What can data mining and knowledge management do? Optimize inventory levels, detect fraud, identify target customers, and forecast demand, answers Amar Gupta, co-director of the Productivity from Information Technology Program at MIT's Sloan School of Management. His study of retail distribution led to a new approach that enabled retail distribution organizations to decrease inventory levels by 50%, yet still maintain a 90% customer satisfaction level. He used a neural network, an approach to computer architecture and programming that emulates human brain functions, to study customer demand patterns for different items at different stores. The work was funded in part by the Defense Logistics Agency and the Defense Advanced Research Projects Agency.