Back to Blog

Workforce Planning in 2020 With Predictive Analytics

Nirman Dave

If you’ve set aside some budget for new hires in 2020, you’re in charge of bringing new faces into your organization. A huge and stressful task that can change the culture of your business positively or negatively. But, If you’ve been collecting hiring data in 2019, your success rate for 2020 will be higher. With just a simple employee survey, you can create a better employee experience or by collecting job posting data, you can adjust your hiring to the labor market and make your job postings more competitive.

Hiring managers, this one’s for you.

For this use case we will divide how to use machine learning for labor planning into 2 sections:

  • Improving Employee Experience
  • Optimizing Hiring Process

Improving Employee Experience With Predictive Analytics

Employee Experience (EX) - The employee’s overall experience working for an organization.

Sometimes machine learning isn’t all about the customer. You can use predictive analytics to improve EX internally by collecting data and making predictions and analyzing it to avoid overstaffing, improve employee satisfaction and learn more about employee churn.

The Types of Datasets to Improve EX

Like we said, you can learn a lot to improve EX with employee end-of-the-year surveys or optimize the hiring process by collecting historical data on your hiring metrics, such as location, applications received, position title, job description, salary, and qualifications.

For example: here is an example of a CSV file of an employee survey for software developers regarding their skillset and job satisfaction.

This CSV file is from a dataset collected from subjects who are currently looking for a job, but this is still a great example of the type of data you can collect.

With this kind of data, you can analyze relationships between job satisfaction and dev type or how formal education relates to if they work on an open source project, etc.

NOTE: For the best visual representations of your data, try to put your answers in numerical value.

Like so:

Here you can clearly see the relationship between job satisfaction and work life balance ranked 1 to 4 (4 being the highest).

Predicting Which Employees Will Be the Happiest

A great way to make predictions on which employees will be happiest regarding environmental factors is to start by creating personas.

If you create enough personas of certain job positions with their attributes, you can begin to accurately predict the satisfaction of the employee.

Say you’re looking to hire a Digital Marketer. Using data from past Digital Marketers or even employees on other teams, you can begin to see what causes a person to be happy at a position and accurately predict what benefits to offer to make them the happiest, what work load to give them, or even where to sit them in the office—all depending on what data you collect.

Improving the Hiring Process With Predictive Analytics

Planning Hires According to Job Descriptions

To plan for hires, the data starts with the Talent of Operations department. If you introduce data collection for job postings, you analyze the data to make optimize your job descriptions.

For example, analyzing which job positions received the most applications in the cities you operate in, gives you a better idea on the talent availability in the city and what job postings had the most engagement.

From here, you can A/B test position titles and job descriptions and collect data over many years to see which cities are best for which position.

Analyzing Skill Shortages

By analyzing your dataset, you can quickly see what skills you need where.

From this dataset of positions at Google, you can visualize the kind of skills in certain locations and match them up to the number of qualified candidates you received. This will give you a good idea of which locations lack skills to fill your company’s position opening and which locations are oversaturated or highly competitive.

This is extremely valuable for planning your growth in departments and where to open up new offices based on talent.

What to Take Away

By now, I hope you realize how easy it is to search through your data to get insights on labor planning for the new year. You should be using your employee satisfaction and hiring data like you would use a search engine.

Because we’re a no-code machine learning platform, hiring or operations managers can get insights without SQL queries or the help of a data scientist. That’s what’s most powerful about Obviously AI.

If you would like to learn more on how to plan your hires for 2020, request a demo to speak to our team directly.

Peace! ✌️

Share on social media 

More from the Blog

Predicting Brazil’s Wildfire Patterns in 2020

Can machine learning predict wildfires? We use our platform to ask historical data questions on wildfire patterns in Brazil.

Read Story

Step-by-Step ML: Powering Your App Growth

Here's how to use machine learning in the ideation, development, and launch of your app.

Read Story

5 No-Code Data-Science Predictions for the 2020s

As we enter the next decade, the way we approach data science will change. Here our 5 predictions on how that will happen.

Read Story

Never miss a minute.

We will never share your email address with third parties.