social Networks for Viral Marketing , 2022 .

[31]  R. Putnam.  Bowling Alone: America's Declining Social Capital , 1995, The City Reader.

[32]  Venkata Rama Kiran Garimella,et al.  Inferring audience partisanship for YouTube videos , 2013, WWW '13 Companion.