Master in Business Analytics Thesis Defense: Nazlı Deniz Türker
HOTEL ROOM SALES PREDICTION FOR A TRAVEL AGENCY
Nazlı Deniz Türker
Master in Business Analytics Thesis Defense
Date: July 12th, 2021, Monday @ 2 pm
Zoom link: https://sabanciuniv.zoom.us/j/5997620479
Keywords: Tourism Analytics, Sales Prediction, Hotel Sales Prediction
The ability to predict sales can be incredibly useful for the tourism industry because it allows planners and managers to predict future performance. By this means, the travel agencies can make more measured decisions about facilities, improve their agreements with more favorable terms, and offer better deals to customers in order to maximize revenue and minimize loss. Sales prediction can allow travel agencies to adjust prices based on supplies of facilities and demands of customers, focus on sales towards different demographics or make changes to their marketing strategy in order to attract more customers of a certain type. In this thesis, we compared different statistical and machine learning models on several datasets consist of basic information on hotels, hotel features, and point of interests around hotels in order to present a robust and accurate solution to the hotels’ room sales prediction problem based on the data of one of the biggest travel agencies in the Turkish tourism market. The results show that machine learning regression models have a great potential for hotel sales prediction. Random Forest Regression is outstanding with the highest goodness of fit and Support Vector Regression is good at accuracy values in the majority of the cases. Besides, there is a significant difference between the predictive performances by using All Segments and Two Adults Segment datasets. However, adding PoI data to any of the main datasets does not have a significant impact on the feature importance list, there is no clear superiority between the PoI included datasets over without PoI datasets.