This document presents a parametric study aimed at enhancing the performance of genetic algorithms (GA) using a ranked-based roulette wheel selection method. The study investigates the effects of varying population size, mutation rate, and crossover rate on the GA's effectiveness in function optimization, revealing that optimal parameter settings significantly improve solution quality and algorithm reliability. The findings indicate that specific ranges for population size, crossover rate above 0.8, and mutation rate between 0.0035-0.0065 are crucial for achieving better results in solving complex optimization problems.