Milan Mirković
Stevan Milisavljević
Danijela Gračanin
Faculty of Technical Sciences, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
DOI: https://doi.org/10.31410/ITEMA.2018.6
2nd International Scientific Conference on Recent Advances in Information Technology, Tourism, Economics, Management and Agriculture – ITEMA 2018 – Graz, Austria, November 8, 2018, CONFERENCE PROCEEDINGS published by the Association of Economists and Managers of the Balkans, Belgrade, Serbia; ISBN 978-86-80194-13-4
2nd International Scientific Conference on Recent Advances in Information Technology, Tourism, Economics, Management and Agriculture – ITEMA 2018 – Graz, Austria, November 8, 2018, CONFERENCE PROCEEDINGS published by the Association of Economists and Managers of the Balkans, Belgrade, Serbia; ISBN 978-86-80194-13-4
Abstract
Predicting customer churn has become increasingly important for companies competing in contemporary markets, as modern technologies keep tipping the scales of power and influence into the hands of customers. Hence, devising and executing retention campaigns targeting the population that is at the risk of being “lost” can make a big difference to the financial performance of a company. In this paper, we present a framework based on opensource technologies that makes evaluation of different churn definitions in a non-contractual business setting easy, in terms of resulting model performance. In particular, we propose an automated approach to feature engineering, model creation, model evaluation and model selection that should enable companies to quickly assess the effects of choosing a particular interval of inactivity as a churn definition period on the potential value of planned retention activities.
Key words
Churn prediction, machine learning, framework, automation, non-contractual business setting
References
[1] Reinartz, W. J., Kumar, V. (2003). The Impact of Customer Relationship Characteristics on Profitable Lifetime Duration. Journal of Marketing, 67, pp. 77–99.
[2] Van den Poel, D., Lariviere, B. (2004). Customer Attrition Analysis For Financial Services Using Proportional Hazard Models. European Journal of Operational Research, 157, pp. 196–217
[3] Nath, S. V, Behara, R. S. (2003). Customer Churn Analysis in the Wireless Industry: A Data Mining Approach. Proceedings-Annual Meeting of the Decision Sciences Institute, (561), pp. 505–510.
[4] Huang, B. Q., Kechadi, T. M., Buckley, B., Kiernan, G., Keogh, E., Rashid, T. (2010). A new feature set with new window techniques for customer churn prediction in land-line telecommunications. Expert Systems ith Applications, 37(5), pp. 3657–3665.
[5] Dudyala Anil, K., Ravi, V. (2008). Predicting credit card customer churn in banks using data mining. International Journal of Data Analysis Techniques and Strategies, pp. 4–28. [6] Pribil, J., & Polejova, M. (2017). A Churn Analysis Using Data Mining Techniques: Case of Electricity Distribution Company. In Proceedings of the World Congress on Engineering and Computer Science, Vol. I, pp. 1–6, San Francisco, USA.
[7] Merkel, D., (2014). Docker: lightweight Linux containers for consistent development and deployment, Linux Journal, 2014.
[8] H2O.ai (2018), Open source software, https://www.h2o.ai/ (accessed: 28.10.2018).
[9] Burez, J., & Van den Poel, D. (2009). Handling class imbalance in customer churn prediction. Expert Systems with Applications, pp. 4626–4636.
[2] Van den Poel, D., Lariviere, B. (2004). Customer Attrition Analysis For Financial Services Using Proportional Hazard Models. European Journal of Operational Research, 157, pp. 196–217
[3] Nath, S. V, Behara, R. S. (2003). Customer Churn Analysis in the Wireless Industry: A Data Mining Approach. Proceedings-Annual Meeting of the Decision Sciences Institute, (561), pp. 505–510.
[4] Huang, B. Q., Kechadi, T. M., Buckley, B., Kiernan, G., Keogh, E., Rashid, T. (2010). A new feature set with new window techniques for customer churn prediction in land-line telecommunications. Expert Systems ith Applications, 37(5), pp. 3657–3665.
[5] Dudyala Anil, K., Ravi, V. (2008). Predicting credit card customer churn in banks using data mining. International Journal of Data Analysis Techniques and Strategies, pp. 4–28. [6] Pribil, J., & Polejova, M. (2017). A Churn Analysis Using Data Mining Techniques: Case of Electricity Distribution Company. In Proceedings of the World Congress on Engineering and Computer Science, Vol. I, pp. 1–6, San Francisco, USA.
[7] Merkel, D., (2014). Docker: lightweight Linux containers for consistent development and deployment, Linux Journal, 2014.
[8] H2O.ai (2018), Open source software, https://www.h2o.ai/ (accessed: 28.10.2018).
[9] Burez, J., & Van den Poel, D. (2009). Handling class imbalance in customer churn prediction. Expert Systems with Applications, pp. 4626–4636.
[10] Chen, D., Sain, S. L., Guo, K. (2012). Data mining for the online retail industry: A case study of RFM model-based customer segmentation using data mining. Journal of Database Marketing & Customer Strategy Management, pp. 197–208.
