Today companies keep a large number of important data, including the work they plan to do in the future,electronically. In many cases, financial information is stolen that can harm the entire company orindividual. One of these types of fraud occurs in bank payments. The use of graph data science augmentsexisting analytics and machine learning pipelines, increasing the accuracy and applicability of existingfraud detection methods. In this study, BankSim dataset created from a bank payment informationsimulation in Spain was used. It is aimed to detect fraud by classifying normal payments and injected fraudsignatures on BankSim. RandomForest (RF), SVM, XGBoost (XGB), K Nearest Neighbors (k-NN)classification algorithms in python language were used for classification. K-fold cross validation was usedfor performance evaluations. Neo4j database was used for graph analysis and CypherQL was used asNeo4j query language. The implementation of this fraud detection has resulted in fewer fraudulenttransactions and a more reliable revenue stream. The performances of SVM, RF, XGB, k-NN algorithmswere evaluated for fraud detection in bank payments, and the performance of the algorithms was comparedaccording to the K-Fold cross-validation results in terms of performance. In the graph mining phase, theresults obtained with the standard machine learning method were optimized together with graph algorithmssuch as PageRank, Community, and degree. In this respect, it has been proven that the use of graph miningand machine learning algorithms together has higher accuracy rates compared to other methods and is amethod that calculates in a faster time.