I know that is possible for a genetic algorithm to not have a mating phase because some genetic algorithms use a "mutation-only" approach, where new candidate solutions are generated by randomly mutating existing solutions without crossover.

But what about creating a genetic algorithm that does not include crossover and mutation? Is that a good approach?

I am thinking of creating a recommendation service that retrieves audio files from the database. This service uses an algorithm that calculates the fitness score of each individual based on some properties of that file and after that, I sort the individuals based on the fitness score and get the best candidate.

But at this point isn't that just a "scoring" algorithm and not a genetic one? Or that's perfectly fine to call it like that?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.