Parking search identification in vehicle GPS traces

The challenge of “cruising for parking” in urban areas has long been a subject of study, but existing research often relies on biased surveys or arbitrary assumptions in the absence of ground truth data. This paper addresses these gaps by introducing the first-ever collection of ground truth data on parking search durations gathered through a self-developed app. The dataset encompasses more than 3500 journeys collected in Germany, with approximately two-thirds of them ending in Frankfurt am Main. Utilizing this unique dataset, we developed a deep learning neural network model that accurately identifies parking search routes in GPS data and predicts search duration. Our model outperforms existing parking search identification models proposed in previous studies. The model’s efficacy is further evaluated on an independent park-and-visit dataset and then applied to a large-scale dataset from Frankfurt/Germany. This generates the first reliable statistics on parking search durations and reveals key insights about parking search patterns in this city. Notably, the predicted mean parking search duration from this extensive dataset, comprising over 860,000 journeys, is approximately 1.5 min. This work not only advances the field by providing a new data collection methodology and a superior predictive model but also offers a reusable framework that can be applied to other cities and datasets for broader urban mobility insights. • Novel deep learning model identifies parking search in GPS data. • Model trained and validated with two distinct datasets, shows high accuracy. • Outperforms existing heuristic models significantly, achieving an MAE under a minute. • Applied to over 860,000 journeys, revealing Frankfurt’s parking search patterns. • Model integration potentially enables real-time parking guidance in navigation apps.