Spatio-Temporal Network Based Bank Transactional Behaviour Analysis to Detect Suspicious Activities

Money laundering is the illicit practice of changing black money into white money. Criminal organizations that want to make effective use of money obtained illegally must engage in money laundering. Money laundering is also linked to other crimes, including the financing of terrorism, drug trafficking, and corruption. In this project, we propose a transactional network and behavior analysis system that utilizes Long Short-Term Memory (LSTM) to identify and stop money laundering operations using two key components: (i) customer risk profiling and (ii) reporting questionable activity. The proposed system uses historical financial data in a time-series format to train the LSTM network and identify patterns and trends that are associated with money laundering activities. By analyzing the data in a time-series format, LSTM can identify unusual patterns of transactions and flag them for further investigation. The system provides a more efficient and accurate method for identifying potential money laundering activities, ultimately leading to a more effective and efficient anti-money laundering framework.