This study demonstrates improved threat detection in cybersecurity using behavioural analytics and machine learning, suggesting significant advancements in risk management.
Key Points
The system achieved an impressive mean accuracy of 95.9% in detecting anomalies, indicating strong performance in cybersecurity risk management.
Utilizing nearly 411,000 records from multiple datasets, the research showcased effective application of machine learning techniques for real-time analysis.
A hybrid deep learning model combining CNN and LSTM was employed, enhancing the capture of spatial-temporal features in user behaviour data.
The findings highlight the importance of integrating human factors and advanced technologies for proactive cybersecurity solutions in dynamic environments.