Interfaces Are Improving Predictive-Information Presentation

There is a revolution in the kinds of information our machines are giving us. Today’s tools, such as predictive analytics, can produce a kind of output that was impossible to imagine even five years ago, when we were concerned about storage and processing capacity.

The ability to gather, process and relentlessly analyze and reanalyze data makes it possible to generate probabilities for virtually anything. The more underlying data and the more it can be processed, the deeper the potential for understanding.

However, predictions are just the odds, based on data, that something may occur. A prediction that is 90 percent likely to be right is 10 percent likely to be seriously wrong. Planned events always have a distribution of success probabilities.

It also matters what is being predicted. A candidate who meets 90 percent of the qualifications is not the same as a candidate who is 90 percent likely to succeed. The former is a quantitative assessment, and the latter is the equivalent of Las Vegas odds. Meeting 90 percent of the qualifications is a fact, whereas a 90 percent likelihood of success is a wager. The downside of the wager is complete failure. Even more complicated is the range of probabilities that this particular candidate is 90 percent qualified.

The ways in which to present predictive information and user interface are also changing. The essence of traditional interfaces is a deep emphasis on clarity (or intuitiveness). One look at the interface tells you what to do. That doesn’t work with likelihoods.

Intelligent output requires the user to think before deciding.

Greenhouse (the enterprise ATS company) and Textio (the augmented-writing company) are leading the way toward new interfaces. Getting it right involves a good deal of experimentation, failure and improvement. (We’ll cover Textio’s amazing interface in a later column.)

Like most credible companies delivering HR technology, Manhattan-based Greenhouse is working hard to discover the places where added intelligence and predictions can be most useful to their customers. One area Greenhouse has focused on is predicting the recruiting department’s results. Hiring and finance managers always want to know when the new person will be hired and whether he or she will show up.

In order to harness the results of predictive tools, Greenhouse instituted a process that involves several repeatable steps:

  1. Clearly define the predictive value you want to deliver. (In this case, that is the likely date that a new candidate will start work and the aggregate likelihood that recruiting will meet its KPIs.)
  2. Collect and process the data to make the prediction.
  3. Develop a combination of graphics and text to communicate the data.
  4. Test the results with customers.
  5. Assess customer satisfaction and iterate both the objective and the interface design.

Underlying the approach is the very clear understanding that learning is an ongoing process. Today’s best may well become tomorrow’s “not good enough.” As users become more sophisticated, interfaces will continuously evolve.

Greenhouse began with the following hypothesis: We believe recruiters want informed predictions about when a hire will start to gain credibility and set clear expectations with both hiring managers and finance teams.

In the initial cycle, Greenhouse used bar-chart histograms to express the likelihood that a job would be filled. These first interfaces focused on helping to understand how the forecasts were developed so recruiters could explain their forecasts. Eye-catching bar charts indicated the array of possibilities suggested by history.

While accurately portraying the statistical reality, recruiters were unable to understand what action was required. In fact, they wanted usable direction rather than understanding. They needed the system to tell them what to do. The Greenhouse team also discovered that project completion meant different things to recruiters, hiring managers and the finance department.

Recruiters focus on the hiring decision. Hiring managers are concerned about the day the new hire reports for work. Finance is interested in cash-flow timing. It turns out that each group had important concerns about different aspects of this simple endpoint. Further, complex data aggravate the anxiety users feel about misinterpreting data.

In the end, the Greenhouse team opted for an interface that gives action-oriented information. Is the project on track? What are the range of dates in which the offer will be accepted? The final interface replaced detailed probability data with clear and actionable insight in the form of a predicted range for both the offer-acceptance date and predicted start date, shown next to the target start date.

Each individual prediction in an HR-technology product will be undergoing this sort of testing and retesting. Greenhouse is one of the companies that is setting the standard for the development and testing of intelligent-software interfaces.

Avatar photo
John Sumser
Emerging Intelligence columnist John Sumser is the principal analyst at HRExaminer. He researches the impact of data, analytics, AI and associated ethical issues on the workplace. John works with vendors and HR departments to identify problems, define solutions and clarify the narrative. He can be emailed at