Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Lessons learned and results from applying data-driven cost estimation to industrial data sets

: Heidrich, Jens; Trendowicz, Adam; Münch, Jürgen; Ishigai, Yasushi; Yokoyama, Kenji; Kikuchi, Nahomi; Kawaguchi, T


Machado, R.J. ; Institute of Electrical and Electronics Engineers -IEEE-:
6th International Conference on the Quality of Information and Communications Technology, QUATIC 2007. Proceedings : 12-14 September, 2007, Lisbon, Portugal
Los Alamitos: IEEE Computer Society, 2007
ISBN: 978-0-7695-2948-6
ISBN: 0-7695-2948-8
International Conference on the Quality of Information and Communications Technology (QUATIC) <6, 2007, Lisbon>
Conference Paper
Fraunhofer IESE ()
cost estimation; measurement; machine learning; evaluation; case study; lessons learned

The increasing availability of cost-relevant data in industry allows companies to apply data-intensive estimation methods. However, available data are often inconsistent, invalid, or incomplete, so that most of the existing data-intensive estimation methods cannot be applied. Only few estimation methods can deal with imperfect data to a certain extent (e.g., Optimized Set Reduction, OSR®). Results from evaluating these methods in practical environments are rare. This article describes a case study on the application of OSR® at Toshiba Information Systems (Japan) Corporation. An important result of the case study is that estimation accuracy significantly varies with the data sets used and the way of preprocessing these data. The study supports current results in the area of quantitative cost estimation and clearly illustrates typical problems. Experiences, lessons learned, and recommendations with respect to data preprocessing and data-intensive cost estimation in general are presented.