Modeling Decision-Making with Intelligent Agents to Aid Rural Commuters in Developing Nations

  • Patricio Julián GerpeEmail author
  • Evangelos Markopoulos
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 965)


More than a billion rural merchants in the developing world depend on hiring on-demand transportation services to commute people or goods to markets. Selecting the optimal fare involves decision-making characterized by multiple alternatives and competing criteria. Decision support systems are used to solve this. However, those systems are based on object-based approaches which lack the high-level abstractions needed to effectively model and scale human-machine communication. This paper introduces AopifyJS, a novel agent-based decision-support tool. We developed a two-agent simulation. One agent makes a request, then another takes a dataset of a stratified sample of 104 Ethiopian commuter criteria preferences and a dataset of fare alternatives. The second agent computes HPA and TOPSIS algorithms to weight, score, rank those alternatives. Once we run the simulation, it returns an interpretable prescription to the first agent, storing all interactions in an architecture that allows developers to program further customization as interactions scale.


Agent-based modeling Agent-oriented programming Multi-criteria decision-making TOPSIS Social innovation Interpretable artificial intelligence 


  1. 1.
    Gollin, D., Rogerson, R.: Agriculture, roads, and economic development in Uganda (No. w15863). National Bureau of Economic Research (2010)Google Scholar
  2. 2.
    Wondemu, K.A., Weiss, J.: Rural roads and development: evidence from Ethiopia. Eur. J. Transp. Infrastruct. Res. 12(4), 417–439 (2012)Google Scholar
  3. 3.
    Roberts, P., Kc, S., Rastogi, C.: Rural Access Index: A Key Development Indicator. World Bank, Washington, DC (2006)Google Scholar
  4. 4.
    Belton, V.: A comparison of the analytic hierarchy process and a simple multi-attribute value function. Eur. J. Oper. Res. 26(1), 7–21 (1986)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Pawlak, Z., Sowinski, R.: Rough set approach to multi-attribute decision analysis. Eur. J. Oper. Res. 72(3), 443–459 (1994)CrossRefGoogle Scholar
  6. 6.
    Saaty, T.L., Erdener, E.R.E.N.: A new approach to performance measurement the analytic hierarchy process. Des. Methods Theor. 13(2), 62–68 (1979)Google Scholar
  7. 7.
    Hwang, C.L., Yoon, K.: Methods for multiple attribute decision making. In: Multiple Attribute Decision Making (pp. 58–191). Springer, Berlin, Heidelberg (1981)CrossRefGoogle Scholar
  8. 8.
    Roy, B. Classement et choix en présence de points de vue multiples (la méthode ELECTRE). La Revue d’Informatique et de Recherche Opérationelle (RIRO) (8): 57–75 (1968)CrossRefGoogle Scholar
  9. 9.
    Brans, J.P., Vincke, P.: A preference ranking organisation method: the PROMETHEE method for MCDM. Manag. Sci. 31, 647–656 (1985)CrossRefGoogle Scholar
  10. 10.
    Ethiopia Population, total. World Bank Group (2017).
  11. 11.
    Annual Report 2016/17. Agricultural Transformation Agency (2017)Google Scholar
  12. 12.
    Shoham, Y.: Agent-oriented programming. Artif. Intell. 60(1), 51–92 (1993)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Shoham, Y.: Agent oriented programming: an overview of the framework and summary of recent research. In: International Conference on Logic at Work, pp. 123–129. Springer, Berlin, Heidelberg (1992)CrossRefGoogle Scholar
  14. 14.
    Lukic, A., Luburi, N., Vidakovi, M., Holbl, M.: Development of multi-agent framework in JavaScript (2017)Google Scholar
  15. 15.
    Calenda, T., De Benedetti, M., Messina, F., Pappalardo, G., Santoro, C.: AgentSimJS: a web-based multi-agent simulator with 3d capabilities. In: WOA, pp. 117–123 (2016)Google Scholar
  16. 16.
    De Jong, J., Stellingwerff, L., Pazienza, G.E.: Eve: a novel open-source web-based agent platform. In: Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on (1537–1541). IEEE (2013)Google Scholar
  17. 17.
    Zionts, S.: A survey of multiple criteria integer programming methods. Annals of Discrete Mathematics 5, 389–398 (1979)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Zavadskas, E.K., Turskis, Z., Kildienė, S.: State of art surveys of overviews on MCDM/MADM methods. Technol. Econ. Dev. Econ. 20(1), 165–179 (2014)CrossRefGoogle Scholar
  19. 19.
    Portugal, I., Alencar, P., Cowan, D.: The use of machine learning algorithms in recommender systems: a systematic review. Expert Syst. Appl. 97, 205–227 (2018)CrossRefGoogle Scholar
  20. 20.
    Saaty, T.L.: Exploring the interface between hierarchies, multiple objectives and fuzzy sets. Fuzzy Sets Syst. 1(1), 57–68 (1978). Scholar
  21. 21.
    Aczél, J., Saaty, T.L.: Procedures for synthesizing ratio judgements. J. Math. Psychol. 27(1), 97 (1983). Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Patricio Julián Gerpe
    • 1
    Email author
  • Evangelos Markopoulos
    • 2
  1. 1.Enpov, Silk LaftoAddis AbabaEthiopia
  2. 2.HULT International Business SchoolLondonUK

Personalised recommendations