Predicting customer satisfaction in hotel industry using neural networks (CROSBI ID 124290)
Prilog u časopisu | izvorni znanstveni rad
Podaci o odgovornosti
Horvat, Jasna ; Hristovska, Ljubica ; Zekić-Sušac, Marijana ; Marković, Suzana
engleski
Predicting customer satisfaction in hotel industry using neural networks
Customer satisfaction with the service quality is one of the key factors of the hotel industry successfulness. The paper investigates the ability of neural networks in predicting customer satisfaction in five Croatian hotels using neural networks. The accuracy of neural network models regarding different customer satisfaction measurements is also examined. The first model uses a seven-point Lickert scale, while the second model is based on a binary output variable. The backpropagation multi-layer perceptron is used as a neural network algorithm. The results show that the neural networks produce better accuracy on the second model, and therefore can be suggested as an effective tool for classifying the customers into satisfied and unsatisfied ones. The analysis of type I and type II errors show that the model classifies satisfied customers with better accuracy that unsatisfied customers. The results should be useful to researchers as well as hotel managers in improving the quality of their services.
customer statisfaction; neural networks; predicting; hotel industry; service quality
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano