In anticipation of his upcoming conference presentation, Integrating Predictive Models within a Rules Engine for Resource Allocation, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Aaron Lanzen, Solutions Architect – Business Rules & Analytics at Cisco, a few questions about his work in predictive analytics.
Q: In your work with predictive analytics, what behavior do your models predict (e.g., attrition, response, fraud, etc.)?
A: Most of the rules and all of our behind-the-scenes modeling activities are designed to give the engine as much “situational awareness” as possible to accurately predict engineer, customer, product, and system behaviors. The goal is to align “reality” with our global strategy including unique regional dynamics. One simple example is determining support engineer “availability.” We use two separate models to calculate a live likelihood that any given engineer is “ready” for new work and capable of handling the call.
Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions?
A: These models work across the organization and force alignment between planning and execution. The support engineer availability model is a great example. We predict two components: Shift information, which provides the “supply” of engineers and “handle time” to determine engineer readiness after taking any type of work. When you put these together you have valuable understanding of human behavior that helps align resources in a live decision plus it provides the foundation for strategic headcount planning.
Q: Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: While I cannot explain specific models or goals because of IP/trade secret issues, I can give you a broad example. In one of our models, we choose a small number of available and qualified engineers to see a case and then allow one of those engineers to accept it. Our previous approach was to show the case to many engineers at once; but if you show it to 200 people, we found no one really felt accountable. Our simple “availability model” allowed Cisco to successfully reduce the number of engineers who see a case from 180 to 5! This drives accountability and much better strategic alignment between the engineer and work.
Q: What surprising discovery have you unearthed in your data?
A: My biggest surprise was how quickly a global organization can align once you provide the ability to handle objections. We took it upon ourselves to quantify and clearly model the stakeholders’ objections and assumptions they felt would impact their portion of the business. Sometimes we learned; other times we were able to prove no relationship existed. The process of defining an objection versus simply allowing an opinion to hold back progress is magical. This behavior drives incredibly productive conversations that we named “the fact based conversation.”
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: People, their thoughts, insights, and objections are incredibly important to any decision-based project. Predictive models cannot really replace people, but if they are used properly, they can be a powerful tool in aligning or influencing an organization to make a successful, fact-based decision. The real secret is to create synergy between your thought leaders and your technical capabilities like rule engines and predictive models.
Don’t miss Aaron Lanzen’s conference presentation, Integrating Predictive Models within a Rules Engine for Resource Allocation, at Predictive Analytics World San Francisco, on Tuesday, March 31, 2015, from 4:45-5:30 pm. Click here to register for attendance.
