Predictive models in direct marketing seek to identify individuals most likely to respond to promotional solicitations or other intervention programs. While standard modeling approaches embody single objectives, real-world decision problems often seek multiple performance measures. Decision-makers here desire solutions that simultaneously optimize on multiple objectives, or obtain an acceptable tradeoff amongst objectives. Multi-criteria problems often characterize a range of solutions, none of which dominate the others with respect to the multiple objectives - these specify the Pareto-frontier of nondominated solutions, each offering a different level of tradeoff. This paper proposes the use of evolutionary computation based procedures for obtaining a set of nondominated models with respect to multiple stated objectives.

We present an approach to learning cooperative behavior of agents. Our approach is based on classifying situations with the help of the nearest-neighbor rule. In this context, learning amounts to evolving a set of good prototypical situations. With each prototypical situation an action is associated that should be executed in that situation. A set of prototypical situation/action pairs together with the nearest-neighbor rule represent the behavior of an agent. We demonstrate the utility of our approach in the light of variants of the well-known pursuit game. To this end, we present a classification of variants of the pursuit game, and we report on the results of our approach obtained for variants regarding several aspects of the classification. A first implementation of our approach that utilizes a genetic algorithm to conduct the search for a set of suitable prototypical situation/action pairs was able to handle many different variants. 1 Introduction Designing a set of agents and ...

This article presents a genetic algorithm-based approach for obtaining models in explicit consideration of this mailing depth. Issues related to overfitting, common in application of machine learning techniques, are examined, and experiments are based on a real-life data set

Lists of if-then rules (i.e. ordered rule sets) are among the most expressive and intelligible representations for inductive learning algorithms. Two extreme strategies searching for such list of rules can be distinguished (i) local strategies primarily based on a step by step search for the optimal list of rules, and (ii) global strategies primarily based on a one strike search for the optimal list of rules. Both approaches have their disadvantages. In this paper we present a intermediate strategy. A sequential covering strategy is combined with a one-strike genetic search for the most promising next rule. To achieve this, a new rule-fitness function is introduced. Experimental results are reported in which the learning results of our intermediate approach are compared to other rule learning algorithms. 1 Introduction Inductive learning typically involves a search through a large hypothesis space to find the hypothesis that covers the training data and that general...

Currently, evolutionary computation (EC) typically takes place in batch mode: algorithms are run autonomously, with the user providing little or no intervention or guidance. Although it is rarely possible to specify in advance, on the basis of EC theory, the optimal evolutionary algorithm for a particular problem, it seems likely that experienced EC practitioners possess considerable tacit knowledge of how evolutionary algorithms work. In situations such as this, computational steering (ongoing, informed user intervention in the execution of an otherwise autonomous computational process) has been profitably exploited to improve performance and generate insights into computational processes. In this short paper, prospects for the computational steering of evolutionary computation are assessed, and a prototype example of computational steering applied to a coevolutionary algorithm is presented.

This paper reports briefly on the development of a new approach to evolutionary computation, called the Learnable Evolution Model or LEM. In contrast to conventional Darwinian-type evolutionary algorithms that employ mutation and/or recombination, LEM employs machine learning to generate new populations. At each step of evolution, LEM determines hypotheses explaining why certain individuals in the population are superior to others in performing the designated class of tasks. These hypotheses are then instantiated to create a next generation. In the testing studies described here, we compared a program implementing LEM with selected evolutionary computation algorithms on a range optimization problems and a filter design problem. In these studies, LEM significantly outperformed the evolutionary computation algorithms, sometimes speeding up the evolution by two or more orders of magnitude in the number of evolutionary steps (births). LEM was also applied to a real-world problem of designing optimized heat exchangers. The resulting designs matched or outperformed the best human designs. 1

Abstract not found

Lists of if-then rules (i.e. ordered rule sets) are among the most expressive and intelligible representations for inductive learning algorithms. Two extreme strategies searching for such list of rules can be distinguished (i) local strategies primarily based on a step by step search for the optimal list of rules, and (ii) global strategies primarily based on a one strike search for the optimal list of rules. Both approaches have their disadvantages. In this paper we present an intermediate strategy. A sequential covering strategy is combined with a one-strike genetic search for the most promising next rule. To achieve this, a new rule-fitness function is introduced. Experimental results are reported in which the performance of our intermediate approach is compared to other rule learning algorithms. 1 Introduction Inductive learning typically involves a search through a large hypothesis space to find the hypothesis that covers the training data and that generalizes to unobs...

e-theses repository This unpublished thesis/dissertation is copyright of the author and/or third parties. The intellectual property rights of the author or third parties in respect of this work are as defined by The Copyright Designs and Patents Act 1988 or as modified by any successor legislation. Any use made of information contained in this thesis/dissertation must be in accordance with that legislation and must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the permission of the copyright holder. Neo-Darwinian evolution is an established natural inspiration for computational op-timisation with a diverse range of forms. A particular feature of models such as Genetic Algorithms (GA) [18, 12] is the incremental combination of partial solutions distributed within a population of solutions. This mechanism in principle allows cer-tain problems to be solved which would not be amenable to a simple local search.

Many metaheuristics have difficulty exploring their search space comprehensively. Exploration time and efficiency are highly dependent on the size and the ruggedness of the search space. For instance, the Simple Genetic Algorithm (SGA) is not totally suited to traverse very large landscapes, especially deceptive ones. The approach introduced here aims at improving the exploration process of the SGA by adding a second search process through the way the solutions are coded. An “observer ” is defined as each possible encoding that aims at reducing the search space. Adequacy of one observer is computed by applying this specific encoding and evaluating how this observer is beneficial for the SGA run. The observers are trained for a specific time by a second evolutionary stage. During the evolution of the observers, the most suitable observer helps the SGA to find a solution to the tackled problem faster. These observers aim at collapsing the search space and smoothing its ruggedness through a simplification of the genotype. A first implementation of this general approach is proposed, tested on the Shuffled Hierarchical IF-and-only-iF (SHIFF) problem. Very good results are obtained and some explanations are provided about why our approach tackles SHIFF so easily.