Prediction bike-sharing demand with gradient boosting methods

The popularity of bike-sharing programs has increased the need for precise demand prediction techniques. In this work, the use of gradientboosting techniques to forecast demand for bike-sharing systems is studied. The gradient boosting algorithms XGBoost, LightGBM, and CatBoost are used in this study to suggest an approach for predicting bike-sharing demand. Two real-world data sets were analyzed in this study, one for Konya and the other for Washington, D.C. Both datasets provide details about the day's particular characteristics and the weather. By using previous data to train a gradient-boosting model, we are able to make extremely precise predictions of future bike-sharing demand. CatBoost outperforms XGboost and LightGBM when all gradient boosting models are trained with the best hyperparameter sets.