IT Operations Automation · Risk Management
The bank wanted a proactive way to monitor a complex IT environment, predict critical service outages, and reduce the impact of infrastructure failures on customers and employees.
Reported impact
The bank can predict high-priority incidents affecting customer-critical systems up to four weeks in advance, improve IT service management quality, reduce outage risk, increase resilience and reliability, and support quarterly regulatory reporting.
DXC worked with the bank’s IT team to build an AIOps-based predictive outage solution for a complex banking estate. Historical system-level log data and service-management metrics from hundreds of banking systems, including customer-facing platforms and back-end credit card and processing systems, were ingested and analyzed to identify patterns linked to future incidents. DXC data scientists used a design thinking process, SME interviews, workshops, and feature engineering to select and productionise 700 features inside the bank’s big data cluster. An AIOps model then continuously observes operating signals, generates outage likelihood risk scores, and feeds iterative learnings back into the model for ongoing accuracy improvement. The resulting predictions and next-best-action insights are surfaced in a dashboard so service managers can intervene before failures occur, and the same data also supports quarterly APRA regulatory reporting.
Historical log and service-management data from hundreds of customer-facing and back-end banking systems are ingested into the bank’s big data cluster, where 700 engineered features were productionised. The AIOps model analyzes three years of incident data, generates outage risk scores and next-best-action insights, and publishes warnings to a dashboard used by service managers and for APRA regulatory reporting.
"700 features were selected and productionised within the bank’s big data cluster, ensuring the creation of the most accurate algorithms."
"DXC data scientists used a design thinking approach and worked hand in hand with the bank to design, prototype and build AI models to consume historical system-level log data from hundreds of banking systems."
"It has fundamentally changed the bank’s approach to system outages — with the ability to predict issues up to four weeks out."
"The objective of this project was to create and support a robust solution that could predict outages in the bank’s IT environment."
"The resulting model uses data, AI and ML to analyse various service management metrics, identify patterns and produce a risk score determining the likelihood of future outages or incidents."
"the data is also used to support quarterly regulatory reporting to the Australian Prudential Regulation Authority (APRA)."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Oct 20, 2025 BNY BNY wanted to scale AI adoption across the company without fragmented point solutions, while maintaining strong governance, risk management, compliance controls, and practical support for workflows such as payments,… 75% more AI solutions in production compared to the prior quarter Contract Review Assistant · Eliza · Eliza agents 
AWS Sample Jul 23, 2026 BBVA As BBVA expanded the number and diversity of AI and ML solutions across the bank, it needed a more flexible, scalable, and automated MLOps architecture that improved code reuse, reproducibility, version control, and… 20% to 75% reduction in development times ADA · AWS Lambda · Amazon EventBridge 
OpenAI Sample Jul 7, 2026 Australian Payments Plus AP+ needed a secure way for employees to move faster through complex payment, identity, and reconciliation work while preserving the governance, accuracy, and accountability demanded by a regulated payments environment. 1 day to build working simulations with Codex ChatGPT Enterprise · Codex 