A Fuzzy Profit Maximization Model using Communities Viable Leaders for Information Diffusion in Dynamic Drivers Collaboration Networks

Assigning shipping orders to the most appropriate driver in the shortest time but with the highest profit is one of the major concerns of transportation companies. Many studies have been conducted on transportation service procurement systems, however, due to the lack of a framework for modeling human interactions, none of them has used the concept of information diffusion for this purpose. In this study, a monoplex weighted drivers collaboration network is developed to model drivers' relationships, within the transportation system. Besides, to identify and track communities during a given time interval of the network, a new community detection algorithm (CDA), called dynamic overlapping community detection (DOCD) algorithm, is designed, which can identify viable leaders in each community. In addition to detecting community leaders, the algorithm is able to monitor, assess and detect the durability of these community leaders over time, which other algorithms are not able to. To evaluate the performance of the algorithm, it is compared with 5 different algorithms in terms of 14 evaluation measures. The results show the proposed DOCD algorithm outperforms the other algorithms with an 88% superiority in the evaluation measures. Then, a fuzzy profit maximization model is developed using information diffused by the identified communities' viable leaders and information diffusion power of each community. Analyzing a real case study obtains two achievements in the form of "high-risk scenario" and "low-risk scenario" for well-known and novice transportation companies, respectively. Therefore, the obtained results show that transportation companies allocate orders to drivers, based on their reputation and risk levels.