aspg-28-3349-1793997237 20261106203357 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group Journal of Artificial Intelligence and Metaheuristics JAIM 2833-5597 2024 8 2 Nima Khodadadi Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL, USA Benyamin Abdollahzadeh Department of Mathematics, Faculty of Science, University of Hradec Králové, 500 03, Hradec Králové, Czech Republic This paper proposes to evaluate how different machine-learning techniques can be used to predict daytime power generation based on the “Daily Power Generation Data” data set. The six models include Random Forest Regressor, Decision Tree Regressor, Nearest Neighbors, Linear Regression, MLP Regressor, and SVR, and their performance is assessed using multiple metrics. The Random Forest Regressor achieves the lowest Mean Squared Error (MSE), 3.57E-06, among the three machine-learning models. The introduction highlights the role of precise planning in the power market, and the following sections describe the topic mathematically. The table of performance results explains why the Random Forest Regressor is the superior full-proof model, with the lowest MSE, highest explained variance, and great resistance to outlying samples. The paper thus gives useful evaluation criteria for choosing the best model because the Random Forest Regressor achieves the highest performance metrics. 2024 01 06 3349 https://creativecommons.org/licenses/by/4.0/ 10.54216/JAIM.080201 https://americaspg.com/journal/28/article/3349 https://americaspg.com/storage/articles/manuscripts/01M5B4EBVGNA21BR2CYBXCAB8R.pdf