SOFTWARE EFFORT ESTIMATION USING MACHINE LEARNING

AbstractSoftware cost and effort estimation is a critical task in software engineering. Research in this fieldcontinually evolves with new techniques, requiring periodic comparative analyses. Accurate softwarecost estimation is vital for project success, as it helps identify the challenges and risks involved indevelopment. The wide variety of machine learning (ML) and non-ML techniques has led tocomparisons and the integration of these methods, making it essential to determine the most effectiveestimation techniques to enhance the project development process.The review follows a three-stage approach: planning (Tollgate approach), conducting (Likert-typescale), and reporting results from five well-known digital libraries. Among the 52 selected articles, theartificial neural network (ANN) model and the Constructive Cost Model (COCOMO) have beenidentified as the most favored techniques. The mean magnitude of relative error (MMRE) is thepreferred accuracy metric, with software engineering and project management being the most relevantfields. The PROMISE repository has emerged as the most widely accessed database. Keywords: Software cost estimation, systematic literature review, tollgate approach, Likert scale,quality assessment, software dependability.