This paper presents an efficient approach for a one-dimensional cutting stock problem for the roll-based manufacturing industry. The problem described in this paper has been investigated by many researchers using integer programming, meta-heuristics, and hybrid method. GA(Genetic Algorithm) is a method of meta-heuristics and we improved the GA method. In the real application, demand should always be satisfied with minimum the trim loss and this means that the solution of the CSP (Cutting Stock Problem) should be guaranteed to meet the demand perfectly. The existing GA approach deals with the shortage of demand as a penalty function, so infeasible solutions degrade the performance during solution search. We suggested an efficient GA approach considering the non-generation of infeasible solutions and a heuristic to determine the production quantity in the evaluation stage without searching the production quantity. We compared our method with a existing GA method to verify the superiority of our method.