Management of Bus Driver Duties Using Data Mining

This paper presents Bus Driver Allocation Problem (BDAP) which deals with the assignment of the drivers to the scheduled duties so that operations costs are minimized while its solution meets hard constraints resulting from the safety regulations of public transportation authorities as well as from the internal company’s agreements. Another concern in this study is the overall satisfaction of the drivers since it has important consequences on the quality and economic return of the company operations. This study proposes a non-dominated bi-criteria allocation approach of bus drivers to trips while minimizing the operations cost and maximizing the level of satisfaction of drivers. This paper proposes a new mathematical formulation to model the allocation problem. Its complexity has lead to solving the BDAP by using techniques such as: Genetic algorithms in order to assign the drivers with minimal operations cost and Fuzzy Logic and Rough Set techniques in order to fuzzyfied some parameters required for the satisfaction module followed by applying the Rough Set technique to evaluate the degree of satisfaction for the drivers. The application of the proposed approach to a medium size Transport Company Bus Driver Allocation Problem is evaluated.