Effective Customer Relationship Management at ATB Financial: A Case Study on Industry-Academia Collaboration in Data Analytics

  • Ian Hargreaves
  • Dylan Roth
  • Muhammad Rezaul KarimEmail author
  • Maleknaz Nayebi
  • Günther Ruhe
Part of the Studies in Big Data book series (SBD, volume 27)


Data analytics serve as a means to detect trends and patterns from organizational data repositories. The variety and dynamism of data and analysis approaches create a wide range of opportunities for collaboration between academia and industry. Successful collaboration projects create win-win scenarios with tangible benefits for both sides. This paper reports about an ongoing project between ATB Financial and the Laboratory for Software Engineering Decision Support (SEDS) at The University of Calgary. The key content of the project was to leverage the benefits of data analytics for efficient and effective customer relationship management (CRM). More precisely, the objective was to find analytic solutions that allow us to predict the complexity of an opportunity and to connect it with the right team member in order to increase efficiency and create value for ATB’s customers. We report the results and lessons learned from running through the various steps of a systematic data analytics process.


CRM Data analytics Case-based reasoning Case study Industry-academia collaboration 


  1. 1.
    Latum FV, et al. Adopting GQM-based measurement in an industrial environment. IEEE Softw. 1998;15(1):78–86.CrossRefGoogle Scholar
  2. 2.
    SAS Institute. SAS Enterprise Miner 13.1,
  3. 3.
    Delen D. Real-world data mining. Upper Saddle River, NJ: Pearson Education; 2014.Google Scholar
  4. 4.
    Ruhe G, Nayebi M. What counts is decisions, not numbers–towards an analytics design sheet. In: Menzies T, et al., editors. Perspectives in data science for software engineering. Burlington, MA: Morgan Kauffman; 2016. p. 113–116.Google Scholar
  5. 5.
    Richter MM, Weber RO. Case-based reasoning. Berlin: Springer; 2013.CrossRefGoogle Scholar
  6. 6.
    Aamodt A, Plaza E. Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun. 1994;7(1):39–59.Google Scholar
  7. 7.
    Noh J, et al. A case-based reasoning approach to cognitive map-driven tacit knowledge management. Expert Syst Appl. 2000;19(4):249–259.CrossRefGoogle Scholar
  8. 8.
    Cichosz P. Data mining algorithms: explained using R. Hoboken, NJ: Wiley; 2015.CrossRefGoogle Scholar
  9. 9.
    Brodersen KH, et al.. The balanced accuracy and its posterior distribution. In: Proceedings 20th international conference on pattern recognition (ICPR), 2010. p. 3121–3124.Google Scholar
  10. 10.
    Wohlin C, et al. The success factors powering industry-academia collaboration. IEEE Softw. 2012;29(2):67–73.CrossRefGoogle Scholar
  11. 11.
    Schubert S. The power of the group processing facility in SAS® Enterprise Miner™. In: SAS Global Forum; 2010. p. 1–13.Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Ian Hargreaves
    • 1
  • Dylan Roth
    • 1
  • Muhammad Rezaul Karim
    • 2
    Email author
  • Maleknaz Nayebi
    • 2
  • Günther Ruhe
    • 2
  1. 1.ATB FinancialCalgaryCanada
  2. 2.Software Engineering Decision Support LaboratoryUniversity of CalgaryCalgaryCanada

Personalised recommendations