Over the past 15 years large systems integrators have grown in size by an order of magnitude. During this time the nature of the systems we build, the manner in which they are built, and the clients for whom they are built have seen corresponding growth. During this talk I will review some of these changes and discuss some of the challenges we see on the horizon as these trends continue. What kind of systems would a systems integrator with 2 million people develop? How would they be built?

This paper describes an Intelligent Shopping Assistant designed for a shopping cart mounted tablet PC that enables individual interactions with customers. We use machine learning algorithms to predict a shopping list for the customer's current trip and present this list on the device. As they navigate through the store, personalized promotions are presented using consumer models derived from loyalty card data for each inidvidual. In order for shopping assistant devices to be effective, we believe that they have to be powered by algorithms that are tuned for individual customers and can make accurate predictions about an individual's actions. We formally frame the shopping list prediction as a classification problem, describe the algorithms and methodology behind our system, and show that shopping list prediction can be done with high levels of accuracy, precision, and recall. Beyond the prediction of shopping lists we briefly introduce other aspects of the shopping assistant project, such as the use of consumer models to select appropriate promotional tactics, and the development of promotion planning simulation tools to enable retailers to plan personalized promotions delivered through such a shopping assistant.

This paper describes a prototype that predicts the shopping lists for customers in a retail store. The shopping list prediction is one aspect of a larger system we have developed for retailers to provide individual and personalized interactions with customers as they navigate through the retail store. Instead of using traditional personalization approaches, such as clustering or segmentation, we learn separate classifiers for each customer from historical transactional data. This allows us to make very fine-grained and accurate predictions about what items a particular individual customer will buy on a given shopping trip.We formally frame the shopping list prediction as a classification problem, describe the algorithms and methodology behind our system, its impact on the business case in which we frame it, and explore some of the properties of the data source that make it an interesting testbed for KDD algorithms. Our results show that we can predict a shopper's shopping list with high levels of accuracy, precision, and recall. We believe that this work impacts both the data mining and the retail business community. The formulation of shopping list prediction as a machine learning problem results in algorithms that should be useful beyond retail shopping list prediction. For retailers, the result is not only a practical system that increases revenues by up to 11%, but also enhances customer experience and loyalty by giving them the tools to individually interact with customers and anticipate their needs.

How do we know if we can afford a particular purchase? We can find out what the payments might be and check our balances on various accounts, but does this answer the question? What we really need to know is how this purchase would affect our other goals. What do I have to give up to afford this purchase?Personal Choice Point is a financial planning tool that addresses these questions by enabling a user to explore the repercussions of her decisions at the level of her lifestyle goals, not just her accounts. The user is presented with a graphical representation of primary lifestyle goals such as home, car, vacation, education, etc. As the user selects goals and modifies them, it presents the impact on the users life by graphically depicting the impact of a decision on her other goals. In effect, Personal Choice Point is a planner that helps restrict the users search for a suitable allocation of resources among goals to the likely set of allocations, from the much larger space of possible ones. The result is a system that changes the focus of the users task from managing the mechanics of resource allocation to the evaluation and selection of likely ones

Current data mining techniques usually do not have a mechanism to automatically infer semantic features inherent in the data being "mined". The semantics are either injected in the initial stages (by feature construction) or by interpreting the results produced by the algorithms. Both of these techniques have proved effective but require a lot of human effort. In many domains, semantic information is implicitly available and can be extracted automatically to improve data mining systems. In this paper we present a case study of a system that is trained to extract semantic features for apparel products and populate a knowledge base with these products and features. We show that semantic features of these items can be successfully extracted by applying text learning techniques to the descriptions obtained from websites of retailers. We also describe several applications of such a knowledge base of product semantics that we have built including recommender systems and competitive intelligence tools and provide evidence that our approach can successfully build a knowledge base with accurate facts which can then be used to create profiles of individual customers, groups of customers, or entire retail stores.