Advanced analytics for digital utilities

Explore use cases and perspectives

Machine intelligence represents the next chapter in the advanced analytics journey. Cognitive systems employ technology and algorithms to automatically extract concepts and relationships from data and “understand” their meaning, learn independently from data patterns and prior experience, and extend what either humans or machines could do on their own. Recent advances in computer vision, pattern recognition, and cognitive analytics are making it possible for companies to shine a light on untapped sources of nontraditional data – image, audio, and video files, machine and sensor information generated by IoT, and raw data found in the “deep web”–to derive insights that can lead to better experiences and decision-making across the business. In addition, machine intelligence provides the algorithmic capabilities that can augment employee performance, automate increasingly complex workloads, and develop “cognitive agents” that simulate both human thinking and engagement.

Safety analytics

Health and safety advanced analytics reduce safety risk.

Advanced analytic models leverage data from various sources (e.g., employee time and attendance, employee leave, telematics, prior incidents, weather incidents, etc.) to identify and profile common characteristics or data attributes of high-risk employees from a safety perspective. Using this model, safety incidents are predicted by leveraging knowledge from past experiences (safety incidents, near misses, etc.). When individuals are in an error-prone situation, information is shared from past experiences to lessen the chance of safety incidents.

Back to top

Labor compliance automation

Advanced analytics proactively monitor US labor compliance.

A custom advanced analytic solution proactively monitors US based locations for potential violations of the Fair Labor Standards Act ("FLSA"). The solution incorporates a range of analytics including advanced visual and geospatial capabilities. Additionally, a risk sensing mechanism focuses investigational efforts with statistical prioritization of locations. The solution allows legal and compliance groups to focus on very specific FLSA risks (i.e. minimum wage violations, overtime, undocumented employees, etc.), as well as regional trends.

Back to top

FCPA analytics

Analytics to detect potential Foreign Corrupt Practices Act (FCPA) violations by third party intermediaries.

Third party intermediaries pose potential reputational, compliance, and financial risks for companies under the Foreign Corrupt Practice Act (FCPA), with 90 percent of FCPA cases involving third parties. Typical risks include unauthorized and illegal payments, engaging with prohibited parties, fraudulent invoices, illegal bidding practices, bribery and corruption, and violation of laws. Supervised and unsupervised (automated) analytic techniques on both structured and unstructured data can help identify potential violations and other emerging global risks. Benefits of running potential FCPA violation analytics include increased visibility into actions of third party intermediaries, reduced reputational, compliance, finance risk, and reduced FPCA monitoring costs.

Back to top

Trade surveillance

Advanced analytics for detecting fraud, market abuse, supervisory failures, and other risks associated with trading operations.

A combination of structured and unstructured analytics as well as basic monitoring algorithms detect potential trading issues. Structured data tools and technologies perform network analysis, trading pattern recognition, clustering and segmentation analysis, and risk scoring. Unstructured analytics evaluate text and voice communications, while basic monitoring algorithms watch for violations of rules and thresholds. This provides advanced detection of trading fraud, abuse, and other issues to reduce trading risk and minimize associated costs.

Back to top

Advanced inventory management analytics

Advanced analytics are used to identify anomalous end user behaviors.

Advanced analytics identify unexpected bulk spares (e.g. spare parts, service items, tools, etc.), inventory consumption, and adjustments resulting in abuse, misuse, or fraud while root cause analysis identifies discrepancies in process cycle movements (e.g., in-transit between shipping locations) and segregation of duty violations. Analytics are customized based on regional preferences and activities to obtain a deeper insight to appropriate inventory movements. Application of advanced analytics will help reduce cost leakage, better understand inventory changes, and improve reporting capabilities.

Back to top

Did you find this useful?