The resulting greedy GA favours objects with higher value densities when it builds random chromosomes, in crossover, and in mutation. The greedy heuristics do well, as does the naive GA, but the greedy GA exhibits the best performance. Genetic algorithms initiate the process of evolution on an optimization problem This system is combined greedy idea and genetic algorithm to form the greedy genetic algorithm which incorporates the global exploring ability of the genetic algorithm and the local convergent ability of the greedy algorithm. In this system, population evolution utilizes quantity of sales for cosmetic goods as integer variables. And this system includes fitness function for requirement of profit amount and quantity of products can be calculated by the specific formula. Then, the selection is performed with method of roulette wheel selection. The final result is the forecasting of cosmetic goods for monthly. The greedy genetic algorithm (GGA) always chooses the best goods during the crossover and mutation process according to their fitness values.