The highest complexity of learning analytics is predictive and prescriptive analytics. This means using data to either predict what might happen, or to prescribe learning activities. And, out of the 5,713 reports we reviewed as part of our Learning Analytics Research Study, we only found a fraction of reports that we classed as “Predictive and Prescriptive.” In this post, we’ll explain how these reports are being used and suggest other ways you can try predictive or prescriptive analytics in your organization.
Minding the Gap
The spider charts we uncovered during our study (see the following image) show individual ratings in terms of both knowledge and business performance for several KPI metrics. These reports are prescriptive because they're used during coaching sessions with managers and inform a coach on:
- which KPIs a manager needs to improve, and
- whether the needed improvement is an issue of knowledge or an issue of application.
A coach can then use this information to prescribe learning activities to address those issues. We call this type of prescriptive analysis “gap analysis” because it analyzes gaps in knowledge and application.
Prescribing Potential Prescriptive Analytics
As more organizations start to push into predictive and prescriptive analytics, we can expect a wide range of approaches as we saw in our Advanced Evaluation blog post. prescriptive analytics might mean:
- Benchmarking success metrics for a new program based on data about the success of previous similar projects
- Automatically recommending training to learners based on their information and/or training histories (e.g. job role, interests, skill sets, etc.)
- Making recommendations into how training and resources are designed based on the success of different modalities and approaches in previous projects
Predicting the Future of Predictive Analytics
Under the heading of predictive analytics, we may start to see some of the following approaches emerge:
- Setting the budget for a training program based on the likely impact of that program as shown by data analysis
- Creating an early warning system for areas of the business less likely to hit compliance targets
- Predicting the lifespan of resources in order to plan updates or replacements
All of these predictive and prescriptive approaches will require innovation and effort to become a reality, as there’s no well-worn path to follow. They also require building on the foundation of the other levels of learning analytics complexity (e.g. benchmarking of success metrics for a new project requires data analysis from previous programs).
You can’t get straight to predictive and prescriptive analytics. You need a strategy to start at the lowest complexity and work your way up.
As you plan how you’re going to get there, think about some of the approaches outlined in this article and identify one or two that would be beneficial in your organization.
Next Up: Experience Types
We’ve looked at different approaches to learning analytics from both category and complexity perspectives. Next week, we’ll explore the different kinds of learning experiences organizations use to collect data!
About the author
As a co-author of xAPI, Andrew has been instrumental in revolutionizing the way we approach data-driven learning design. With his extensive background in instructional design and development, he’s an expert in crafting engaging learning experiences and a master at building robust learning platforms in both corporate and academic environments. Andrew’s journey began with a simple belief: learning should be meaningful, measurable, and, most importantly, enjoyable. This belief has led him to work with some of the industry’s most innovative organizations and thought leaders, helping them unlock the true potential of their learning strategies. Andrew has also shared his insights at conferences and workshops across the globe, empowering others to harness the power of data in their own learning initiatives.
Subscribe to our blog