Evolutionary optimization of flavors

We have acquired panelist data that provides hedonic (liking) ratings for a set of 40 flavors each composed of the same 7 ingredients at different concentration levels. Our goal is to use this data to predict other flavors, composed of the same ingredients in new combinations, which the panelist will like. We describe how we first employ Pareto-Genetic Programming (GP) to generate a surrogate for the human panelist from the 40 observations. This surrogate, in fact an ensemble of GP symbolic regression models, can predict liking scores for flavors outside the observations and provide a confidence in the prediction. We then employ a multi-objective particle swarm optimization (MOPSO) to design a well and consistently liked flavor suite for a panelist. The MOPSO identifies flavors that are well liked (high liking score), and consistently-liked (of maximum confidence). Further, we generate flavors that are well and consistently liked by a cluster of panelists, by giving the MOP...

• Type: Conference
• Year: 2010
• Where: GECCO
• Authors: Kalyan Veeramachaneni, Katya Vladislavleva, Matt Burland, Jason Parcon, Una-May O'Reilly
• Keywords: GECCO 2010, Liking Score, Optimization, Panelist, Panelist Data