n the rota scheduling problem (RSP) in public bus transport, the re-serve shifts currently are evenly planned for all drivers without considering moredetailed information such as historical or weekday-depended sickness absence rates.In case that the absence rate exceeds the available reserve personnel, usually ad-ditional drivers are called manually. This causes discontent for the drivers as wellas continuous organizational effort for the bus company. In order to reduce thediscrepancy between a planned roster and the actual one, a new stochastic opti-mization model for the RSP is presented in this paper. In addition to the presentreserve shifts, optional reserve shifts are introduced