Prediction of Software Reliability Using Fuzzy ARIMA Model

摘要

In this paper a Fuzzy ARIMA (FARIMA) time series model has been proposed to analyze the reliability of software. The concept of interval model and parameter has been used in the proposed model which is useful for predicting the time between failures (TBFs) of software. This concept makes it possible for decision makers to predict the best and worst possible situations based on fewer observations than the ARIMA model in which at least 50 and preferably 100 observations or more are used. Usefulness of the proposed model has been demonstrated using real software failure data.