Predicting waiters prompt service by analyzing restaurants rating and other factors using machine learning

This project aims to predict waiters prompt service and analyze how other factors like Restaurant’s ranking, Ambience, customers finance etc., effect waiters small incentive. Major reasons were analyzed so, that restaurant brings some changes to increase waiter’s service along with restaurant’s reputation and it’s like giving good reward for their appreciative service. Not only waiters service effect their incentive but also restaurants ambience, ranking, food quality also because some effect. Some models were proposed to predict the tip these shows the result with all the factors involved and helps to predict the expected result. The proposed model is validated against techniques like Random forest Regressor Using Hyper tuning, Bayesian Ridge Regressor, Elasticnet Regressor. Along with good visualization for better analysis using Mat plot, seaborn. They are particularly suited to predicting exact output as expected. For implementation purposes, choose features like total_bill, tip, sex, smoker, day, time, etc., the proposed model is evaluated with a waiter’s tip data set along with some changes to dataset based on various performance to show its effectiveness.