Bank currency is our country's most valuable asset, therefore it's no surprise that criminals would attempt to exploit this by flooding the financial market with counterfeit bills that seem quite similar to the real thing. Fake bills are prevalent in the economy when demonetization occurs. Since many qualities of a forged note are identical to those of an actual one, it is often impossible for a person to distinguish between the two without the use of different factors meant for identification. Identifying genuine banknotes from counterfeits is a difficult undertaking. It follows that a fully automated system, accessible through bank tellers and ATMs, is required. Due to the accuracy with which counterfeit banknotes are produced, it is imperative that an effective algorithm be developed to determine whether or not a given banknote is real. In this research, we use six supervised machine learning methods to the dataset for detecting Bank money authenticity that is accessible in the UCI machine learning repository. We used a variety of machine learning methods, including Support Vector Machines, Random Forests, Logistic Regressions, Naive Bayes, Decision Trees, and K-Nearest Neighbours, with three different train test ratios (80:20, 70:30, and 60:40) and analysed their results using a number of different quantitative metrics. For a subset of train test ratios, certain SML algorithms can guarantee a perfect 100% success rate.