Abstract
The deployment of production-quality ML solutions, even for simple applications, requires significant software engineering effort. Often, companies do not fully understand the consequences and the business impact of ML-based systems, prior to the development of these systems. To minimize investment risks while evaluating the potential business impact of an ML system, companies can utilize continuous experimentation techniques. Based on action research, we report on the experience of developing and deploying a business-oriented ML-based dynamic pricing system in collaboration with a home shopping e-commerce company using a continuous experimentation (CE) approach. We identified a set of generic challenges in ML development that we present together with tactics and opportunities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Breck, E., Cai, S., Nielsen, E., Salib, M., Sculley, D.: The ML test score: a rubric for ML production readiness and technical debt reduction. In: Proceedings - 2017 IEEE International Conference Big Data, Big Data 2017, vol. 2018, pp. 1123–1132 (2018)
Lindgren, E., Münch, J.: Raising the odds of success: the current state of experimentation in product development. Inf. Softw. Technol. 77, 80–91 (2016)
Fagerholm, F., et al.: The RIGHT model for continuous experimentation. J. Syst. Softw. 123, 292–305 (2017)
Olsson, H.H., Bosch, J.: From opinions to data-driven software R&D: a multi-case study on how to close the ‘Open Loop’ problem. In: 2014 40th EUROMICRO Conference on Software Engineering and Advanced Applications, pp. 9–16 (2014)
Huang, H., Huang, H., Liu, Q.: Intelligent retail forecasting system for new clothing products considering stock-out. Fibres Text. East. Eur. 25(121), 10–16 (2017)
Ferreira, K.J., Lee, B.H.A., Simchi-Levi, D.: Analytics for an online retailer: demand forecasting and price optimization. Manuf. Serv. Oper. Manag. 18(1), 69–88 (2016)
Dos Santos, P.S.M., Travassos, G.H.: Action research can swing the balance in experimental software engineering. Adv. Comput. 83, 205–276 (2011)
Checkland, P., Holwell, S.: Action research: its nature and validity. Syst. Pract. Action Res. 11(1), 9–21 (1998)
Raj, A., Bosch, J., Olsson, H.H., Arpteg, A., Brinne, B.: Data management challenges for deep learning. In: 45th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), pp. 1–8 (2019)
Lwakatare, L.E., Raj, A., Bosch, J., Olsson, H.H., Crnkovic, I.: Agile Processes in Software Engineering and Extreme Programming, vol. 149. Springer, Berlin (2013). https://doi.org/10.1007/978-3-642-38314-4
Sculley, D., et al.: Machine Learning : The High-Interest Credit Card of Technical Debt, pp. 1–9 (2014)
Pineau, J.: Building reproducible, reusable, and robust machine learning software. In: 41st ACM/IEEE International Conference on Software Engineering (ICSE 2019) (2019)
Levy, M., Grewal, D., Kopalle, P., Hess, J.: Emerging trends in retail pricing practice: implications for research. J. Retail. 80(3), 13–21 (2004)
Acknowledgments
This work was partially supported by the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation and by the Software Center.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Online Appendix
Online Appendix
The online appendix, available at https://github.com/davidissamattos/icsob-2019, presents additional information regarding the CE process, the analysis of the experiment and the developed ML dynamic pricing system
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Mattos, D.I., Bosch, J., Olsson, H.H. (2019). Leveraging Business Transformation with Machine Learning Experiments. In: Hyrynsalmi, S., Suoranta, M., Nguyen-Duc, A., Tyrväinen, P., Abrahamsson, P. (eds) Software Business. ICSOB 2019. Lecture Notes in Business Information Processing, vol 370. Springer, Cham. https://doi.org/10.1007/978-3-030-33742-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-33742-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33741-4
Online ISBN: 978-3-030-33742-1
eBook Packages: Computer ScienceComputer Science (R0)