Using Coevolution and Substitution of the Fittest for Health and Well-Being Recommender Systems

This research explores substitution of the fittest (SF), a technique designed to counteract the problem of disengagement in two-population competitive coevolutionary genetic algorithms. SF is domain independent and requires no calibration. We first perform a controlled comparative evaluation of SF's ability to maintain engagement and discover optimal solutions in a minimal toy domain. Experimental results demonstrate that SF performs similarly to alternative techniques presented in the literature but has the advantage of requiring no parameter tuning. We then address the more complex real-world problem of evolving recommendations for health and well-being. We introduce a coevolutionary extension of EvoRecSys, a previously published evolutionary recommender system. We demonstrate that SF is able to maintain a better trade-off between engagement and performance than other techniques in the literature, and the resultant recommendations using SF are higher quality and more diverse than those produced by EvoRecSys.