Our experiments with capital markets data suggest that the domain can be effectively modeled by classification rules induced from available historical data for the purpose of making gainful predictions for equityinvestments. New classification techniques developed at IBM Research, including minimal rule generation (R-MINI) and contextual feature analysis, seem robust enough for consistently extracting useful information from noisy domains such as financial markets. We will briefly introduce the rationale for our minimal rule generation technique, and the motivation for the use of contextual information in analyzing features. We will then describe our experience from several experiments with the S&P 500 data, illustrating the general methodology, and the results of correlations and simulated managed investment based on classification rules generated by R-MINI. Wewillsketchhow the rules for classifications can be effectively used for numerical prediction, and eventually to an investment ...

. While many constructive induction algorithms focus on generating new binary attributes, this paper explores novel methods of constructing nominal and numeric attributes. We propose a new constructive operator, X-of-N. An X-of-N representation is a set containing one or more attribute-value pairs. For a given instance, the value of an X-of-N representation corresponds to the number of its attribute-value pairs that are true of the instance. A single X-of-N representation can directly and simply represent any concept that can be represented by a single conjunctive, a single disjunctive, or a single M-of-N representation commonly used for constructive induction, and the reverse is not true. In this paper, we describe a constructive decision tree learning algorithm, called XofN. When building decision trees, this algorithm creates one X-of-N representation, either as a nominal attribute or as a numeric attribute, at each decision node. The construction of X-of-N representations is carrie...

Most constructive induction researchers focus only on new boolean attributes. This paper reports a new constructive induction algorithm, called XofN, that constructs new nominal attributes in the form of X-of-N representations. An X-of-N is a set containing one or more attribute-value pairs. For a given instance, its value corresponds to the number of its attribute-value pairs that are true. The promising preliminary experimental results, on both artificial and real-world domains, show that constructing new nominal attributes in the form of X-of-N representations can significantly improve the performance of selective induction in terms of both higher prediction accuracy and lower theory complexity. 1 Introduction A well-known elementary limitation of selective induction algorithms is that when task-supplied attributes are not adequate for describing hypotheses, their performance in terms of prediction accuracy and/or theory complexity is poor. To overcome this limitation, constructiv...

ion for Modeling and Prediction C. Apte, S.J. Hong, J. Lepre, S. Prasad, and B. Rosen IBM Research Division Technical Report RC-20271 RAMP: Rules Abstraction for Modeling and Prediction Chidanand Apte, Se June Hong, Jorge Lepre, Seema Prasad, and Barry Rosen IBM T.J. Watson Research Center Yorktown Heights, NY 10598 January 12, 1996 Abstract Generating accurate and robust models is crucial to the successful use and deployment of classifiers on a large scale. Rule induction, i.e., generating decision rule models from data, is often a preferred approach to classification modeling and prediction, due to the enhanced explanatory capability and interpretability of decision rules. The RAMP system for rules abstraction and modeling is evolving with accuracy and robustness as primary goals. The system provides the following key capabilities: 1) feature analysis and selection based upon contextual merits technique, 2) "optimal" discretization of numerical features, 3) generation of m...

Abstract not found

A well-known fundamental limitation of selective induction algorithms is that when tasksupplied attributes are not adequate for, or directly relevant to, describing hypotheses, their performance in terms of prediction accuracy and/or theory complexity is poor. One solution to this problem is constructive induction. It constructs, by using task-supplied attributes, new attributes that are expected to be more appropriate than the task-supplied attributes for describing the target concepts. This thesis focuses on constructive induction with decision trees as the theory description language. It explores: (1) novel approaches to constructing new binary attributes using existing constructive operators, and (2) novel methods of constructing new nominal and new continuous-valued attributes based on a newly proposed constructive operator. The thesis investigates a fixed rule-based approach to constructing new binary attributes for decision tree learning. It generates conjunctions from producti...