Analysis of the impact of policy measures on parking behavior using interpretable time series models

Growing awareness of the environmental impact of abundant parking has led to recent measures focused on decreasing car use in urban areas. This paper employs interpretable time series models to analyze the effects of these measures on parking demand. The study utilizes a dataset of more than 22 million parking transactions from 3,594 on-street selling points and 8 park-and-ride (P&R) locations in Amsterdam. Three models with external regressors, namely, Error Trend Seasonality (ETSX) models, Seasonal Autoregressive Integrated Moving Average (SARIMAX) models, and Interpretable Multi-Variate Long Short-Term Memory (IMV-LSTM) models, are compared against a Seasonal Naïve benchmark model. The ETSX model achieved the lowest error values, as indicated by both RMSE and SMAPE. The results show a significant decrease in parking (up to a 77% decline), primarily attributed to the tariff change, which had a greater impact than the introduction of a metro line. Moreover, both measures caused a shift in parking to P&R locations and peripheral areas. The introduction of the metro line led to more parking near a new metro station. In addition, COVID-19 measures resulted in a significant decrease in parking demand. These results are presented in an application that visualizes the influence of external regressors on parking ticket demand.

• View at Publisher

Free Full Text ( Final Version , 1mb )