The Credit card frauds represent facile and amiable targets, particularly as the proliferation of e-commerce and various online platforms has led to a commensurate expansion in online payment modalities, thereby augmenting the susceptibility to online fraudulent activities. In response to the escalating rates of fraudulent incidents, researchers have undertaken the utilization of diverse machine learning methodologies to ascertain and scrutinize frauds within the realm of online transactions. The primary objective of this scholarly endeavor is to formulate and advance an innovative fraud detection modus operandi tailored for Streaming Transaction Data. The overarching goal is to meticulously scrutinize the historical transaction particulars of patrons and distill discernible behavioral patterns. This involves the clustering of cardholders into disparate cohorts predicated upon their transactional magnitudes. Subsequently, a sliding window strategy is employed to amalgamate transactions conducted by cardholders across distinct groups, facilitating the extraction of their respective behavioral patterns. Consecutively, diverse classifiers trained on these distinct groups, and the classifier exhibiting superior rating scores is earmarked as one of the preeminent methods for prognosticating fraudulent activities. This is succeeded by the implementation of a feedback mechanism aimed at mitigating the challenges posed by the phenomenon of concept drift. The empirical investigation detailed in this paper is grounded in the analysis of a European credit card fraud dataset. It is imperative for credit card companies to adeptly discern instances of fraudulent credit card transactions to preclude customers from incurring charges for items they did not legitimately acquire. The resolution to such quandaries lies in the realm of Data Science, a discipline whose significance, when coupled with Machine Learning, is of paramount importance. This undertaking endeavors to elucidate the construction of a model utilizing machine learning techniques for Credit Card Fraud Detection. The Credit Card Fraud Detection Problem entails the modeling of historical credit card transactions, incorporating data from those that transpired as fraudulent. Subsequently, this model is employed to ascertain the veracity of new transactions, distinguishing between fraudulent and non-fraudulent activities. The primary aim is the meticulous detection of 100% of fraudulent transactions, while concurrently minimizing instances of erroneous classifications of non-fraudulent transactions. Credit Card Fraud Detection serves as a quintessential exemplar of classification challenges. In the course of this endeavor, significant emphasis has been placed on the analysis and pre-processing of datasets. Furthermore, a diverse array of anomaly detection algorithms, including the Local Outlier Factor and Isolation Forest algorithm, have been deployed on Principal Component Analysis (PCA) transformed Credit Card Transaction data. KEYWORDS: Card-Not-Present frauds, Card-Present-Frauds, Concept Drift,,Credit card fraud, applications of machine learning, data science.