Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/10438095-7972-4704-B1B9-BBCF509AEAA8 | ||
| Year | 2023 | ||
| Type of Item | Master Thesis | ||
| License |
|
||
| Bibliographic Citation | Chrysa Antria, "Machine learning algorithms for predicting the prices of short term rental properties", Master Thesis, School of Production Engineering and Management, Technical University of Crete, Chania, Greece, 2023 https://doi.org/10.26233/heallink.tuc.104246 | ||
| Appears in Collections |
The rapid expansion of the short-term rental market through platforms such as Airbnb has created a growing need for more accurate and reliable rental price prediction models. This study explores the application of machine learning algorithms for forecasting rental prices of short-term accommodation, with a focus on the city of Thessaloniki.Following data collection and preprocessing using information from the Inside Airbnb platform, two predictive models were developed and evaluated: one based on Artificial Neural Networks and another on the Random Forest algorithm. The performance of both models was assessed using key metrics, including the coefficient of determination (R2) and the Root Mean Squared Error (RMSE). Results indicated that the Random Forest algorithm can provide better estimations, as it is more efficient with an R² coefficient of 0,898 and a mean error (RMSE) of 13,442.These findings highlight the potential of machine learning as a decision-support tool in the pricing strategy of short-term rental properties. At the same time, they point to future opportunities for improvement through the incorporation of external variables and the application of more advanced algorithmic approaches.
Copyright © DIAS 2013
