As digital infrastructure expands in new regions of the globe, developing ways to include more diverse information in financial decisions is important. However, making use of novel data sources requires developing methods to evaluate credit with diverse and complex datasets with missing information, dynamic patterns and relationships with decision recommendations, and larger feature sets. Feature selection is one approach that can support the application of machine learning to dynamically build models for credit evaluation with complex data. Genetic algorithms (GAs) have been proved to reach good performance in other research, with high computation cost though. In this paper, we review existing GA approaches and test and develop a novel method based on niching and the use of subpopulations with different data for fitness evaluation. This formulation allows less computation cost, even with better prediction performance in feature selection. In further experiments, we compare the proposed GA-based feature selection approaches in four traditional credit datasets and a novel emerging market dataset from China. The results indicate that the advanced GA-based feature selection methods perform more effectively.