Journal of Business Economics

, Volume 88, Issue 5, pp 563–592 | Cite as

Privacy-preserving condition-based forecasting using machine learning

  • Fabian TaigelEmail author
  • Anselme K. Tueno
  • Richard Pibernik
Original Paper


As machines get smarter, massive amounts of condition-based data from distributed sources become available. This data can be used to enhance maintenance management in several ways, such as by improving maintenance demand forecasting and spare parts and capacity planning. Regarding the former, machine learning techniques promise substantial benefits for forecasting the demand for spare parts over conventional techniques that are commonly used. While development and implementation of these techniques is difficult, practical applications pose another important challenge to providers of maintenance, repair, and overhaul services. Their customers are reluctant to provide access to sensitive real-time data because of privacy concerns, and even more so when their data is stored and processed in the cloud. In this paper we describe an application for privacy-preserving forecasting of demand for spare parts based on distributed condition data. It combines machine learning techniques—more specifically, decision-tree classification—with order-preserving encryption. The application is appropriate whenever planning for spare parts for the maintenance of condition-monitored machinery is needed, and it is particularly suitable for cloud-based implementation.


Forecasting Maintenance planning Secure cloud computing Order-preserving encryption Secure multi-party computation 



Special thanks goes to Florian Hahn, Product Security Research, SAP SE, for his support with the performance tests.


  1. Agrawal R, Kiernan J, Srikant R, Xu Y (2004) Order preserving encryption for numeric data. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD ’04, pp 563–574Google Scholar
  2. Babaï MZ, Syntetos AA, Dallery Y, Nikolopoulos K (2009) Dynamic re-order point inventory control with lead-time uncertainty: analysis and empirical investigation. Int J Prod Res 47(9):2461–2483CrossRefGoogle Scholar
  3. Barkataki S, Zeineddine H (2015) On achieving secure collaboration in supply chains. Inf Syst Front 17(3):691–705CrossRefGoogle Scholar
  4. Barratt M (2004) Understanding the meaning of collaboration in the supply chain. Supply Chain Manag Int J 9(1):30–42CrossRefGoogle Scholar
  5. Beimel A (2011) Secret-sharing schemes: a survey. In: Proceedings of the Third International Conference on Coding and Cryptology, Springer-Verlag, Berlin, Heidelberg, IWCC’11, pp 11–46Google Scholar
  6. Bost R, Popa RA, Tu S, Goldwasser S (2015) Machine learning classification over encrypted data. In: 22nd Annual Network and Distributed System Security Symposium, NDSS 2015, San Diego, California, USAGoogle Scholar
  7. Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd International Conference on Machine Learning, ACM, New York, NY, USA, ICML ’06, pp 161–168Google Scholar
  8. Caruana R, Karampatziakis N, Yessenalina A (2008) An empirical evaluation of supervised learning in high dimensions. In: Proceedings of the 25th International Conference on Machine Learning, ICML ’08, pp 96–103Google Scholar
  9. Coraddu A, Oneto L, Ghio A, Savio S, Anguita D, Figari M (2016) Machine learning approaches for improving condition-based maintenance of naval propulsion plants. Proc Inst Mech Eng, Part M: J Eng Maritime Environ 230(1):136–153CrossRefGoogle Scholar
  10. Cramer R, Damgrd IB, Nielsen JB (2015) Secure multiparty computation and secret sharing, 1st edn. Cambridge University Press, New YorkCrossRefGoogle Scholar
  11. Dahan H, Cohen S, Rokach L, Maimon O (2014) Proactive data mining with decision trees. SpringerBriefs in Electrical and Computer Engineering. Springer, New YorkCrossRefGoogle Scholar
  12. Dekker R, Pinçe Ç, Zuidwijk R, Jalil MN (2013) On the use of installed base information for spare parts logistics: a review of ideas and industry practice. Int J Prod Econ 143(2):536–545CrossRefGoogle Scholar
  13. Deloux E, Castanier B, Bérenguer C (2009) Predictive maintenance policy for a gradually deteriorating system subject to stress. Reliability Eng Syst Saf 94(2):418–431CrossRefGoogle Scholar
  14. Deshpande V, Schwarz LB (2006) Secure collaborative planning, forecasting, and replenishment. CERIAS Tech Report 2006–65:2006Google Scholar
  15. Deshpande V, Iyer AV, Cho R (2006) Efficient supply chain management at the u.s. coast guard using part-age dependent supply replenishment policies. Oper Res 54(6):1028–1040CrossRefGoogle Scholar
  16. Ducas L, Micciancio D (2015) Fhew: bootstrapping homomorphic encryption in less than a second. In: Annual International Conference on the Theory and Applications of Cryptographic Techniques, Springer, pp 617–640Google Scholar
  17. Elwany AH, Gebraeel NZ (2008) Sensor-driven prognostic models for equipment replacement and spare parts inventory. IIE Trans 40(7):629–639CrossRefGoogle Scholar
  18. Frank E, Hall M (2001) A simple approach to ordinal classification. In: Proceedings of the 12th European Conference on Machine Learning, Springer-Verlag, London, UK, UK, EMCL ’01, pp 145–156Google Scholar
  19. Gentry C (2009) Fully homomorphic encryption using ideal lattices. In: Mitzenmacher M (ed) Proceedings of the Forty-first Annual ACM Symposium on Theory of Computing, ACM, New York, NY, USA, STOC ’09, pp 169–178Google Scholar
  20. Gentry C, Halevi S, Smart NP (2012) Homomorphic evaluation of the aes circuit. In: Safavi-Naini R, Canetti R (eds) Advances in Cryptology - CRYPTO 2012, vol 7417. Lecture Notes in Computer Science. Berlin Heidelberg, Berlin, Heidelberg, pp 850–867Google Scholar
  21. Ghobbar A, Friend C (2002) Sources of intermittent demand for aircraft spare parts within airline operations. J Air Transp Manag 8(4):221–231CrossRefGoogle Scholar
  22. Hellingrath B, Cordes AK (2014) Conceptual approach for integrating condition monitoring information and spare parts forecasting methods. Prod Manuf Res Open Access J 2(1):725–737Google Scholar
  23. Jardine AK, Lin D, Banjevic D (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech Syst Signal Process 20(7):1483–1510CrossRefGoogle Scholar
  24. Jawurek M, Kerschbaum F (2012) Fault-tolerant privacy-preserving statistics. In: Privacy Enhancing Technologies - 12th International Symposium, PETS 2012, Vigo, Spain, July 11-13, 2012. Proceedings, pp 221–238Google Scholar
  25. Kerschbaum F (2009) Adapting privacy-preserving computation to the service provider model. In: Proceedings of the 12th IEEE International Conference on Computational Science and Engineering, CSE 2009, Vancouver, BC, Canada, August 29-31, 2009, pp 34–41Google Scholar
  26. Kurz J (2016) Capacity planning for a maintenance service provider with advanced information. Eur J Oper Res 251(2):466–477CrossRefGoogle Scholar
  27. Letourneau S, Famili F, Matwin S (1999) Data mining to predict aircraft component replacement. IEEE Intell Syst 14(6):59–66CrossRefGoogle Scholar
  28. Lin X, Basten R, Kranenburg A, van Houtum GJ (2012) Condition based spare parts supply. Beta Working Paper series (371)Google Scholar
  29. Lindell Y, Pinkas B (2000) Privacy preserving data mining. In: Bellare M (ed) Advances in cryptology-CRYPTO 2000, Springer, Berlin and New York, Lecture notes in computer science, vol 1880, pp 36–54Google Scholar
  30. Lomax S, Vadera S (2013) A survey of cost-sensitive decision tree induction algorithms. ACM Comput Surv 45(2):1–35CrossRefGoogle Scholar
  31. Matt G (2005) Adaptive einflussgröenkombination (aek) - prognosen mit schrittweiser regression und adaptivem gewichten. In: Mertens P, Rässler S (eds) Prognoserechnung. Physica-Verlag, Heidelberg, pp 125–168CrossRefGoogle Scholar
  32. Mertens P, Zeller AJ, Große-Wilde J (2012) Kooperative vorhersage in unternehmensnetzwerken. In: Mertens, Rässler (Hg.) 2012 – Prognoserechnung, pp 621–637Google Scholar
  33. Murphy KP (2012) Machine learning: a probabilistic perspective. Adaptive computation and machine learning series. MIT Press, CambridgeGoogle Scholar
  34. Peng Y, Dong M, Zuo MJ (2010) Current status of machine prognostics in condition-based maintenance: a review. Int J Adv Manuf Technol 50(1–4):297–313CrossRefGoogle Scholar
  35. Popa RA, Redfield CMS, Zeldovich N, Balakrishnan H (2011) Cryptdb: Protecting confidentiality with encrypted query processing. In: Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles, ACM, New York, NY, USA, SOSP ’11, pp 85–100Google Scholar
  36. Popa RA, Li FH, Zeldovich N (2013) An ideal-security protocol for order-preserving encoding. In: Proceedings of the 2013 IEEE Symposium on Security and Privacy, IEEE Computer Society, Washington, DC, USA, SP ’13, pp 463–477Google Scholar
  37. Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81–106Google Scholar
  38. Rokach L, Maimon O (2008) Data mining with decision trees: theory and applications, Series in machine perception and artificial intelligence, vol 69. World Scientific, SingaporeGoogle Scholar
  39. Schneier B (1995) Applied Cryptography (2Nd Ed.): Protocols, Algorithms, and Source Code in C. John Wiley & Sons, Inc., New York, NY, USAGoogle Scholar
  40. Seifert D (2006) Konzepte des supply-chain-managements—cpfr als unternehmensübergreifende lösung. In: Zentes J (ed) Handbuch Handel. Gabler, Wiesbaden, pp 781–794CrossRefGoogle Scholar
  41. van Wingerden E, Basten R, Dekker R, Rustenburg WD (2014) More grip on inventory control through improved forecasting: a comparative study at three companies. Int J Prod Econ 157:220–237CrossRefGoogle Scholar
  42. Veenstra AW, Zuidwijk R, Geerling B (2006) Maintenance logistics in the dutch dredging industry. In: Service Operations and Logistics, and Informatics, 2006. SOLI’06. IEEE International Conference on, IEEE, pp 436–441Google Scholar
  43. Viswanathan S, Widiarta H, Piplani R (2007) Value of information exchange and synchronization in a multi-tier supply chain. Int J Prod Res 45(21):5057–5074CrossRefGoogle Scholar
  44. Wu DJ, Feng T, Naehrig M, Lauter KE (2016) Privately evaluating decision trees and random forests. PoPETs 4:335–355Google Scholar
  45. Yam R, Tse P, Li L, Tu P (2001) Intelligent predictive decision support system for condition-based maintenance. Int J Adv Manuf Technol 17(5):383–391CrossRefGoogle Scholar
  46. Zilli A, Pibernik R, Kurz J, Taigel, Fabian et al (2015) D24.2 - business modeling: Practice technical report.

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Chair of Logistics and Quantitative Methods at University of WürzburgWürzburgGermany
  2. 2.Product Security Research, SAP SEWalldorfGermany

Personalised recommendations