Market segmentation refers to "the subdividing of a market into distinct subsets of customers where any subset may conceivably be selected as a market target to be reached with a distinct marketing mix" [Kotler 1980]. The reason for segmenting a market is that consumers are often numerous, geographically dispersed, and heterogeneous, and therefore seek varying benefits from the products they buy. Consumers within a segment are expected to have homogeneous buying preferences whereas those in different segments tend to behave differently. By properly identifying the benefit segment of a firm's product, the marketing manager can target the sales effort at specific groups of consumers rather than at the total population. The identification of consumer segments is of critical importance for key strategic issues in marketing involving the assessment of a firm's opportunities and threats. The marketing manager must evaluate the potential of the firm's products in the target segment and ultimately select the most promising strategy for the segment. In thisresearch, we introduce a new approach, a neural networks based method, to discover market segments and configure them into meaningful structures. The particular type of neural networks, the Self-Organizing Map networks, can be used as a decision support tool for supporting strategic decisions involving identifying and targeting market segments. The Self-Organizing Map (SOM) network, a variation of neural computing networks, is a categorization network developed by Kohonen. The theory of the SOM network is motivated by the observation of the operation of the brain. This paper presents the technique of SOM and shows how it may be applied as a clustering tool to market segmentation. A computer program for implementing the SOM neural networks is developed and the results will be compared with other clustering approaches. The study demonstrates the potential of using the Self-Organizing Map as the clustering tool for market segmentation.