Effective IT change management is important for businesses that depend on software and services, particularly in highly regulated sectors such as finance, where operational reliability, auditability, and explainability are essential. A significant portion of IT incidents are caused by changes, making it important to identify high-risk changes before deployment. This study presents a predictive incident risk scoring approach at a large international bank. The approach supports engineers during the assessment and planning phases of change deployments by predicting the potential of inducing incidents. To satisfy regulatory constraints, we built the model with auditability and explainability in mind, applying SHAP values to provide feature-level insights and ensure decisions are traceable and transparent. Using a one-year real-world dataset, we compare the existing rule-based process with three machine learning models: HGBC, LightGBM, and XGBoost. LightGBM achieved the best performance, particularly when enriched with aggregated team metrics that capture organisational context. Our results show that data-driven, interpretable models can outperform rule-based approaches while meeting compliance needs, enabling proactive risk mitigation and more reliable IT operations.
Figures & tables
LightGBM
Metric
Base
HGBC
XGB
Without
With
Threshold
60
99
98
17
29
Precision
0.04
0.02
0.05
0.02
0.04
wR
0.56
0.86
0.89
0.91
0.93
w F2
0.88
0.88
0.90
0.92
0.93
AUC
0.55
0.61
0.71
0.67
0.60
Table 1. Performance of Baseline, ML Models, and LightGBM with and without Additional Features
Figure 1. Feature Importance of LightGBM. Horizontal bar chart showing the top 15 features ranked by SHAP values for the LightGBM model. Higher values indicate a greater importance of a feature to the model’s predictions across the evaluation set. The plot highlights the relative influence of textual, configuration-related, and temporal features in identifying incident-inducing changes (RQ2).
Figure 2. Sliding Window of Baseline vs. LightGBM Performance.
Figure 3. Feature Importance of LightGBM with Additional Features. Horizontal bar chart showing the top 15 features ranked by SHAP values for the LightGBM model extended with additional features. Higher values indicate a greater importance of a feature to the model’s predictions across the evaluation set. The figure illustrates how textual, organisational, configuration-related, and operational metrics contribute to identifying incident-inducing changes (RQ3).
Figure 4. Top 10 SHAP Values for Two Example Changes.
Technology change management in large financial institutions depends on risk assessments that are accurate, consistent, and auditable. In practice, many institutions still rely on self-reported questionnaires. Those questionnaires are subjective, easy to game, and poor at separating routine changes from the ones that later trigger major incidents. This paper presents SENTRY, a risk assessment platform that replaces questionnaire-based scoring with a deterministic machine learning pipeline built from gradient-boosted decision trees (XGBoost) and hybrid retrieval-augmented generation (RAG). The system combines structured operational metadata, application dependency graphs, and historical incident records with a hybrid semantic and lexical search over historical change requests. The retrieval step captures the risk signal in unstructured change request text, then compresses that signal into a single scalar feature before model inference. That design keeps the model deterministic and preserves per-prediction explainability via SHAP values. Evaluated on enterprise-scale change data, SENTRY achieves a ROC AUC of 0.87 and 85% overall accuracy, and it detects high-risk changes at roughly 3.25 times the rate of the existing process. We close by examining the architectural trade-offs behind this design and what they imply for the use of machine learning in regulated change management.
Daniel Arulpragasam, Christer Henrysson, Ella Ly +2
Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible explanations. In the context of just-in-time defect prediction, highlighting small portions of a software change (diff) -- beyond rule-based lints -- where risk may be concentrated has not yet been extensively investigated. In this work, we leverage attention weights from an LLM-based Diff Risk Score (DRS) model to highlight parts of a diff that the model focuses on when predicting risk. We aggregate token-level attention into interpretable code units (lines, hunks, and files), and present the top-K units to developers as a lightweight form of guidance during code review. We evaluate our approach using expert-labeled changes that have caused real outages. Results show that the highlighted snippets cover expert-labeled outage-causing change lines 53.85% of the time when highlighting the top-2 hunks, while requiring developers to review 26.28% of the changed lines on average. Because attention is produced during standard model inference, the approach is scalable for large development workflows and can be surfaced in the code review UI with low additional latency.
At Amazon Prime Video, we face the critical operational challenge of managing code deployments during live events and rapid feature releases without causing service outages. Current change control approaches use blanket deployment freezes that block all changes regardless of risk, creating significant developer toil. While prior research has explored risky change predictors, these rely on developer-specific metadata or extensive historical data, raising privacy concerns and limiting applicability to new projects. We introduce a framework centered on diff-aware features, characteristics derived directly from code modifications. Our key contribution is the systematic identification of which quantitative metrics (code-level and change-level metrics) and qualitative indicators (coding style violations, change type classification) are necessary for risk prediction. We employ LLMs as multi-language feature extractors, demonstrating their effectiveness for code analysis beyond generation tasks and eliminating the need for language-specific tooling. We evaluated our framework on two datasets: Prime Video's production environment and the public ApacheJIT dataset. Our best-performing model achieves an average recall of 0.83 and F1 score of 0.81 across both datasets for detecting risky code changes. Notably, ablation analysis reveals that change-level volume metrics (e.g., lines added/deleted) are noisy predictors, while structural code complexity provides a substantially stronger risk signal. These results demonstrate that thoughtful feature curation enables effective change risk assessment across different programming languages and organizational contexts while avoiding privacy concerns.
Mayur Kurup, Hyunjae Suh, Swathi Vaidyanathan +3
Amazon.com Austin, Texas, USA · University of California Irvine, California, USA · Amazon.com Seattle, Washington, USA