The business world is full of decisions that would be so much easier with a crystal ball to help predict the future: Which applicant should we hire or promote? Of this quarter’s new sales recruits, which ones are most likely to succeed as team leaders? Will learners engage with this simulation, or should we develop a serious learning game instead? Will sending this manager to an MBA program pay off? Using predictive analytics in eLearning—as well as in hiring and promotion decisions—can help with these choices.

Study history to detect patterns

Data provide a record of what has happened in the past. This information is useful in a variety of ways (learn more at The eLearning Guild’s Data & Analytics Summit)—but identifying historical patterns can be a great way to predict future patterns or behaviors. For example: Colleges and universities study historical data to identify students most—or least—likely to complete a degree. They can use that information to decide which students to accept. They can also use it to figure out what failing students have in common—and tailor assistance programs to target common weaknesses. This approach is transferrable to corporate L&D, where using data analytics to identify employees’ weak areas or potential weak areas enables instructional designers to create better training, as well as to personalize eLearning.

Some predictive analytics tools harness artificial intelligence algorithms to sift through large amounts of data—choosing applicants to interview from a pool of thousands, for example. A caveat with automated predictive analytics is that some historical patterns are not desirable and could be the result of historical or implicit bias baked into algorithms. For example, an algorithm could easily learn from studying successful top-level executives that, in addition to, say, having an MBA and 10 years of management experience, the clear majority of “successful executives” in US corporations are white men. Thus, use of predictive analytics should be balanced with human intervention to ensure that undesirable patterns are not inadvertently imbedded in key personnel decisions. Used in conjunction with hiring committees and performance support tools that support broad corporate hiring goals, predictive analytics can play an important role in recruiting, hiring, promotion, and training strategies.

Put predictive analytics to work in eLearning

Looking at analytics data from a mindset of predicting learner behavior makes it possible to anticipate what employees will engage with and how their performance could improve as a result.

On an individual level, that could mean tailoring each learner’s roster of training courses and performance support tools based on past behavior. Consider a learner who has never completed a video longer than three minutes but who consistently engages with a chatbot that sends short games, quiz questions, and links to short articles. Placing that learner in a video-based training course would be a mistake!

On the other hand, if data from course evaluations shows that most learners engaged with the interactive video content but loathed the discussion boards, a virtual classroom with interactive videos and other activities might be just the ticket.

Leveraging predictive analytics is just one way to take advantage of data that most companies already collect. The eLearning Guild’s research report Putting Data to Work explores more opportunities for using and applying data and using predictive analytics in eLearning.