Supply chain management includes four major elements; namely, manufacturers, suppliers, distributors and retailers. Inventory control plays a very important role in each of the four modules in the supply chain. In this paper, a decision surface modeling tool is developed using neural networks. It is capable of capturing the essential features of the retail simulation model in multidimensional, mathematical relationships between performance (e.g., service level and lost sales) and key decision parameters (e.g., SKU mix and season length). The simulation model is used to generate the training data. Once trained, the neural network is able to predict performance for new sets of inputs in real-time and can be used to build an interactive, graphical representation of the input-performance relationships.