This paper aimed to develop a practical finite capacity material requirement planning (FCMRP) system based on the needs of an automotive-part manufacturing company in Thailand. The approach includes a linear programming model to determine the optimal start time of each operation to minimize the weighted average of total earliness, total tardiness, and average flow-time considering the finite capacity of all work centers and precedence of operations. Important factors of the proposed FCMRP system were objective function weights and dispatching rules. Effects of these factors on the performance measures were statistically analyzed based on a real situation of an auto-part factory. Statistical results showed that the dispatching rules and objective function weights had significant effects on the performance measures of the proposed FCMRP system. The proposed FCMRP system offered a good trade-off between conflicting performance measures and resulted in the best weighted average performance measure when compared with conventional forward and forward-backward finite capacity scheduling systems.