Abstract: Data mining were employed for the optimization of material release of PCB (Printed Circuit Board) template. PCB scrap ratio related parameters were specified and prediction model variables were chosen according to hypothesis test. Multiple linear regression (MLR), Chi-squared automatic interaction detector, artificial neural network and support vector machine approaches for the prediction of scrap ratio were employed. Evaluation indictors called as superfluous ratio, supplement release ratio and weighted sum of the two were presented; the material release simulation was conducted and then the four approaches were compared and MLR was taken as the preferred one. Adjust coefficient was introduced and optimized according to factory’s cost model. Finally, material release tool were developed and verified. Comparison results shown that superfluous and supplement release ratio has significant reduction which indicates that the approach can systematically reduce the cost of material release, waste of inventory, tardiness and so on.

Key words: PCB, scrap ratio, data mining, prediction, optimization of material release