Feature Aware Prediction of User Action in Software Process

A lot of Software Process Description Languages have been exercised and made. Some implement one paradigm, for example rule based languages (pre-/post conditions), net based languages (petri nets, state machines), or imperative languages (based on programming languages). Others implement multiple paradigms .all of them are not very efficient, reliable and robust and the approach we use, observes the user’s action and tries to predict his next step. For this we use approaches in the area of machine learning (sequence learning) and adopt these for the use in software processes. This paper describes an approach for user (e.g. SW architect) assisting in software processes. The sequence prediction technique, which is presented in this paper, is based on IPAM4 and Jacobs/Blockeel5. The results show that our approach predicts continuously better than the original algorithm. In this paper we described an approach to assist users by predicting the next step the user starts during process enactment. We evaluated this work by defining situations and we compared our approach with the core algorithm we have adopted.