Time Series Machine Learning Model for Analyzing Growth of Insider Threats Across Global Sectors
Bibliographic record
Abstract
This research investigates the application of time-series machine learning models to quantify and forecast the growth of insider threats across global sectors. Insider incidents are increasingly recognized as high-impact risks, causing economic disruption and prolonged operational challenges. Open-source cyber incident data, comprising 3,000 records from 2015 to 2024, was analyzed. The data covers attributes such as country, year, attack type, industry, financial loss, affected users, vulnerabilities, and defense mechanisms. Prior studies have primarily focused on short-term anomaly detection, resulting in a research gap in long-range forecasting and sector-specific risk planning. The novelty of this study lies in moving beyond detection toward longitudinal forecasting of insider threat growth, integrating statistical modeling with industry-level impact profiling. An auto regressive Integrated Moving Average (ARIMA (0, 1, 1)) model was developed to forecast annual financial losses, with the model selected using AIC and residual diagnostics, and validated through RMSE and MAE metrics. Findings reveal that the IT, banking, and government sectors consistently incur the highest losses, while the healthcare and retail sectors are increasingly liable to these losses. Country-level analysis identified the United Kingdom as the most financially impacted. Attack vectors, like phishing, DDoS, and SQL injection, incur global loss, while ransomware continues to be a persistent burden. Practical implications include utilizing forecasted loss trends and multi-metric industry profiles, which encompass loss, incident frequency, and resolution time, to inform cyber budgeting, training, and insurance strategies. Compared to existing research emphasizing anomaly detection accuracy, this study highlights the value of predictive modeling for risk management.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".