Marketing optimization models are defined by the "4P" marketing decision variables: Product (Does the product/service meet the needs of the customer?) , Price (re: list price, discounts, financing, leasing, allowances, etc.), Place (re: location, channel, market coverage, internet, etc.), and Promotion (re: advertising, public relations, message, media, etc.). Marketing optimization models are concerned with either 1) the individual effect of a marketing decision variable, and/or the interaction effects of combinations of the variables, or 2) the levels of the marketing mix variables, as to their optimal effect on the target variable. The target variable is a performance measure, such as sales, market share, or profitability. There are many statistical marketing optimization modeling approaches, which are based on a pre-selected inflexible parametric, assumption-full model. The purpose of this article is to present an alternative flexible nonparametric, assumption-free approach - the GenIQ Model
©. The GenIQ Model (based on genetic programming; not calculus as used in statistical modeling optimization) let's the data determine the model itself, along with optimizing the target variable. Two cases studies show that the genetic approach to the marketing optimization modeling problem is quite promising.