IBM Predictive Analytics Reduces Server Downtime

References

• Bogojeska J, Wiesmann D (2018) Transfer learning for server behavior classification in small IT environments. Proc. Network Oper. Management Sympos. (Institute of Electrical and Electronics Engineers, Washington, DC), 1–9.Google Scholar
• Bogojeska J, Giurgiu I, Lanyi D, Stark G, Wiesmann D (2014) Impact of HW and OS type and currency on server availability. Proc. Network Oper. Management Sympos. (Institute of Electrical and Electronics Engineers, Washington, DC), 1–9.Google Scholar
• Bogojeska J, Lanyi D, Giurgiu I, Stark G, Wiesmann D (2013a) Classifying server behavior and predicting impact of modernization actions. Proc. Network Oper. Management Sympos. (Institute of Electrical and Electronics Engineers, Washington, DC), 59–66.Google Scholar
• Bogojeska J, Giurgiu I, Lanyi D, Lucic M, Pfitzmann B, Stark GE, Wiesmann D (2013b) System recommendations based on incident analysis. U.S. Patent 9,406,023, filed December 19, 2013, and issued August 2, 2016.Google Scholar
• Bozman JS, Broderick KT (2010) Server refresh: Meeting the changing needs of enterprise IT with hardware/software optimization. White paper, International Data Corporation, Farmington, MA.Google Scholar
• Chen C, Liaw A, Breiman L (2004) Using random forest to learn imbalanced data. Technical report, University of California, Berkeley, Berkeley.Google Scholar
• Childress RL, Nidd ME, Rivers M, Stark GE, Tummalapenta SB, Wiesmann D (2017) Deriving optimal actions from a random forest model. U.S. Patent 10,348,768, filed March 9, 2017, and issued September 11, 2019.Google Scholar
• Diao Y, Jamjoom H, Loewenstern D (2009) Rule-based problem classification in IT service management. Proc. IEEE Internat. Conf. Cloud Comput. (Institute of Electrical and Electronics Engineers, Washington, DC), 221–228.Google Scholar
• Diao Y, Heching A, Northcutt D, Stark G (2011) Modeling a complex global service delivery system. Jain S, Creasey RR, Himmelspach J, White KP, Fu M, eds. Proc. 2011 Winter Simulation Conf. (Institute of Electrical and Electronics Engineers, Washington, DC), 690–702.Google Scholar
• Friedman J (2001) Greedy function approximation: A gradient boosting machine. Ann. Statist. 29(5):1189–1232.Google Scholar
• Gewirtz D (2017) The astonishing hidden and personal costs of IT downtime (and how predictive analytics might help). ZDNet (May 30), https://www.zdnet.com/article/the-astonishing-hidden-and-personal-costs-of-it-downtime-and-how-predictive-analytics-might-help/.Google Scholar
• Gupta R, Prasad H, Luan L, Rosu D, Ward C (2009) Multidimensional knowledge integration for efficient incident management in a services cloud. Proc. IEEE Internat. Conf. Services Comput. (Institute of Electrical and Electronics Engineers, Washington, DC), 57–64.Google Scholar
• Lanyi D, Bogojeska J, Wiesmann D (2019) Robust automatic classification of IT incidents. Working paper, IBM Research–Zurich, Zurich.Google Scholar
• Le Q, Mikolov T (2014) Distributed representations of sentences and documents. Proc. Machine Learn. Res. 32(2):1188–1196.Google Scholar
• Lucca GAD, Penta MD, Gradara S (2002) An approach to classify software maintenance requests. Proc. IEEE Internat. Conf. Software Maintenance (Institute of Electrical and Electronics Engineers, Washington, DC), 93–102.Google Scholar
• Meyer D, Leisch F, Hornik K (2003) The support vector machine under test. Neurocomputing 55(1–2):169–186.Google Scholar
• Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of phrases and their compositionality. Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ, eds. Proc. 26th Internat. Conf. Neural Inform. Processing Systems, vol. 2 (Curran Associates, Red Hook, NY), 3111–3119.Google Scholar
• Pinheiro E, Weber W, Barros L (2007) Failure trends in a large disk drive population. Proc. 5th USENIX Conf. File Storage Tech. (USENIX Association, Berkeley, CA), 17–29.Google Scholar
• Schroeder B, Gibson GA (2006) A large-scale study of failures in high-performance-computing systems. Proc. Internat. Conf. Dependable Systems Networks (IEEE Computer Society, Los Alamitos, CA), 249–258.Google Scholar
• Schroeder B, Damouras S, Gill P (2010) Understanding latent sector errors and how to protect against them. Noh SH, ed. Proc. ACM Trans. Storage (Association for Computing Machinery, New York), 71–84.Google Scholar
• Schroeder BE, Pinheiro E, Weber W (2011) DRAM errors in the wild: A large-scale study. Comm. ACM 54(2):193–204.Google Scholar
• Statista (2019) Average cost per hour of enterprise server downtime worldwide in 2019. Accessed June 8, 2020, https://www.statista.com/statistics/753938/worldwide-enterprise-server-hourly-downtime-cost/.Google Scholar
• The Stationery Office (2011) ITIL Service Operation, 2011 edition (The Stationery Office (TOS), Norwich, UK).Google Scholar
• Van Dessel G (2011) CNet Promoter Score (NPS)—Use, application and pitfalls. Checkmarket (June), https://www.checkmarket.com/blog/net-promoter-score/.Google Scholar
• Varshney KR, Fang D, Heching AR, Mojsilovic A, Singh M (2011) Classification of IT service tickets for defect prevention. Presentation at the INFORMS Annual Meeting, November 13–16, Charlotte, NC, Institute for Operations Research and the Management Sciences, Hanover, MD.Google Scholar