Forecasting Regional Tourist Influx with Decision Tree Regression and GRNN: A Data-Driven Approach

Kumaun, a renowned region in Uttarakhand, attracts a large number of tourists annually due to its natural beauty and rich cultural heritage. The influx of tourists varies significantly with the seasons, with certain months experiencing higher footfall than others. This study aims to predict tourist arrivals in the region using various factors such as month, temperature, number of local events, and hotel prices. A preexisting dataset comprising 100 records was utilized for the analysis. Two predictive models were developed: Decision Tree Regression and Generalized Regression Neural Network (GRNN). The performance of both models was evaluated using standard metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>). The Decision Tree Regression model demonstrated moderate predictive capability with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of approximately 44.94%, whereas the GRNN model underperformed, yielding a negative R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value. Based on these results, the Decision Tree model is considered more suitable for this application. The findings of this study may assist government bodies and tourism authorities in better planning and resource management during peak and off-peak tourist seasons.

Ҳали таржима қилинмаган