A simulation-based study to determine the negative externalities of hyper-local food delivery

Hyper-local food delivery involves delivering food from neighborhood eateries by gig workers, mostly using motorized two-wheelers. An accurate assessment of the negative external costs will help decision-makers sustainably regulate such services. As a first step, this research develops an agent-based simulation of a hyper-local food delivery system. Using primary data from Kolkata, India, the simulator estimates the fleet size, the average distance traveled per order, the average number of orders delivered and the average idle time spent by a delivery worker, at varying order volumes. The negative externalities estimated are the emissions per order and the spatio-temporal parking demand generated by the delivery fleet. The results show that at an order volume of 2100, on average, the distance traveled per order is 5.85 km, the orders delivered per worker is 15, the idle time spent is 59.2% and each delivery results in the emission of 163.08 gm CO2.