Population Diversity Control of Genetic Algorithm Using a Novel Injection Method for Bankruptcy Prediction Problem

Exploration and exploitation are the two main concepts of success for searching algorithms. Controlling exploration while executing search algorithm will enhance overall performance algorithm. usually controlled offline by proper settings parameters that affect population-based performance. In this paper, we proposed a dynamic controller one most well-known algorithms, which is Genetic Algorithm (GA). Population Diversity Controller-GA (PDC-GA) as novel feature-selection to reduce space building machine-learning classifier. The PDC-GA combining GA with k-mean clustering control population diversity through process. An injection method redistribute once 90% solutions located in cluster. A real case study bankruptcy problem obtained from UCI Machine Learning Repository used paper binary classification problem. results show ability approach machine learning classifiers range 1% 4%.