<![CDATA[The increasing demand for Artificial Intelligence-related jobs has intensified global labor market dynamics, characterized by high salary variability and growing industry uncertainty. These conditions pose significant challenges for organizations and professionals in determining accurate, objective, and data-driven salary estimations. This study aims to develop and compare the performance of several regression models for predicting Artificial Intelligence job salaries, namely Linear Regression, Gradient Boosting, and Support Vector Regression. A large-scale global job postings dataset is employed, incorporating conventional job attributes such as location, experience level, and job type. In addition, this study integrates industry risk variables, including layoff risk and automation risk, to capture more realistic labor market dynamics. The research methodology consists of data preprocessing, model development using a machine learning pipeline to ensure consistent processing between training and testing data, and performance evaluation. The dataset is split into training and testing sets using an 80:20 ratio, and model performance is assessed using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²). The experimental results indicate that Gradient Boosting achieves the best performance with the lowest prediction errors and the highest explanatory power, followed by Linear Regression. In contrast, Support Vector Regression exhibits relatively poor performance on high-dimensional feature representations. These findings confirm that ensemble-based approaches are more effective in modeling the heterogeneous and non-linear salary structures of Artificial Intelligence jobs and provide valuable insights for data-driven labor market analysis.]]>
