Performance Evaluation on Resolution Time Prediction Using Decision Tree, Random Forest and eXtreme Gradient Boosting

Providing excellent customer service is always important for an organisation, and one of the biggest demands from customers is the speed of resolution. Customers anticipate a prompt, simple, and efficient response when they submit a service ticket to request service. While the customer service representatives attempt to resolve problems assigned to them while simultaneously giving clients a nice experience and upholding the company's excellent reputation, they receive several tickets each day. On-time services may boost customer satisfaction, foster client loyalty, and grow the number of prospective loyal consumers. The best option for speeding up ticket resolution in this case will be a prediction model that makes use of Machine Learning techniques. Experimental evaluations revealed that eXtreme Gradient Boosting works better than other strategies by achieving a low Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and MAE (Mean Absolute Error) scores with good model accuracy.