Using experimental design to find effective parameter settings for heuristics

In this paper, we propose a procedure, based on statistical design of exper iments and gradient descent, that finds effective settings for parameters f ound in heuristics. We develop our procedure using four experiments. We use our procedure and a small subset of problems to find parameter settings fo r two new vehicle routing heuristics. We then set the parameters of each he uristic and solve 19 capacity-constrained and 15 capacity-constrained and r oute-length-constrained vehicle routing problems ranging in size from 50 to 483 customers. We conclude that our procedure is an effective method that deserves serious consideration by both researchers and operations research practitioners.