Abstract
The sophistication of covert activities employed by criminal networks with technology has been proven to be very challenging for criminal enforcement fraternity to cripple their activities. In view of this, law enforcement agencies need to be equipped with criminal network analysis (CNA) technology which can provide advanced and comprehensive intelligence to uncover the primary members (nodes) and associations (links) within the network. The design of tools to predict links between members mainly rely on Social Network Analysis (SNA) models and machine learning (ML) techniques to improve the precision of the model. The primary challenge of constructing classical ML models such as random forest (RF) with an acceptable level of accuracy is to obtain a large enough dataset to train the model. Obtaining a large enough dataset in the domain of criminal networks is a significant problem due to the stealthy and covert nature of their activities compared to social networks. The main objective of this research is to demonstrate that a link prediction model constructed with a relatively small dataset and dataset generated through self-simulation by leveraging on deep reinforcement learning (DRL) can contribute towards higher precision in predicting links. The training of the model was further fused with metadata (i.e. environment attributes such as criminal records, education level, age and police station proximity) in order to capture the real-life attributes of organised crimes which is expected to improve the performance of the model. Therefore, to validate the results, a baseline model designed without incorporating metadata (CNA-DRL) was compared with a model incorporating metadata (MCNA-DRL).
Highlights
Members of organised crimes often work together to form a resilient and flexible structure to execute their covert and stealthy activities [1]
The proposed MCNA-deep reinforcement learning (DRL) model and criminal network analysis (CNA)-DRL models are evaluated based on the area under curve (AUC) score which is a typical technique adopted to evaluate the precision of the classification models [13]
To train the CNA-DRL and MCNA-DRL models, the dataset is formulated into a feature matrix whereby each state of the network represents the formation or cessation of an edge
Summary
Members of organised crimes often work together to form a resilient and flexible structure to execute their covert and stealthy activities [1]. SNA which combines knowledge of graph theory and the discipline of social science [3] is a common method employed to analyse the criminal network to uncover hidden structural relationships and key players in criminal syndicates [4,5]. These SNA applications have a graphical interface that provides a comprehensive visual topological analysis of domain with network orientated dataset [6]. In the topological analysis of criminal network, environmental factors that can affect the evolving formations of links between participants of the network have to be taken into consideration [8] These factors such as criminal records, education level, age and family background (Fig. 1) are known as metadata. They provide further circumstantial information that may affect structural patterns of a criminal network over a period of time [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
