Aim: The goal of this study is to provide an improved accuracy for credit card fraud detection using pipelining and ensemble learning methods in logistic regression compared with k-nearest neighbor algorithms to detect credit card fraud and comparing their accuracy. Materials and Methods: The sample size for logistic regression (N=10) and for K-nearest neighbor algorithm (N=10) was iterated 20 times to predict credit card fraud. Results : logistic regression has significantly better accuracy (98%) compared to k-nearest neighbor (94%)The statistical significance difference 0.00(p<0.05 independent sample test) value states that the results in the study are significant. Conclusion: The results depicted that logistic regression provides good results in detection of credit card fraud over k-nearest neighbor.