Data-driven operations management in bike sharing systems

The self-service bike sharing systems, which offer an environmentally friendly option for the first-and-last mile transportation, have become prevalent in urban cities. In this dissertation, I aim to integrate the advanced Data Mining techniques and Operations Management algorithms for bike sharing system daily operations management, service area expansion, and station site selection. Daily Operations Management. Due to the geographical and temporal unbalance of bike usage demand, a number of bikes need to be reallocated among stations during midnight so as to maintain a high service level of the system. To conduct such bike rebalancing operations, I develop a bike demand predictor for station pick-up demand and drop-off demand prediction. Then, a Mixed Integer Linear Programming (MILP) model is formulated to optimize the routing problem of rebalancing vehicles. To address the challenge of computational efficiency, I propose a data-driven hierarchical optimization methodology to decompose the multi-vehicle routing problem into smaller and localized single-vehicle routing problems. Expansion Area Demand Analysis. Another key to success for a bike sharing systems expansion is the bike demand prediction for expansion areas. I develop a hierarchical station bike demand predictor which analyzes bike demands from functional zone level to station level. Specifically, I first divide the studied bike stations into functional zones by a novel Bi-clustering algorithm which is designed to cluster bike stations with similar POI characteristics and close geographical distances together. Then, the hourly bike check-ins and check-outs of functional zones are predicted by integrating three influential factors: distance preference, zone-to-zone preference, and zone characteristics. The station demand is estimated by studying the demand distributions among the stations within the same functional zone. Station Site Location Selection. In an ideal bike sharing network, the station locations are usually selected in a way that there are balanced pick-ups and drop-offs among stations. This can help avoid expensive re-balancing operations and maintain high user satisfaction. Here I propose a bike sharing network optimization approach based on an Artificial Neural Network for station demand prediction and a Genetic Algorithm for station site optimization. The goal is to enhance the quality and efficiency of the bike sharing service by selecting the right station locations.Ph.D.Includes bibliographical reference