Test and learn: a virtuous cycle

Continuous evaluation and improvement of models

Turning your predictive analytics practices into a thriving model factory requires closing the loop from model creation, to performance monitoring, to problem and opportunity identification and subsequent model improvement, in a formal and disciplined way. This includes continuous measurement of each model, and creating a virtuous cycle of model improvement through portfolio management of your models.

Continuous measurement

Continuous measurement of model performance is about drawing insights from model performance, and identifying opportunities for model enhancement. You can find these opportunities by stratifying the customer population to isolate pools of customers who behave differently with respect to the predicted outcome; tuning the model for specific pools of risks that contribute to the predictive outcome in different ways; and adding new predictive drivers to the model to help address customer behavior not being explained effectively by the current model. Read More

Top Ten data science talent challenges

Successful talent recruitment, growth and retention

In the thirty-plus years I’ve worked with analytics organizations, management has faced several recurring challenges. Without an active (even if informal) practice to watch and react to these challenges, management will find their organizations becoming unable to cope with the ever-rising flood of requests that requires a capable, agile, powerful, happy and healthy analytics team. These Top Ten challenges are sorted in increasing order of strategic impact (i.e., from least to most), and in order of difficulty of detection and prevention (i.e., easiest to most difficult).

Read More

Lightning utility analytics video demo introduces better path to grid forecasting

Electric utility hourly demand forecasting for distribution planning

If your work for an electric utility is focused on the launch or plans for launching a grid modernization initiative, we know your load forecast needs. Critical from the start is ensuring your plan meets both top-down regulatory requirements and bottom-up distributed energy resource impacts.

If you’re like our other clients, including Southern California Edison, you’ll agree the ideal approach to effective grid modernization must be transparent and proven. It demands expertise and technology to design a modular strategy built on a scalable analytics platform. To address this business need, we introduced the Lightning solution in 2021.

Answering key questions to grid challenges

Our white box, service-based platform for tackling analytics for grid modernization was created based on the client questions we encounter when building a strategy. Getting to the bottom of the Where/When/Why and How of challenges impacting the grid – from location to cause and magnitude – is the basis for getting on a roadmap to addressing critical grid issues. This requires expertise across the data, grid and human factors influencing a reliable analytics-based forecast.

Corios Lightning is a distribution planning and forecasting solution that provides a ten-year hourly forecast of megawatt demand for every substation and feeder on your grid, adjusted for economic growth, load growth projects, capacity transfers and DER adoption.

Utility grid data at work

John Willey, lead designer and architect of Corios Lightining and the leader of our utility analytics practice, will guide you through the insights to be gained when applying Lightning at the foundation of distribution and asset planning efforts.

As you view the video walk through in the link below, take note of the proof in the example reports and discover the detail in the forecasting as it is applied to different scenarios that power planning engineers are considering as the future of power demands shift.

Want to learn more about Corios Lightning for your utility’s grid modernization? Send me a note directly to president@coriosgroup.com or use our contact us form to tell us more about your project.

Finding end-user models

Harder than hunting for needles in the haystack

The SAS Institute platform is a powerful tool that offers a host of data aggregation, data cleansing and analytical tools to your analyst community. Because of this breadth of capability, you may have analysts or teams creating what regulatory groups would consider models subject to model governance and compliance review. Furthermore, many SAS workloads qualify under the CECL, CCAR and IFRS9 regulatory guidelines as End User Computing workloads, which need to be inventoried, reviewed and placed under a governance scope.

Do you know who these teams and analysts are? Can you prove that your model governance process has identified all these models? Chances are, many of these models and End User Computing instances have gone unidentified, in many cases because they’re hiding in plain sight. SAS workloads can be created, executed and results generated through multiple means; there isn’t just one way to execute a SAS workload.
Read More

Tale of Three Cities

Modernizing traditional SAS business applications to Viya on AWS

Clients ask us this question frequently: “…Should we stick with our business applications on SAS 9.4, or should we take the plunge into SAS Viya? I’ve heard there are some functional differences between the two, and some of my colleagues are concerned that Viya implementations still feels new and a little risky. As a professional designer and implementer, what are Corios’ assessment of the risks and challenges (and benefits)?”

Everyone’s mileage will vary, but here is our experience with migrating three clients from traditional SAS to Viya on AWS. Our clients include a credit card issuing-bank, a commercial bank, and a business financial data clearinghouse. Read More