To adapt to the fast-changing landscape of technology and the increasing complexity of skills needed as a result, an outcome-based delivery model, called crowdsourcing, emerges in recent years for software development. In this model, some of the work required by a large project is broken down into self-contained short-cycle components, and a resource pool of vetted freelancers is leveraged to perform the tasks. The resource pool must be managed carefully by the service provider to ensure the availability of the right skills at the right time when they are needed. This article proposes a statistical framework of demand forecasting to support the capacity planning and management of resource pool services. The proposed method utilizes the predictive information contained in the system that facilitates the resource pool operation through survival models, and combine the results with special complementary time series models to produce demand forecasts in multiple categories at multiple time horizons. A dataset from a real-world resource pool service operation for software development is used to motivate and evaluate the proposed method.
By: Ta-Hsin Li
Published in: RC25585 in 2016
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .