5 Steps to Complete a People Analytics Project

Learn how to effectively execute a people analytics project from start to finish, using a practical example to guide your organisation’s data-driven decisions.

What should your first people analytics project be? Many teams start with employee attrition because it has clear outcomes, it has a direct impact on the company, and attrition data is already in your HRIS.

So to understand the five steps you need to follow during people analytics projects, let’s walk through an example of how Penelope, a fictional people analytics practitioner, might approach an employee attrition project, from start to finish.

Step 1: Define the problem

The first step in any people analytics project is to define the problem you want to solve. In this case, the problem is employee attrition. Specifically, we want to understand why employees are leaving the company and what we can do to reduce attrition.

"As an HRBP, I noticed a trend of high employee turnover in the company. I began to investigate why employees were leaving and how we could reduce this trend. My goal was to identify the underlying causes of this issue and develop a plan to address it," says Penelope.

Step 2: Gather the data


The next step is to gather the data you need to analyse the problem. In this case, you'll need data on the employees who have left and their reasons for leaving (if available). This data can often be found in your HRIS, as well as employee surveys or exit interviews.

"To gather the necessary information, I dove into the company's HRIS system, as well as employee surveys and exit interviews. I collected data on employee demographics, job history, performance metrics, and reasons for leaving. I made sure to gather as much relevant information as possible to ensure a comprehensive analysis," shares Penelope.

Step 3: Analyse the data

Once you have the data, it's time to analyse it. There are a variety of statistical methods you can use to analyse attrition data, including survival analysis, logistic regression, and decision trees. But you can also start with descriptive methods. Your choice of method will depend on the nature of your data and the questions you want to answer, and you don’t always need advanced methods.

"I took a look at attrition trends across each of the major groups within the company. Using descriptive statistics, I found that some teams were experiencing higher attrition than others within similar business units. I wanted to identify why the attrition rate was high, so I looked for factors that were strongly correlated with attrition," notes Penelope.

Step 4: Tell the story

After analysing the data, it's time to tell the data story. This is where data visualisation and data storytelling come in. You'll want to create charts, graphs, and other visualisations that help you communicate your findings to stakeholders. You'll also want to craft a narrative that ties the data together and explains what it means for the company.

"Using the results from the data analysis, I created charts, graphs, and other visualisations that I could use to communicate my findings to stakeholders. I crafted a narrative that brought my business knowledge into the story and explained the factors contributing to the high attrition rate and the steps we could take to address it. I presented the data and narrative to the company's leadership team," explains Penelope.

Step 5: Implement solutions

Finally, it's time to implement solutions based on your findings. This might involve changes to HR policies, changes to compensation structures, or changes to management practices. Whatever the solution, it should be informed by the data you've gathered and analysed.

"Based on the data and narrative, I recommended changes to HR policies, compensation structures, and management practices. I presented the recommendations to the company's leadership team and worked with them to implement the changes. Over time, we saw a decrease in the attrition rate and an increase in employee satisfaction," says Penelope.

Overall, attrition is a great starting point for any people analytics team. It's a universal problem that every company faces, and the data is often readily available. By analysing attrition data, you can gain valuable insights into your workforce and make data-driven decisions that improve retention and reduce turnover.


people analytics 101-1New to people analytics or ready to enhance your existing program?

Either way, our eBook People Analytics 101 covers everything you need to know about establishing a strong people analytics foundation for smarter HR strategies and meaningful change across your organisation.

5 Steps to Prepare Your Organisation for People Analytics

5 Steps to Prepare Your Organisation for People Analytics

If you're preparing for people analytics, there’s a lot to do before you hire that first data scientist. To build the right foundation for success,...

Read More
5 ways people analytics and One Model can help you resolve underpayments issues

5 ways people analytics and One Model can help you resolve underpayments issues

Following our blog last month about how systems issues can open the door to staff underpayment, a number of our stakeholders have asked if we might...

Read More
How to craft data-informed HR stories

How to craft data-informed HR stories

A well-crafted data-informed story can effectively influence decision-making, foster understanding, and drive meaningful change within the...

Read More