A Machine Learning Approach for Modelling Parking Duration in Urban Land-use

TL;DR

This paper develops an interpretable machine learning model using neural networks and explanation techniques to predict parking durations based on socioeconomic and travel data, aiding urban land-use planning in developing countries.

Contribution

It introduces a novel approach combining ANNs with LIME and Garson algorithms for interpretable parking duration prediction in urban land-use contexts.

Findings

LIME provides higher prediction accuracy and interpretability.

The model effectively predicts parking durations for different land-uses.

Policy recommendations are derived from model insights.

Abstract

Parking is an inevitable issue in the fast-growing developing countries. Increasing number of vehicles require more and more urban land to be allocated for parking. However, a little attention has been conferred to the parking issues in developing countries like India. This study proposes a model for analysing the influence of car users' socioeconomic and travel characteristics on parking duration. Specifically, artificial neural networks (ANNs) is deployed to capture the interrelationship between driver characteristics and parking duration. ANNs are highly efficient in learning and recognizing connections between parameters for best prediction of an outcome. Since, utility of ANNs has been critically limited due to its Black Box nature, the study involves the use of Garson algorithm and Local interpretable model-agnostic explanations (LIME) for model interpretations. LIME shows the prediction for any classification, by approximating it locally with the developed interpretable model. This study is based on microdata collected on-site through interview surveys considering two land-uses: office-business and market/shopping. Results revealed the higher probability of prediction through LIME and therefore, the methodology can be adopted ubiquitously. Further, the policy implications are discussed based on the results for both land-uses. This unique study could lead to enhanced parking policy and management to achieve the sustainability goals.