Towards Execution Time Prediction for Manual Test Cases from Test Specification

Abstract

Knowing the execution time of test cases is importantto perform test scheduling, prioritization and progressmonitoring. This work in progress paper presents a novelapproach for predicting the execution time of test cases basedon test specifications and available historical data on previouslyexecuted test cases. Our approach works by extractingtiming information (measured and maximum execution time)for various steps in manual test cases. This information is thenused to estimate the maximum time for test steps that have notpreviously been executed, but for which textual specificationsexist. As part of our approach, natural language parsing ofthe specifications is performed to identify word combinationsto check whether existing timing information on various testactivities is already available or not. Finally, linear regressionis used to predict the actual execution time for test cases. A proof-of-concept use case at Bombardier Transportationserves to evaluate the proposed approach.