Free-Floating Micro-mobility Smart Redistribution Using Spatio-temporal Demand Forecasting

Micro-mobility refers to a variety of small and lightweight vehicles designed for individual use. These new vehicles are inexpensive, simple to operate, and enjoyable to ride, making them the easiest and most suitable mode of transportation for trips of less than five miles. They have become extremely popular, especially with the advent of free-floating systems that offer users flexible parking in order to facilitate the rental process. However, the problem of imbalance and maldistribution is among the major challenges of these systems, causing dissatisfaction and loss of customers. Therefore, to ensure the balancing of the fleet and to make the best decision for its reorganization, we must consider strategic locations that are accessible to all. In this paper, we propose a machine learning model for spatio-temporal demand forecasting using a multi-output regression technique. The main goal of the paper is to help pick the ideal areas for fleet deployment and balance the system according to user needs. Our solution, designed for public electric scooters, is based on the estimation of user demand over a grid-based service area. In addition, we propose an enhanced solution that outperforms other baseline models, including the Random Forest, Gradient Boosting, and Stacking Regressor.

I. Introduction

Nowadays, micro-mobility services have gained great popularity. E-scooters, bikes, or motorcycles are examples of micro-mobility devices that offer an attractive solution to minimize car dependency while helping cities achieve their social and environmental goals and improving road safety [1]. In fact, these lightweight travel vehicles are receiving significant attention due to their ecological character and their ability to solve problems such as traffic jams and increased carbon emissions [1]. Many companies are taking full advantage of the shift in people's perceptions towards this new means of transportation; bikes or e-scooters are used as a shared resource between several users, hence the term “shared micro-mobility”. Thanks to their market dominance, these companies provide rental services and improve operational efficiency. Except for a few minor structural variations, each of these companies has its own rental strategy and fleet structure. For the parking procedure, we generally have two operating modes: (i) a dock-based system, where the user is required to park at the nearest station in the service area, which facilitates the management of micro-vehicles; (ii) a free-floating system, which allows users to park the fleet freely, making the rental procedure more convenient and easier [2]. Despite being the most convenient mode, free-floating poses many regulatory challenges such as poorly parked fleets by users, maintenance difficulties, and unloaded fleet collection [3]–[5]. Furthermore, because of the uncontrolled parking system, fleets can be parked in irrelevant areas, leading to an unbalanced system.