Learn the 4 types of HR analytics

What is HR analytics?

HR analytics enables users to measure past outcomes, forecast future results and recommend actions based on data. The steps of HR analytics are collection of data, confirmation that the data is acceptable for analysis, data analysis and then interpretation of the results.

Following each step of HR data analysis is crucial to be sure that the end results are reliable and actionable. For example, incomplete or inaccurate data might skew results.

The term HR analytics is often used interchangeably with people analytics or workforce analytics, but all three have different, if related, meanings. HR analytics focuses on data owned by the HR team, while people analytics also includes employee data from across the company. That data could include information from IT, finance or other departments.

Meanwhile, workforce analytics extends beyond full-time employees and includes all types of workers, such as temporary employees and consultants.

The 4 types of HR analytics

Four types of HR analytics exist. Descriptive and diagnostic analytics use data to evaluate what took place, while predictive and prescriptive analytics focus on the future.

Learn more about each type of HR analytics.

1. Descriptive analytics

Descriptive analytics primarily creates summaries of historical data. That data might be about employees, such as demographic data, or about actions that have taken place.

For example, an HR team could break down the employee population by age groups or generations, or look up the turnover rate for the past year. Other examples include the distribution of performance ratings across employees, the number of requests received and answered by HR, or the average base salary for an employee group.

2. Diagnostic analytics

An HR team uses diagnostic analytics to understand what caused an issue or concern. Use of diagnostic analytics typically follows use of descriptive analytics, since descriptive analytics can point out areas of concern, such as high turnover. Diagnostic analysis relies on historical data to determine the root cause of a situation.

Examples of diagnostic analytics include trying to determine why turnover has increased year over year or why turnover is abnormally high in one department. Another example is evaluating causes of absenteeism.

While HR teams often use diagnostic analytics to understand problems, it can also be used to understand the reasons for positive outcomes. For example, a company might attract more candidates for a job posting than was expected.

3. Predictive analytics

HR teams use predictive analytics to forecast what will happen in the future based on what has happened in the past. Historical data is used again, but with the addition of statistical models, which can make carrying out predictive analytics difficult for employees who don't have a firm grasp of certain statistical concepts.

HR systems and advanced spreadsheets can play an important role in predictive analytics. The key is to produce projections that are accurate so that HR staff can rely on their conclusions.

Examples of predictive analytics include forecasting turnover, identifying candidates with the highest potential for growth and estimating employee head count needs based on the company's growth trajectory.

4. Prescriptive analytics

Prescriptive analytics suggest what the HR team should do to address future needs and opportunities. These analytics might rely on AI, machine learning and third-party data in addition to historical data, and can incorporate large data sets.

Prescriptive analytics could use a combination of internal and external data to suggest the skill sets that a company will need in the next five years. HR staff could also use prescriptive analytics when deciding what type of training to provide for employees.

Eric St-Jean is an independent consultant with a particular focus on HR technology, project management, and Microsoft Excel training and automation. He writes about numerous business and technology areas.