Towards Real-Time Prediction of Unemployment and Profession

  • Pål Sundsøy
  • Johannes Bjelland
  • Bjørn-Atle Reme
  • Eaman Jahani
  • Erik Wetter
  • Linus Bengtsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10540)

Abstract

At a societal level unemployment is an important indicator of the performance of an economy and risks in financial markets. This study provides the first confirmation that individual employment status can be predicted from standard mobile phone network logs externally validated with household survey data. Individual welfare and households’ vulnerability to shocks are intimately connected to employment status and professions of household breadwinners. By deriving a broad set of novel mobile phone network indicators reflecting users’ financial, social and mobility patterns we show how machine learning models can be used to predict 18 categories of profession in a South-Asian developing country. The model predicts individual unemployment status with 70.4% accuracy. We further show how unemployment can be aggregated from individual level and mapped geographically at cell tower resolution, providing a promising approach to map labor market economic indicators, and the distribution of economic productivity and vulnerability between censuses, especially in heterogeneous urban areas. The method also provides a promising approach to support data collection on vulnerable populations, which are frequently under-represented in official surveys.

References

  1. 1.
    Lovati, J.: The unemployment rate as an economic indicator. Federal reserve bank of st.louis (1976)Google Scholar
  2. 2.
    Keynes, M.: The General Theory of Employment, Interest and Money. Palgrave Macmillan, Basingstoke, Hampshire (2009). ISBN 0-230-00476-8Google Scholar
  3. 3.
    International Labour Organization: Global Unemployment Trends. (2013)Google Scholar
  4. 4.
    Garegnani, P.: Heterogeneous capital, the production function and the theory of distribution. Rev. Econ. Stud. 37(3), 407–436 (1970)CrossRefGoogle Scholar
  5. 5.
    Faberman, D., Haltiwanger, J.: The flow approach to labor markets: new data sources and micro-macro links. J. Econ. Perspect. 20(3), 3–26 (2006)CrossRefGoogle Scholar
  6. 6.
    U.S. Bureau of Labor Statistics: How the Government Measures Unemployment. (2014)Google Scholar
  7. 7.
    International Labour Organization: World Employment Social Outlook. (2017)Google Scholar
  8. 8.
    Economy Watch: Unemployment and Poverty (2010). http://www.economywatch.com/unemployment/poverty.html
  9. 9.
    Einav, L., Levin, J.: Economics in the age of big data. Science 346(6210) (2014). DOI:10.1126/science.1243089
  10. 10.
    Lokanathan, S. Gunaratne, R.L.: Behavioral insights for development from Mobile Network Big Data: enlightening policy makers on the State of the Art (2014). http://dx.doi.org/10.2139/ssrn.2522814
  11. 11.
    Sundsøy, P.: Big Data for Social Sciences: Measuring patterns of human behavior through large-scale mobile phone data. PHD Thesis, arXiv:1702.08349 [cs.CY] (2017)
  12. 12.
    Lazer, D., Pentland, A., Adamic, L., Aral, S., Barabasi, A.L., Brewer, D., Christakis, N.: Computational social science. Science 323(5915), 721–723 (2009)CrossRefGoogle Scholar
  13. 13.
    Blumenstock, C.: Predicting poverty and wealth from mobile phone metadata. Science 350(6264), 1073–1076 (2015)CrossRefGoogle Scholar
  14. 14.
    Steele, J. E., Sundsøy, P., Pezzulo, C., Alegana, V., Bird, T., Blumenstock, J., Bjelland, J., Engø-Monsen, K., de Montjoye, Y. A., Iqbal, A., Hadiuzzaman, K., Lu, X., Wetter, E., Tatem, A., Bengtsson, L.: Mapping poverty using mobile phone and satellite data. J. R. Soc. Interface 14(127), (2017). 20160690Google Scholar
  15. 15.
    Sundsøy, P.: Mitigating the risks of financial exclusion: Predicting illiteracy with standard mobile phone logs. In: SBP-BRiMS 2017 International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (2017)Google Scholar
  16. 16.
    Deville, P., Linard, C., Martin, S., Gilbert, M., Stevens, F.R., Gaughan, A.E., Blondel, V.D., Tatem, A.J.: Dynamic population mapping using mobile phone data. In: PNAS, pp. 15888–15893 (2014). doi:10.1073/pnas.1408439111
  17. 17.
    Lu, X., Wrathall, D.J., Sundsøy, P.R., Nadiruzzaman, M., Wetter, E., Iqbal, A., Qureshi, T., Tatem, A.J., Canright, G.S., Engø-Monsen, K., Bengtsson, L.: Detecting climate adaptation with mobile network data in Bangladesh: anomalies in communication, mobility and consumption patterns during cyclone Mahasen. Clim. Change 138(3), 505–519 (2016)CrossRefGoogle Scholar
  18. 18.
    Lu, X., Wrathall, D.J., Sundsøy, P.R., Nadiruzzaman, M., Wetter, E., Iqbal, A., Qureshi, T., Tatem, A.J., Canright, G.S., Engø-Monsen, K., Bengtsson, L.: Unveiling hidden migration and mobility patterns in climate stressed regions: A longitudinal study of six million anonymous mobile phone users in Bangladesh. Glob. Environ. Change 38, 1–7 (2016)CrossRefGoogle Scholar
  19. 19.
    Wesolowski, A., Qureshi, T., Boni, M.F., Sundsøy, P.R., Johansson, M.A., Rasheed, S.B., Engø-Monsen, K., Buckee, C.O.: Impact of human mobility on the emergence of dengue epidemics in Pakistan. Proc. Nat. Acad. Sci. 112(38), 11887–11892 (2015)CrossRefGoogle Scholar
  20. 20.
    Guitierrrez, Krings, Blondel: Evaluating socio-economic state of a country analyzing airtime credit and mobile phone datasets. arXiv preprint arXiv:1309.4496 (2013)
  21. 21.
    Sundsøy, P., Bjelland, J., Reme, B., Iqbal, A., Jahani, E.: Deep learning applied to mobile phone data for Individual income classification. In: ICAITA 2016 International Conference on Artificial Intelligence and applications (2016)Google Scholar
  22. 22.
    Felbo, B., Pentland, S., Sundsøy, P., Montjoye, Y., Lehmann, S.: Using Deep Learning to predict demographics from mobile phone metadata. arXiv:1511.06660v4 (2016)
  23. 23.
    Jahani, E., Sundsøy, P., Bjelland, J., Pentland, A., Bengtsson, L.M.: Improving official statistics in emerging markets using machine learning and mobile phone data. EPJ Data Sci. 6(1), 3 (2017)CrossRefGoogle Scholar
  24. 24.
    Montjoye, Y.-A., Quoidbach, J., Robic, F., Pentland, A(.: Predicting Personality Using Novel Mobile Phone-Based Metrics. In: Greenberg, Ariel M., Kennedy, William G., Bos, Nathan D. (eds.) SBP 2013. LNCS, vol. 7812, pp. 48–55. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37210-0_6 CrossRefGoogle Scholar
  25. 25.
    Sundsøy, P., Bjelland, J., Iqbal, A.M., de Montjoye, Y.A.: Big data-driven marketing: how machine learning outperforms marketers’ gut-feeling. In: International Conference on Social Computing, Behavioral-Cultural Modeling, and Prediction, pp. 367–374 (2014)Google Scholar
  26. 26.
    Toole, J., Lin, Y.-r., Muehlegger, E., Shoag, D., Gonzalez, M., Lazer, D.: Tracking employment shocks using mobile phone data. J. R. Soc. Interface 12(107) (2015)Google Scholar
  27. 27.
    Almaatouq, A., Prieto-Castrillo, F., Pentland, A.: Mobile communication signatures of unemployment. In: International Conference on Social Informatics, pp. 407–418 (2016)Google Scholar
  28. 28.
    Dahl, G.: Improving Deep Neural Networks for LVCSR using Rectified Linear Units and Dropout. In: ICASSP, pp. 8609–8613 (2013)Google Scholar
  29. 29.
    Koyejo, O.: Consistent Binary Classification with Generalized Performance Metrics. NIPS (2014)Google Scholar
  30. 30.
    Gedeon, T.: Data Mining of inputs: analysing magnitude and functional measures. Int. J. Neural Syst. 8(2), 209–218 (1997)CrossRefGoogle Scholar
  31. 31.
    OECD: Main Economic Indicators (2016)Google Scholar
  32. 32.
    Ciccone, A., Hall, R.: Productivity and density of economic activity. Am. Econ. Rev. 86(1), 54–70 (1996)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Pål Sundsøy
    • 1
  • Johannes Bjelland
    • 1
  • Bjørn-Atle Reme
    • 1
  • Eaman Jahani
    • 2
  • Erik Wetter
    • 3
    • 4
  • Linus Bengtsson
    • 3
    • 5
  1. 1.Telenor Group ResearchFornebuNorway
  2. 2.MIT Institute for Data, Systems and SocietyCambridgeUSA
  3. 3.Flowminder FoundationStockholmSweden
  4. 4.Stockholm School of EconomicsStockholmSweden
  5. 5.Department of Public Health SciencesKarolinska InstituteStockholmSweden

Personalised recommendations