A machine learning approach for modelling parking duration in urban land-use

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