Closed bdzyubak closed 3 months ago
Implemented the model, and obtained improved performance using the following hyperparameter settings: learning_rate = 0.001 max_tree_depth = [10] n_estimators=10000 (converges on just over 3000)
Further hyperparameter search, feature engineering and time-series cross validation will be implemented in another issue. So are comparisons to Kaggle benchmarks, if any
There is an interesting dataset of hourly power consumption across multiple utilities available on Kaggle. A baseline model fails to fit the extremes of power consumption. Implement and improve the tutorial. Then, in separate issues, improve performance. https://www.kaggle.com/code/robikscube/time-series-forecasting-with-machine-learning-yt/notebook