From Data Mining to Knowledge Discovery in Databases

Model search can consist of greedy hill climbing

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: both the structure and the parameters of graphic models can be learned directly from databases (Buntine 1996; Heckerman 1996). Model-evaluation criteria are typically Bayesian in form, and parameter estimation can be a mixture of closed-form estimates and iterative methods depending on whether a variable is directly observed or hidden. Model search can consist of greedy hill-climbing methods over various graph structures. Prior knowledge, such as a partial ordering of the variables based on causal relations, can be useful in terms of reducing the model search space. Although still primarily in the research phase, graphic model induction methods are of particular interest to KDD because the graphic form of the model lends itself easily to human interpretation. Relational Learning Models Although decision trees and rules have a representation restricted to propositional logic, relational learning (also known as inductive logic programming) uses the more flexible pattern language of first-order logic. A relational learner can easily find formulas such as X = Y. Most research to date on model-evaluation methods for relational learning is logical in nature. The extra representational power of relational models comes at the price of significant computational demands in terms of search. See Dzeroski (1996) for a more detailed discussion. Discussion Given the broad spectrum of data-mining methods and algorithms, our overview is in- 48 AI MAGAZINE evitably limited in scope; many data-mining techniques, particularly specialized methods for particular types of data and domains, were not mentioned specifically. We believe the general discussion on data-mining tasks and components has general relevance to a variety of methods. For example, consider timeseries prediction, which traditionally has been cast as a predictive regression task (autoregressive models, and so on). Recently, more general models have been developed for time-series applications, such as nonlinear basis functions, example-based models, and kernel methods. Furthermore, there has been significant interest in descriptive graphic and local data modeling of time series rather than purely predictive modeling (Weigend and Gershenfeld 1993). Thus, although different algorithms and applications might appear different on the surface, it is not uncommon to find that they share many common components. Understanding data mining and model induction at this component level clarifies the behavior of any data-mining algorithm and makes it easier for the user to understand its overall contribution and applicability to the KDD process. An important point is that each technique typically suits some problems better than others. For example, decision tree classifiers can be useful for finding structure in high-dimensional spaces and in problems with mixed continuous and categorical data (because tree methods do not require distance metrics). However, classification trees might not be suitable for problems where the true decision boundaries between classes are described by a second-order polynomial (for example). Thus, there is no univ...
View Full Document

This document was uploaded on 02/15/2014.

Ask a homework question - tutors are online