ABSTRACT :

Fraudulent transactions have a huge impact on the economy and trust of a blockchain network. Consensus algorithms like proof of work or proof of stake can verify the validity of the transaction but not the nature of the users involved in the transactions or those who verify the transactions. This makes a blockchain network still vulnerable to fraudulent activities. One of the ways to eliminate fraud is by using machine learning techniques. Machine learning can be of supervised or unsupervised nature. In this paper, we use various supervised machine learning techniques to check for fraudulent and legitimate transactions. We also provide an extensive comparative study of various supervised machine learning techniques like decision trees, Naive Bayes, logistic regression, multilayer perceptron, and so on for the above task .

EXISTING SYSTEM :

The problem of detecting fraudulent transactions is being studied for a long time. Fraudulent transactions are harmful to the economy and discourage people from investing in bitcoins or even trusting other blockchain-based solutions. Fraudulent transactions are usually suspicious either in terms of participants involved in the transaction or the nature of the transaction. Members of a blockchain network want to detect Fraudulent transactions as soon as possible to prevent them from harming the blockchain network’s community and integrity. Many Machine Learning techniques have been proposed to deal with this problem, some results appear to be quite promising [4], but there is no obvious superior method. This paper compares the performance of various supervised machine learning models like SVM, Decision Tree, Naive Bayes, Logistic Regression, and few deep learning models in detecting fraudulent transactions in a blockchain network. Such comparative study will help decide the best algorithm based on accuracy and computational speed trade-off. Our goal is to see which users and transactions have the highest probability of being involved in fraudulent transactions.

DISADVANTAGES OF EXISTING SYSTEM :

1) Less accuracy

2)low Efficiency

PROPOSED SYSTEM :

The workflow for detecting fraudulent activity is summarised in Figure 1. Essentially, after the Blockchain network has approved a transaction after all basic checks, our proposed system kicks in and does additional checks to detect if the transaction can be fraudulent. This approach makes sure that there is no extra overhead of even checking the transactions that the Blockchain network itself can easily invalidate.

The work done can be divided mainly into three phases:

1. Preprocessing phase

2. Building and training various models

3. Performance evaluation of all the models.

ADVANTAGES OF PROPOSED SYSTEM :

1) High accuracy

2)High efficiency

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10