The predominant aim of software engineering is to broaden top notch software program tasks that meet all necessities with minimum funding in budget, resources, and human resources. Estimating software development efforts are considered one of the most important tasks in software development. SDEE involves assessing the manpower, budget, and time needed to develop high quality software. SDEE accuracy enables effective planning, control, and software projects on budget and on schedule. SDEE overestimation/ underestimation is an important issue. Regular rigorous reviews are required to improve forecasts. Estimating or predicting software development efforts early in the software development life cycle helps and encourages teams to develop and deliver quality software within time and budget. Therefore, as the entire software development process relies on these predictions, the person responsible for the project manager must have the ability to accurately and reliably estimate software development effort. While software engineering experts have utilised a variety of effort estimating strategies over the last four decades, including those based on statistical and machine learning methods, no consensus has been established on which strategy performs best in all situations. Ensemble learning approaches were developed to address this problem. The ensemble model's purpose is to automatically manage each of its component model's strengths and weaknesses, resulting in the best possible decision being made overall. The main purpose of this study is to develop a model using an ensemble technique.

___________________________________________________________________________________

Keywords: Machine Learning, Software Effort Estimation, Ensemble Techniques.