In this work we propose Dynamit, a monitoring framework to detect reentrancy vulnerabilities in Ethereum smart contracts. Dynamit extracts features from transaction data and uses a machine learning model to classify transactions as benign or harmful. In this work, we propose Contract Ward to detect vulnerabilities in smart contracts with machine learning techniques. The system is developed the different machine learning algorithm for detecting the vulnerability in smart contract effectively. The experimental results shows that accuracy, precision, recall, f1 score, ROC and confusion matrix.