Credit card fraud detection is an important aspect of financial institutions that provide various online payment services to its customers. One of criteria which affect performance of credit card fraud detection models is the selection of variables. This paper studies the effects of feature engineering on two sets of feature ranked imbalanced credit card fraud datasets for four classifier techniques. This paper employs the credit card fraud datasets (Taiwan and European bank) obtained from UCI and ULB repositories containing 30,000 and 284,807 transactions respectively. Feature ranking on the sets of datasets is carried out using correlation analysis technique. Algorithms of four classifiers are produced and used on feature and raw ranked data. The algorithms of the classifiers are run in MATLAB. The performance metrics applied in assessing the effects of the four classifiers on the feature and raw ranked datasets are specificity, precision, Matthews correlation coefficient, sensitivity, accuracy, and balanced classification rate. Results from the comparative analysis show that decision tree variants classifiers outperform naïve bayes, support vector and neural network radial basis function techniques respectively. The feature ranked and raw datasets of the European credit card fraud data recorded highest performance metrics for decision trees. The paper investigates the effect of feature ranking of two imbalanced credit card fraud data on four machine learning techniques using filter approach.