Open Access

ARTICLE

Analyzing Human Trafficking Networks Using Graph-Based Visualization and ARIMA Time Series Forecasting

Naif Alsharabi^1,*, Akashdeep Bhardwaj^2,*

1 College of Computer Science and Engineering, University of Hail, Hail, 81481, Saudi Arabia
2 Centre for Cybersecurity, School of Computer Science, UPES, Dehradun, 248007, India

* Corresponding Authors: Naif Alsharabi. Email: ; Akashdeep Bhardwaj. Email:

Journal of Cyber Security 2025, 7, 135-163. https://doi.org/10.32604/jcs.2025.064019

Received 01 February 2025; Accepted 26 May 2025; Issue published 18 June 2025

Abstract

In a world driven by unwavering moral principles rooted in ethics, the widespread exploitation of human beings stands universally condemned as abhorrent and intolerable. Traditional methods employed to identify, prevent, and seek justice for human trafficking have demonstrated limited effectiveness, leaving us confronted with harrowing instances of innocent children robbed of their childhood, women enduring unspeakable humiliation and sexual exploitation, and men trapped in servitude by unscrupulous oppressors on foreign shores. This paper focuses on human trafficking and introduces intelligent technologies including graph database solutions for deciphering unstructured relationships and entity nodes, enabling the comprehensive visualization of datasets linked to the scourge of human trafficking. The authors propose an autoregressive integrated moving average (ARIMA) time series model, showcasing its remarkable accuracy in forecasting temporal trends within the dataset’s timeframe. The research analysis leverages a comprehensive human trafficking dataset from Kaggle, comprising 48,800 records encompassing 63 distinct attributes. The findings underscore the effectiveness of the proposed model, revealing a compelling correlation between the predictions generated by the model and the actual values embedded in the dataset.

---

Keywords

---