Enhancing Financial Risk Management in Cryptocurrency Markets Through Machine Learning Analysis
Keywords:
Chartered Professional Accountants Canada (CPAC), Hierarchical Risk Parity (HRP), Anti-Money Laundering (AML), Support Vector Machines (SVM), Logistic Regression Models (LRM), Machine Learning (ML), Decision Tree Classifier (DTC), Naive Bayes (NB)Abstract
This project aims to develop a sophisticated risk analysis system which is capable of providing analysis for cryptocurrency transactions to determine if there is any potential risk involved. This project focuses on analysing the risks associated with cryptocurrency and developing a risk management framework using Hierarchical Risk Parity (HRP) and supervised machine learning. It aims to assess the intrinsic risks of cryptocurrency, particularly regarding the likelihood of occurrence and financial impact. The project also aims to rank exchange-level control risks and identify the highest likelihood risks within the cryptocurrency ecosystem. The proposed system utilizes HRP for cryptocurrency portfolio management based on machine learning techniques. It delves into the realm of professional accounting concerning the risks associated with cryptocurrencies and how these risks are anticipated to influence financial statements. Additionally, it aims to find intrinsic risks negatively correlated with cryptocurrency. In conclusion, the project employs Machine Learning (ML) and HRP for risk management in cryptocurrency networks. Machine learning techniques, providing high-performance evaluations due to its learning-based approach. HRP demonstrates superior diversification properties, enhancing risk management outcomes. Subsequent research endeavours will expand upon the suggested methodology by incorporating out-of-sample testing performance and optimization strategies to elevate risk management effectiveness.
