Revolutionizing tour cost prediction through the integration of cutting-edge analytical and computational techniques
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This will help stakeholders within the tourist sector make better decisions with machine learning (ML) algorithms in a timely manner for a more realistic prediction of tourism expenses. Algorithms analyze historical data to predict tourism costs, aiding budget planning, resource management, and improved customer satisfaction and revenues. This was achieved by considering two ML models, quadratic discriminant analysis (QDA) and logistic regression classifier (LRC), and the performances of each were also improved with the Victoria Amazonica optimizer. Furthermore, the two newly created hybrid models, namely, LRVA and QDVA, have been tested under conditions such as high, higher, highest, low, lower, and normal in two different phases of training and testing. Among these comparisons, the recall value of base models, LRC and QDA, was 0.951 and 0.947, respectively, when the models were fitted in the training phase, showing that they are relatively weak performers. However, the hybrid models, LRVA and QDVA, seemed to be very good performers and had given recall values of 0.971 and 0.961, respectively; hence, these models have become the best and runner-up correspondingly. Therefore, this analysis underlines the potency of ML in optimizing the cost predictions of tourism and enhancing its overall efficiency in the tourism sector.
Fields of Study & Subjects
Data Mining and Machine Learning Applications
Forecasting Techniques and Applications
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- Communications in Statistics - Simulation and Computation
- Pages
- 1–17
- Publication date
- 27 March 2026
- Language
- EN