Spatiotemporal Integration of Mobile, Satellite, and Public Geospatial Data for Enhanced Credit Scoring

Abstract

Credit scoring of financially excluded persons is challenging for financial institutions because of a lack of financial data and long physical distances, which hamper data collection. The remote collection of alternative data has the potential to overcome these challenges, enabling credit access for such individuals. Whereas alternative data sources such as mobile phones have been investigated by previous researchers, this research proposes the integration of mobile-phone, satellite, and public geospatial data to improve credit evaluations where financial data are lacking. An approach to integrating these disparate data sources involving both spatial and temporal analysis methods such as spatial aggregation was employed, resulting in various data combinations. The resulting data sets were used to train classifiers of varying complexity, from logistic regression to ensemble learning. Comparisons were based on various performance metrics, including accuracy and the area under the receiver operating-characteristic curve. The combination of all three data sources performed significantly better than mobile-phone data, with the mean classifier accuracy and F1 score improving by 18% and 0.149, respectively. It is shown how these improvements can translate to cost savings for financial institutions through a reduction in misclassification errors. Alternative data combined in this manner could enhance credit provision to financially excluded persons while managing associated risks, leading to greater financial inclusion.

Psychometric profiling of individuals using Twitter profiles: A psychological Natural Language Processing based approach

“…Advancements in Artificial Intelligence and Machine Learning have enabled scoring algorithms to work with nonfinancial data such as digital footprints from mobile devices and psychometric data to compute credit scores. [23][24][25] A considerable amount of evidence has mounted with regard to the potential for financial inclusion for these sources of data. [26][27][28] Psychometric credit scoring provides a worthy alternative to these thin-filed individuals.…”

“…In the above light, it becomes essential for researchers and finance industries to look for ways to expand the reach of financial inclusion. Advancements in Artificial Intelligence and Machine Learning have enabled scoring algorithms to work with nonfinancial data such as digital footprints from mobile devices and psychometric data to compute credit scores 23‐25 . A considerable amount of evidence has mounted with regard to the potential for financial inclusion for these sources of data 26‐28 .…”

On the dynamics of credit history and social interaction features, and their impact on creditworthiness assessment performance

“…Another approach to enhance the creditworthiness assessment is to include alternative data sources. More and better data leads to better decisions, and in the case of application scoring, the researchers have analyzed the contribution of alternative data sources such as satellite and geospatial data (Simumba et al, 2021), psychometric data (Djeundje et al, 2021;Rabecca et al, 2018;Shoham, 2004), mobile phone data and communication networks ( Óskarsdóttir et al, 2018; Óskarsdóttir et al, 2019), network data (Cnudde et al, 2019;Freedman and Jin, 2017;Giudici et al, 2020;Masyutin, 2015;Wei et al, 2016), and written risk assessments (Stevenson et al, 2021). These studies have in common that most of the increase in creditworthiness assessment performance occurs when applicant traditional information is scarce or non-available.…”