Learn More
The application of boosting procedures to decision tree algorithms has been shown to produce very accurate classiiers. These classi-ers are in the form of a majority v ote over a n umber of decision trees. Unfortunately, these classiiers are often large, complex and diicult to interpret. This paper describes a new type of classiication rule, the alternating(More)
Much recent attention, both experimental and theoretical, has been focussed on classi-cation algorithms which produce voted combinations of classiiers. Recent theoretical work has shown that the impressive generalization performance of algorithms like Ad-aBoost can be attributed to the classiier having large margins on the training data. We present an(More)
Much recent attention, both experimental and theoretical, has been focussed on classii-cation algorithms which produce voted combinations of classiiers. Recent theoretical work has shown that the impressive generalization performance of algorithms like AdaBoost can be attributed to the classiier having large margins on the training data. We present abstract(More)
Recent theoretical results have shown that the generalization performance of thresh-olded convex combinations of base classiiers is greatly improved if the underlying convex combination has large margins on the training data (correct examples are classiied well away from the decision boundary). Neural network algorithms and AdaBoost have been shown to(More)
We describe KDD-Cup 2000, the yearly competition in data mining. For the first time the Cup included insight problems in addition to prediction problems, thus posing new challenges in both the knowledge discovery and the evaluation criteria, and highlighting the need to " peel the onion " and drill deeper into the reasons for the initial patterns found. We(More)
Standard ambulatory night sleep electroencephalograph (EEG) of 11 long-term practitioners of the Transcendental Meditation (TM) program reporting "higher states of consciousness" during sleep (the experimental group) was compared to that of nine short-term practitioners and 11 non-practitioners. EEG tracings during stages 3 and 4 sleep showed the(More)
The architecture of Blue Martini Software's e-commerce suite has supported data collection, transformation, and data mining since its inception. With clickstreams being collected at the application-server layer, high-level events being logged, and data automatically transformed into a data warehouse using meta-data, common problems plaguing data mining(More)
We show that the e-commerce domain can provide all the right ingredients for successful data mining and claim that it is a killer domain for data mining. We describe an integrated architecture, based on our experience at Blue Martini Software, for supporting this integration. The architecture can dramatically reduce the pre-processing, cleaning, and data(More)