An Optimal Composition of Market Samples for New Product Test Marketing

The development of new products is crucial for a business to maintain its competitive advantages, but the introduction of new products is risky. To avoid huge losses from launching unsuccessful products, marketers try to test the market potential of a new product in the early stages of the development process. It is not uncommon for a multi-store retail chain to test the potential profitability of a new product in a few selected stores before it introduces the product to the entire chain. Since test marketing would involve huge costs, marketers need to find a better way to select markets for accurate testing while keeping the number of test markets as low as possible. This study proposes a model to develop an optimal sampling network with which one can identify the optimal combination of markets for test marketing. Based on a simple demand model, an approach to find an optimal sampling network that would lead to an efficient estimate of the market size of a new product is developed. It is also demonstrated that the samples based on the proposed procedure produces a much more accurate estimate of the market size for a new product than randomly chosen samples do.