Hybrid models improve visitor forecasting for Nebraska lakes
A Hybrid Visitor Prediction Framework using Interpretable Temporal features, Integrating IQR and Anomaly Detection in Lakes in Nebraska
Machine Learning
Summary
Predicting how many people will visit lakes helps manage resources and plan facilities. The authors created a method that uses simple time-related data and cleans unusual visit numbers to make forecasts better. They combined several prediction models and found that removing weird data and adding past visit trends helped. Their best combined model was more accurate than standard methods, especially when using anomaly detection to clean data.
What this means in practice
- •For tourism planners: Adjust daily operational plans at lakes by using improved forecasts of visitor numbers that account for past trends and remove data errors.
- •For environmental resource managers: Manage lake resources sustainably with better daily visitation predictions that include cleaned data and combined modeling approaches.
Authors
Israt Zarin, Christopher Chizinski
Abstract
For effective resource management, infrastructure planning, and sustainable tourism, it is really important to predict accurate visitors. This paper estimates the daily visitation of Nebraska lakes using spatial, basic temporal, and interpretable temporal features. Moreover, we evaluate the base models with multiple metrics. Using the best three models, our method will ensemble hybrid models and choose the best hybrid technique. Further, we investigate the impact of lag features and how the models work with different outlier detection techniques such as Interquartile Range (IQR) and anomaly detection. The models are evaluated using regression metrics (MAE, MSE, RMSE, MAPE, and R2). Experiment results show that, after removing anomalies, MAE, MSE, RMSE, and MAPE are reduced. Adding lag features also shows some positive effects on the results. Moreover, anomaly detection techniques perform better than IQR in improving performance while preserving data. The reported anomaly-based cross-validation results favored the voting ensemble over the compared base models on the evaluated metrics. In anomaly-based cross-validation, VOTE improved prediction errors compared with MLP (256,128,64); improvements varied in the single-split comparison. Specifically, the hybrid model reduced MAE by 9.82%, MSE by 3.12%, RMSE by 1.76%, and MAPE by 6.77%. In the reported cross-validation comparison, the best anomaly-based hybrid model had lower MAE, MSE, RMSE, and MAPE than the best IQR-based hybrid model by 9.81%, 34.30%, 18.99%, and 0.66%, respectively.