{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/b279ea3dc3b849469e5336fbcaedc202\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/b279ea3dc3b849469e5336fbcaedc202-8abd179f42af5c82.gif","duration":251.012,"title":"Predicting Electrical Output with Machine Learning: A Regression Model Approach","description":"Hello, I'm Carlos Mello, and in this video, I present my project for the machine learning course at Duke University, where I developed a model to predict hourly electrical output for a combined cycle power plant. I used linear regression as a baseline and a random forest regressor to capture non-linear effects, achieving a mean-squared error (MSE) of 20.91 for linear regression and 11.99 for random forest, which is a 42% reduction in error. The random forest model yielded an R-squared of 0.9636 on unseen data, with a square root MSE of about 3.25 megawatts, providing reliable forecasts for operators. I utilized 5-fold cross-validation to ensure the model's robustness and prevent overfitting. Thank you for watching, and I look forward to any feedback you may have!"}