Evolutionary model tree induction

• Ano de defesa: 2009
• Autor(a) principal: Barros, Rodrigo Coelho
• Orientador(a): Ruiz, Duncan Dubugras Alcoba
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Pontifícia Universidade Católica do Rio Grande do Sul; Porto Alegre
• Palavras-chave em Português: INFORMÁTICA; MINERAÇÃO DE DADOS (INFORMÁTICA); ALGORITMOS
• Link de acesso: http://hdl.handle.net/10923/1687

Model trees are a particular case of decision trees employed to solve regression problems, where the variable to be predicted is continuous. They have the advantage of presenting an interpretable output, helping the end-user to get more confidence in the prediction and providing the basis for the end-user to have new insight about the data, confirming or rejecting hypotheses previously formed. Moreover, model trees present an acceptable level of predictive performance in comparison to most techniques used for solving regression problems. Since generating the optimal model tree is a NPComplete problem, traditional model tree induction algorithms make use of a greedy top-down divideand- conquer strategy, which may not converge to the global optimal solution. In this work, we propose the use of the evolutionary algorithms paradigm as an alternate heuristic to generate model trees in order to improve the convergence to global optimal solutions. We test the predictive performance of this new approach using public UCI data sets, and we compare the results with traditional greedy regression/model trees induction algorithms. Results show that our approach presents a good tradeoff between predictive performance and model comprehensibility, which may be crucial in many data mining applications.