<![CDATA[Software has become an essential part of everyday life, both in the workplace and in education. Various applications such as Microsoft Office and Google Workspace are widely used to enhance productivity. As public demand for digital solutions continues to rise, software distribution through global platforms such as Amazon has also seen significant growth. However, not all software products are able to achieve high sales figures due to the lack of effective strategies in understanding consumer behavior and market demands. Therefore, accurate sales prediction plays a crucial role in supporting successful software marketing strategies. This study aims to predict the best-selling software on Amazon by applying two algorithms: Linear Regression and Support Vector Regression (SVR). Before implementing these algorithms, several stages were conducted, including identifying the research object, preprocessing the data—where the original dataset consisting of 2,424 rows was reduced to 1,338 rows—followed by splitting the dataset into 80% training, 10% validation, and 10% testing sets. The final stage involved developing and comparing prediction models using both the Linear Regression and SVR algorithms. The results of this study are expected to contribute to determining the most suitable algorithm for predicting software sales and to serve as a reference for future research in this field]]>
Copyrights © 2025
