• Higher population size increases chances of finding the optimal solution but also increases the time and resources needed
  • Higher crossover rate leads to faster convergence as it combines the beneficial traits from different individuals more frequently. Extremely high crossover rates may lead to premature convergence
  • Higher mutation rate maintains genetic diversity and prevents getting stuck at a local optimum. Extremely high mutation rates may cause the algorithm to struggle at finding a solution
  • Too narrow bounding parameters means that you may miss finding the optimum and if they’re too wide, time and resources to find the solution will increase
  • Way too high elitism can cause premature convergence