• DocumentCode
    1670552
  • Title

    Cross-Skill Training Plan Generation for Accounts in Application Management Service (AMS)

  • Author

    Ying Li ; Yichong Yu

  • Author_Institution
    IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
  • fYear
    2015
  • Firstpage
    586
  • Lastpage
    591
  • Abstract
    This paper presents our latest work on assisting AMS (application management service) clients or accounts to generate effective cross-skill training plans. Specifically, we aim to answer the following two questions: "Whom to train?" and "What to train?", both of which are very critical to training plan generation. To achieve this goal, we first analyze a given account\´s service request data and identify a set of candidate categories (which indicate skills) for each account consultant to be trained upon, then we measure the following three important metrics: the importance of each such category, consultant\´s resource utilization, and the temporal correlation between such category and the categories that the consultant can already handle. Finally, we present all measurements to the account team allowing it to generate very flexible cross-skill training plans based on various goals. So far, we have applied this tool to a couple of real AMS accounts, and have received some initial yet encouraging feedback.
  • Keywords
    outsourcing; resource allocation; software management; AMS account; application management service; consultant resource utilization; cross-skill training plan generation; temporal correlation; Correlation; Maintenance engineering; Predictive models; Resource management; Training; Weight measurement; Application Management Service (AMS); cross-skill training; incident tickets; resource utilization; temporal correlation; ticket category; training plan generation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Services Computing (SCC), 2015 IEEE International Conference on
  • Conference_Location
    New York, NY
  • Print_ISBN
    978-1-4673-7280-0
  • Type

    conf

  • DOI
    10.1109/SCC.2015.85
  • Filename
    7207403