Urban Lens

Predicting socio-economic indices from big data of individual bank card's transaction

scr
About the app: Overview

The web application enables a comparative exploration of the statistical characteristics of Spanish provinces together with the indicators developed by Urban Lens methodology. The indicators are categorized by attributes, such as ‘Business Oriented’, ‘Customer Oriented’, and ‘Categories of Spending’.

scr
About the app: Comparison Mode

Each collection of indicators is visualized as a radial plot on the right. Users can select a province of their interest in the map. When more that two provinces are selected, their commercial activities can be easily compared.

scr
About the app: Density Map Mode

This mode is about spatial distribution of the selected indicator as a density map.
When an indicator is selected, the normalized data of it is shown on the map and visualized
as a bar graph on the right.

scr
About the app: Spatial Clusters Mode

Provinces are clustered in groups with respect to the similarity in their commercial activities. In the visualization on the right, it shows the overall distribution of clusters among the total of 52 provinces. Number of clusters can be selected between 2 to 9.

Description

Since the advent of pervasive digital technologies in our daily lives, people are leaving an increasing amount of digital traces. Creating data analytics and data visualization from this new layer of information sheds light on the rich insight of human behavior from the micro scale of individuals and households, that can scale up to a macro scale characterization of cities and countries.

Urban Lens explores millions of anonymized financial transactions in Spain based on data provided by BBVA, which holds a ubiquitous banking infrastructure in the country. The data provides an opportunity to uncover macro trends derived from a fine-grained scale of individual economic behavior. In light of the failure of past decades to produce models that effectively predict and explain the macroeconomic trends, we noticed that a gap exists between models of micro behaviors and macro phenomena. This project performs a comparative analysis of city microeconomics, aiming to elucidate how bigger economic patterns could be understood utilizing data of individual economic transactions.

Researchers at the Senseable City Lab built a novel multi-scale predictive model of Spanish regions, quantifying the distinctive signature of each region based on their spending behavior by identifying indicators regarding the amount of spending, type of spending, type of individual, and individual mobility. The model was validated at the provincial scale using official performance statistics, and proved a strong correlation between individual spending behavior and official socioeconomic indices. Finally, a scale-free clustering was developed to enable a consistent aggregation of regions in different spatial dimensions.

Urban Lens holds tremendous potential in its far-reaching applicability to discover patterns that can be used in urban planning, policy-making and business decisions. The web application allows users to explore these indicators and cluster regions based on their distinctive economic signature.

Papers
Download Data

1. Sobolevsky, S., Sitko, I., Combes, R. T. D., Hawelka, B., Arias, J. M., & Ratti, C. (2015). Cities through the Prism of People's Spending Behavior. PLOS ONE, 11(2): e0146291

2. Sobolevsky, S., Sitko, I., Grauwin, S., Combes, R. T. D., Hawelka, B., Arias, J. M., & Ratti, C. (2014). Mining urban performance: Scale-independent classification of cities based on individual economic transactions. arXiv preprint arXiv:1405.4301. . Fifth ASE International Conference on Data Science in Stanford, CA, May, 2014

3. Sobolevsky, S., Sitko, I., Tachet des Combes, R., Hawelka, B., Murillo Arias, J., Ratti, C. (2014). Money on the Move: Big Data of Bank Card Transactions as the New Proxy for Human Mobility Patterns and Regional Delineation. The Case of Residents and Foreign Visitors in Spain. IEEE International Congress on Big Data, 136-143.

4. Sobolevsky, S., Bojic, I., Belyi, A., Sitko, I., Hawelka, B., Arias, J. M., & Ratti, C. (2015). Scaling of city attractiveness for foreign visitors through big data of human economic and social media activity. arXiv preprint arXiv:1504.06003. IEEE Big Data Congress’2015 in NYC

5. Sobolevsky, S., Massaro, E., Bojic, I., Arias, J. M., & Ratti, C. (2015). Predicting Regional Economic Indices Using Big Data Of Individual Bank Card Transactions. arXiv preprint arXiv:1506.00036. Sixth ASE International Conference on Data Science in Stanford, CA, August, 2015 (best paper award)

6. Dashdorj, Z., Sobolevsky, S., Serafini, L., & Ratti, C. (2014, November). Human activity recognition from spatial data sources. In Proceedings of the Third ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems (pp. 18-25). ACM.

7. Dashdorj, Z., Sobolevsky, S., Serafini, L., Antonelli, F., & Ratti, C. (2015). Semantic Enrichment of Mobile Phone Data Records Using Background Knowledge. arXiv preprint arXiv:1504.05895.

8. Yuji Yoshimura, Stanislav Sobolevsky, Juan N Bautista Hobin, Carlo Ratti (2015). Urban Association Rules: uncovering consumer behaviors in urban settings through Transaction data. Submitted to Environmental And Planning B

9. P. Thébault, D. Lee, K. Greco, S. Sobolevsky, J. Murillo Arias, A. Biderman and C. Ratti (2014). Designing real-time data browsers for the data-driven society. Submitted.

10. Bojic, I., Massaro, E., Belyi, A., Sobolevsky, S., & Ratti, C. (2015). Choosing the right home location definition method for the given dataset. In Social Informatics (pp. 194-208). Springer.

11. Yoshimura, Y., Amini, A., Sobolevsky, S., Blat, J., Ratti, C. (2016). Analysis of Customers’ Spatial Distribution Through Transaction Datasets. Transactions on Large-Scale Data- and Knowledge-Centered Systems XXVII, 9860, 177-189. Springer

Download Data

Behrooz Hashemian, Emanuele Massaro, Iva Bojic, Juan Murillo-Arias, Stanislav Sobolevsky, Carlo Ratti (2017). Socioeconomic characterization of regions through the lens of individual financial transactions.

The information offered on this Website is for informational purposes and shall not be deemed in any case as recommendation, technical, financial, legal, tax, or investment advice, or an offer or a guarantee by BBVA or MIT SCL, nor should it be understood as a recommendation to trade, or constitute the basis for any decision-making. Complete Terms and Conditions available for download.

Team

MIT Senseable City Lab, USA

Carlo Ratti, Lab director
Stanislav Sobolevsky, Project lead
Behrooz Hashemian, Data analyst
Emanuele Massaro, Data analyst
Youjin Shin, App and visualization
Chaewon Ahn, Web design
Wonyoung So, Web design

BBVA data & Analytics, Spain

Juan Murillo
Marco Bressan
Elena Alfaro
Heribert Valero

A Research Project by
senseable city lab    +   


For more information please contact
senseable-bbva@mit.edu