Prediction-based One-shot Dynamic Parking Pricing

TL;DR

This paper introduces a prediction-driven framework using neural ordinary differential equations for dynamic parking pricing, enabling rapid one-shot optimization to match targeted occupancy rates efficiently.

Contribution

It presents a novel combination of NODE-based occupancy prediction with a one-shot price optimization method for dynamic parking management.

Findings

Prediction model outperforms existing forecasting methods in accuracy.

One-shot optimization significantly reduces search time and finds optimal prices.

Framework tested with real data from San Francisco and Seattle.

Abstract

Many U.S. metropolitan cities are notorious for their severe shortage of parking spots. To this end, we present a proactive prediction-driven optimization framework to dynamically adjust parking prices. We use state-of-the-art deep learning technologies such as neural ordinary differential equations (NODEs) to design our future parking occupancy rate prediction model given historical occupancy rates and price information. Owing to the continuous and bijective characteristics of NODEs, in addition, we design a one-shot price optimization method given a pre-trained prediction model, which requires only one iteration to find the optimal solution. In other words, we optimize the price input to the pre-trained prediction model to achieve targeted occupancy rates in the parking blocks. We conduct experiments with the data collected in San Francisco and Seattle for years. Our prediction model shows the best accuracy in comparison with various temporal or spatio-temporal forecasting models. Our one-shot optimization method greatly outperforms other black-box and white-box search methods in terms of the search time and always returns the optimal price solution.