will not be "much worse" (in a precise technical sense) than the predictions made by the best reasonably small pruning of the given decision tree. Thus, our procedure is guaranteed to be competitive (in terms of the quality of its predictions) with any pruning algorithm. We prove that our procedure

We design ecient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a

the process. On each step, the algorithm tentatively prunes each of the remaining features, selects the best, and generates a new tree with one fewer attribute. This continues until the accuracy of the best pruned tree is less than the accuracy of the current one. Unlike Focus and Schlimmer's method

Abstract not found

Most decision tree classifiers are designed to keep class histograms for single attributes, and to select a particular attribute for the next split using said histograms. In this paper, we propose a technique where, by keeping histograms on attribute pairs, we achieve (i) a significant speed

Abstract—This paper considers the problem of piecewise linear prediction from a competitive algorithm approach. In prior work, prediction algorithms have been developed that are “universal” with respect to the class of all linear predictors, such that they perform nearly as well, in terms of total

ABSTRACT This paper presents semantics query optimization on distributed database using Decision Tree algorithm based on that. Whenever user query from server the master sever can process the query of user from different server's database in Heterogeneous environment on alternative basis

clustering algorithms like K mean and DBSCAN. The classification model was used as predictive model to quantify prediction of a place given a combination of explanatory variables like frequency and duration. Different classifiers like KNN, Naïve Bayes, and Decision Trees were used to build the predictive

.5 decision tree (Breiman’s Bagging, Ho’s Random subspaces, their combination we labeled ‘Bagfs’, and Breiman’s Random forests) and five large benchmark data bases. It is worth noticing that the proposed procedure may easily be extended to other base learning algorithms than a decision tree as well

validation: a protocol can use data traffic as active topology probes, quickly discovering and fixing routing loops. The second is adaptive beaconing: by extending the Trickle code propagation algorithm to routing control traffic, a protocol sends fewer beacons while simultaneously reducing its route repair