Establishing Model Risk Management
http://ccro.org © Copyright 2025, CCRO. All rights reserved. 11
4. Model Usage
Energy markets are highly volatile, subject to complex valuation drivers, and can often lack
transparent observable data. Input data can often be dependent on relationships with other
data, tenors, locations, and data sources. Beyond those factors, the energy sector faces ongoing
complexity due to the influences of weather, logistics, geopolitics, environmental changes,
social and governance factors, consumer preferences, and physical market structure changes.
For example, power markets are subject to real-time hourly spot electricity prices, non-standard
price determination processes for renewables, grid/transmission reliability, zonal or nodal price
spreads, and a complex interplay between environmental events, generation performance,
available capacity, and variable load demand. As such, our members have observed an
organizational need and focus on a wide variety of financial and operational models to manage
both their business and system reliability.
Energy also has diverse use cases for models beyond traditional financial and credit risk
management activities. For example, operational safety and reliability are highly valued in the
energy sector, as are supply security, optimal asset utilization, portfolio valuation, financial
planning and analysis, and long-term forecasting. The advent of Big Data, Artificial Intelligence
(“AI”) and Machine Learning (“ML”) has further fueled the use of complex models and a need
for traceability.
With increased usage comes increased responsibility. The Committee of Chief Risk Officers
(“CCRO”) recommends its members develop MRM framework suitable to their specific lines of
business and risk profiles. Recognizing an opportunity to efficiently convey an industry
perspective, the CCRO formed a dedicated MRM Working Group (the “Working Group”) to
consider the issue and publish this position paper.
http://ccro.org © Copyright 2025, CCRO. All rights reserved. 11
4. Model Usage
Energy markets are highly volatile, subject to complex valuation drivers, and can often lack
transparent observable data. Input data can often be dependent on relationships with other
data, tenors, locations, and data sources. Beyond those factors, the energy sector faces ongoing
complexity due to the influences of weather, logistics, geopolitics, environmental changes,
social and governance factors, consumer preferences, and physical market structure changes.
For example, power markets are subject to real-time hourly spot electricity prices, non-standard
price determination processes for renewables, grid/transmission reliability, zonal or nodal price
spreads, and a complex interplay between environmental events, generation performance,
available capacity, and variable load demand. As such, our members have observed an
organizational need and focus on a wide variety of financial and operational models to manage
both their business and system reliability.
Energy also has diverse use cases for models beyond traditional financial and credit risk
management activities. For example, operational safety and reliability are highly valued in the
energy sector, as are supply security, optimal asset utilization, portfolio valuation, financial
planning and analysis, and long-term forecasting. The advent of Big Data, Artificial Intelligence
(“AI”) and Machine Learning (“ML”) has further fueled the use of complex models and a need
for traceability.
With increased usage comes increased responsibility. The Committee of Chief Risk Officers
(“CCRO”) recommends its members develop MRM framework suitable to their specific lines of
business and risk profiles. Recognizing an opportunity to efficiently convey an industry
perspective, the CCRO formed a dedicated MRM Working Group (the “Working Group”) to
consider the issue and publish this position paper.
