This project aims to predict whether hotel bookings will be canceled in order to optimize operational planning and minimize financial losses. I utilize various machine learning algorithms such as logistic regression, decision trees, Random Forest and K-Nearest Neighbors (KNN).
My goal is to accurately predict whether a hotel booking will be canceled or not. For this purpose, I use historical booking data and consider important factors such as the lead time, room category, and previous cancellations. My model should be able to predict the cancellation behavior of customers, allowing hotels to improve their operational planning and avoid empty rooms.
Decision Trees with Random Forest: I combine multiple decision trees to make accurate predictions. The Random Forest algorithm takes into account the predictions of all the trees and provides a consistent result.
Install the required dependencies using pip install -r requirements.txt
.
Execute the "hotel_cancellation.ipynb" notebook to load the dataset, train the model, and generate predictions.
To directly Access the best model from this notebook which interprets the data and gives you a prediction, go to: https://stornierungsvorhersage.flitschi.vip
It provides the opportunity to improve cancellation prediction in the hotel industry, thereby optimizing profitability and guest experience.