Bringing forecasting into the future: Using Google to predict visitation in U.S. national parks.

摘要: In recent years, visitation to U.S. National Parks has been increasing, with the majority of this increase occurring in a subset parks. As result, managers these parks must respond quickly increasing visitor-related challenges. Improved forecasting would allow more proactively plan for such increases. study, we leverage internet search data that is freely available through Google Trends create model. We compare model traditional autoregressive Overall, our accurately predicted 97% total variation all one year advance from 2013 2017 and outperformed by metrics. While performs better overall, was not case each park unit individually; accuracy varied significantly park. hypothesized attributes related trip planning correlate model, but none variables tested produced overly compelling results. Future research can continue exploring utility forecast visitor use protected areas, or methods demonstrated paper explore alternative sources improve Parks.