The need for technology has always found space in Financial Transaction as the number of fraud in financial transactions increases day by day. In this research we have proposed a new methodology by using the isolation forest algorithm and local outlier detection algorithm to detect the financial fraud. A standard data set is used in experimentation to classify a transaction occurred is a fraudulent or not. We have used neural networks and machine learning for classification. We have focused on the deployment of anomaly detection algorithms that is Local Outlier Factor and Isolation Forest algorithm (IFA) on financial fraud transactions data.