Software cost estimation is an important early stage in the software development cycle. This process requires careful analysis of the project, taking into account various factors that affect cost and time to completion such as errors in the initial identification of what kind of software will be built and its utilization. One of the main challenges in budgeting is the lack of clear reference prices, which often results in the use of historical data as the basis for calculations. This research proposes a combination of methods to improve the accuracy and reliability of cost estimation, including text summarization and word2vec for sentence analysis and weighting, and catalog extraction to identify SRS documents as system features, including ambiguity features. The goal is to provide a more effective tool for future software project budgeting, ensuring cost estimation that matches the complexity of the project and proper assignment of experts. With this method, it is expected that companies can reduce the risk of miscalculation and inappropriate assignment of experts, thereby avoiding financial losses and project delays.
Copyrights © 2024