Andrew E. Fano

The future of business services in the age of ubiquitous computing

Redefining the key aspects of the business-customer relationship.

Text mining for product attribute extraction

We describe our work on extracting attribute and value pairs from textual product descriptions. The goal is to augment databases of products by representing each product as a set of attribute-value pairs. Such a representation is beneficial for tasks where treating the product as a set of attribute-value pairs is more useful than as an atomic entity. Examples of such applications include demand forecasting, assortment optimization, product recommendations, and assortment comparison across retailers and manufacturers. We deal with both implicit and explicit attributes and formulate both kinds of extractions as classification problems. Using single-view and multi-view semi-supervised learning algorithms, we are able to exploit large amounts of unlabeled data present in this domain while reducing the need for initial labeled data that is expensive to obtain. We present promising results on apparel and sporting goods products and show that our system can accurately extract attribute-value pairs from product descriptions. We describe a variety of application that are built on top of the results obtained by the attribute extraction system.

Shopper's eye: using location-based filtering for a shopping agent in the physical world

1. ABSTRACT Agents of all types rely on easily computed features that are suggestive of a user’s preferences and goals to define and constrain their tasks. Although a person’s location is usually suggestive of their current activity, agents have not relied upon a user’s location to constrain their task. This is because users have typically used their computers only from home or work, and because location has not been easily computable. However the explosive growth in the use personal digital assistants (PDAs), laptop computers, and global positioning system (GPS) receivers is enabling people to use computers in the most remote of locations, and to have their location accessed by software.

Situated computing: bridging the gap between intention and action

Situated computing represents a new class of computing applications that bridges the gap between peoples intentions and the actions they can take to achieve those intentions. These applications are contextually embedded in real-world situations, and are enabled by the proliferation of new kinds of computing devices, expanding communication capabilities and new kinds of digital content. Three types of discontinuities give rise to intention/action gaps and provide opportunities for situated computing applications: physical discontinuities, information discontinuities and and awareness discontinuities. Several examples of applications that overcome these discontinuities are presented.

Predicting customer shopping lists from point-of-sale purchase data

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 shoppers 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.

Building intelligent shopping assistants using individual consumer models

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 customers 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 individuals 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.

Personal choice point: helping users visualize what it means to buy a BMW

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

Examples of commercial applications of ubiquitous computing

Emerging tools will simply transform business practices---and customer expectations---in the near future.

What are a Location’s “File” and “Edit” Menus?

Abstract: The promise of mobile devices lies not in their capacity to duplicate the capabilities of desktop machines, but rather in their promise of enabling location-specific tasks. One of the challenges that must be addressed if they are to be used in this way is how intuitive interfaces for mobile devices can be designed that enable access to location-specific services usable across locations. We are developing a prototype mobile valet application that presents location-specific services organised around the tasks associated with a location. The basic elements of the interface exploits commonalties in the way we address tasks at various locations just as the familiar “file” and “edit” menus in various software applications exploit regularities in software tasks.

Emerging challenges for large scale systems integration

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?