Mobile Money: Understanding and Predicting its Adoption and Use in a Developing Economy

Access to financial institutions is difficult in developing economies and especially for the poor. However, the widespread adoption of mobile phones has enabled the development of mobile money systems that deliver financial services through the mobile phone network. Despite the success of mobile money, there is a lack of quantitative studies that unveil which factors contribute to the adoption and sustained usage of such services. In this paper, we describe the results of a quantitative study that analyzes data from the world's leading mobile money service, M-Pesa. We analyzed millions of anonymized mobile phone communications and M-Pesa transactions in an African country. Our contributions are threefold: (1) we analyze the customers' usage of M-Pesa and report large-scale patterns of behavior; (2) we present the results of applying machine learning models to predict mobile money adoption (AUC=0.691), and mobile money spending (AUC=0.619) using multiple data sources: mobile phone data, M-Pesa agent information, the number of M-Pesa friends in the user's social network, and the characterization of the user's geographic location; (3) we discuss the most predictive features in both models and draw key implications for the design of mobile money services in a developing country. We find that the most predictive features are related to mobile phone activity, to the presence of M-Pesa users in a customer's ego-network and to mobility. We believe that our work will contribute to the understanding of the factors playing a role in the adoption and sustained usage of mobile money services in developing economies.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  Nicholas Economides,et al.  Mobile Money in Tanzania , 2015 .

[3]  Alex Pentland,et al.  Predicting Spending Behavior Using Socio-mobile Features , 2013, 2013 International Conference on Social Computing.

[4]  Gabriel Cadamuro,et al.  Predicting poverty and wealth from mobile phone metadata , 2015, Science.

[5]  Nuria Oliver,et al.  MobiScore: Towards Universal Credit Scoring from Mobile Phone Data , 2015, UMAP.

[6]  S. Lonie,et al.  M-PESA: Mobile Money for the Unbanked Turning Cellphones into 24-Hour Tellers in Kenya , 2007, Innovations: Technology, Governance, Globalization.

[7]  Kentaro Toyama,et al.  A comparison of mobile money-transfer UIs for non-literate and semi-literate users , 2009, CHI.

[8]  Alex Pentland,et al.  Composite Social Network for Predicting Mobile Apps Installation , 2011, AAAI.

[9]  Robin I. M. Dunbar,et al.  Social network size in humans , 2003, Human nature.

[10]  David L. Smith,et al.  Quantifying the Impact of Human Mobility on Malaria , 2012, Science.

[11]  Muhammad R. Khan,et al.  Predictors without Borders: Behavioral Modeling of Product Adoption in Three Developing Countries , 2016, KDD.

[12]  Petter Holme,et al.  Predictability of population displacement after the 2010 Haiti earthquake , 2012, Proceedings of the National Academy of Sciences.

[13]  Kenth Engø-Monsen,et al.  Impact of human mobility on the emergence of dengue epidemics in Pakistan , 2015, Proceedings of the National Academy of Sciences.

[14]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[15]  Britni Must,et al.  Mobile Money: Cell Phone Banking in Developing Countries , 2010 .

[16]  Tilman Ehrbeck,et al.  Financial inclusion and development : recent impact evidence , 2014 .

[17]  Robin I. M. Dunbar,et al.  The social brain hypothesis and its implications for social evolution , 2009, Annals of human biology.

[18]  Ignacio Mas,et al.  Branchless and Mobile Banking Solutions for the Poor: A Survey of the Literature , 2011, Innovations: Technology, Governance, Globalization.

[19]  Joshua Blumenstock,et al.  Determinants of Mobile Money Adoption in Pakistan , 2017 .

[20]  Thomas Lengauer,et al.  Permutation importance: a corrected feature importance measure , 2010, Bioinform..

[21]  Nathan Eagle,et al.  Mobile divides: gender, socioeconomic status, and mobile phone use in Rwanda , 2010, ICTD.

[22]  Jari Saramäki,et al.  Daily Rhythms in Mobile Telephone Communication , 2015, PloS one.

[23]  Vanessa Frías-Martínez,et al.  Forecasting socioeconomic trends with cell phone records , 2013, ACM DEV '13.

[24]  Alex Pentland,et al.  Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data , 2014, ICMI.

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

[26]  Vanessa Frías-Martínez,et al.  On the relation between socio-economic status and physical mobility , 2012, Inf. Technol. Dev..

[27]  David Pastor-Escuredo,et al.  Flooding through the lens of mobile phone activity , 2014, IEEE Global Humanitarian Technology Conference (GHTC 2014).

[28]  Nicholas A. Christakis,et al.  Social contagion theory: examining dynamic social networks and human behavior , 2011, Statistics in medicine.

[29]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[30]  William Jack,et al.  The long-run poverty and gender impacts of mobile money , 2016, Science.

[31]  Ignacio Mas,et al.  Scaling Mobile Money , 2011 .

[32]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.