These are all interesting, innovative projects, mainly in cybersecurity or IT Operations, and reliant upon use of AI.
Automated anomaly/threat detection
A valuable addition to a strong security management posture. Heuristics and ML algorithms mines network traffic data for botnets, scripts or other threats that can take out a network. Especially when these threats are complex, multi-vector and layered, AICHOO machine learning exposes patterns that can undermine business service availability.
Justification is reduced loss of service, reduced threat of ransomware, plus consequential losses from failure to implement.
Intelligent alerting
By ingesting data from different systems within the IT environment, AICHOO filters and correlates the data into meaningful incidents. This helps prevent alert storms coming from domino effects—for example, a failure in System A triggers an alert, impacting system B, which also triggers an alert, and so on. Intelligent alerting also reduces alert fatigue and helps with prioritization based on user and business impact. A self-learning system will identify patterns and use its consequent predictions to reduce the impact of future, identical or similar storms. The quantity of data involved meant a linear programming or rules-based approach was infeasible.
Justification: lowers manpower requirement, improves effectiveness by reducing number of incidents requiring manual investigation.
Cross-domain situational understanding
AICHOO aggregates all the data and creates causality/relationship analyses, providing IT with an overview of consequences, and providing a better understanding of the situation. Uses a combination of big data analytics tools for comprehension and reporting, and a self-learning AI system to predict potential or probable outcomes of changes.
[Project in planning phase]
Justification: Improves impact analysis, allows resources to be used more effectively.
Automating identification of (probable) root causes
IT is presented with the top suspected causes of alerts, plus evidence. Transparency and feedback enable AICHOO to learn from human expertise. After root-cause alerts and issues are confirmed, subject matter experts are alerted for faster remediation.
Justification: reduces manpower hours spent on troubleshooting.
Cohort analysis
Analysis of related items while studying and predicting user behavior. Within a highly distributed architecture where tens of thousands of instances are running at the same time, AICHOO identifies outliers in configuration or deployed application versions. Used for system tuning and performance improvement, plus cybersecurity.
[Project in planning phase]
Justification: reduces man hours required in system optimisation and security.
Automated remediation
AICHOO drives automated remediation for known issues, using historical data from past issues. Extracts root cause inferences from infrastructure alerts and route them automatically to relevant sector experts, reducing time to fix.
Justification: addresses service and security issues arising from spikes in demand.
Employee Risk analysis
AICHOO predicts which employees may pose an internal cybersecurity or other risk. Aggregates employee online-behaviour data with employee HR records from point of recruitment onward.
Justification: risk reduction
Note: restricted geographical use as not legal in all jurisdictions.