'Machine learning models can provide deeper insight into employees' performance and skills'
When clients of Itransition, an HR software provider, would come to the company with a new project, the process of deciding whether or not to hire new employees to meet these new demands could took weeks.
Since this soon became untenable, the company needed a way to more effectively manage its own internal talent and marry that to outside capabilities that may need to be hired.
It turned to predictive analytics as a way to keep a handle on its current and future workforce.
“Predictive analytics in HR is using data mining, statistics, and machine learning to make more informed decisions about recruiting, staffing and other HR functions. Whether it’s identifying employees that are at risk of quitting or determining the best candidate for a position, by analyzing data from CVs, job descriptions, and HRIS systems, predictive analytics can significantly improve talent management,” says Andrey Koptelov, innovation analyst with Itransition.
Breakdown in communications
Due to its recent growth, the company found itself struggling to manage its base of developers and other employees in more than 15 countries in which the Lakewood, Colo.-based company operates.
“Every department started to work as a small company, with some processes and some specific tools, and it became really hard to communicate between these departments, and exchange information between them and especially, for example, when some requests for project launching came to us or a request for a new candidate has come, our managers had little understanding of the potential of our company pool and of its strengths and weaknesses,” says Anna Mihalyova, product owner for Talenteer, which is the company’s talent management software.
The number of internal departments grew from three to more than 21 today, according to Mihalyova.
Because those departments in far-flung regions didn’t always communicate well, and some employees weren’t being considered for upskilling to meet new demands for skills and capabilities, it affected the company’s retention, she says.
“This led us to a gap between our people and opportunities within the company. So… our leaders deal with the challenge that we lose our valuable employees because when people can’t find a person within the company, then they start to looking for them outside and sometimes employees leave and the company loses really valuable employees, and the attrition rate increases.”
“The main result is that the project suffers and it’s closing became really long and even the speed of project launching becomes too long,” she says.
Predictive analytics can be a great tool to slow down the “great resignation,” according to another expert.
Decentralized talent information
In the past, the company also struggled to match the right worker with the right task, according to Dmitriy Karpenkov, director of strategic initiatives at Itransition.
“The information about the employees and their skills was decentralized and managed differently in different departments, so it was a kind of manual process for us to go in and find the right people for the right positions.”
Today, Itransition is able to easily match the right worker with the right job, according to Mihalyova.
“The manager can study information with our centralized information storage, about his talent pool, and about the whole company’s available talent pool, about the skills, availability locations, and so on and this helps our manager to make data-driven decisions.”
“After that, managers can choose the best of the best candidates, invite them for an interview, and decide whether they’re relevant for him or not,” says Mihalyova.
What are the gaps?
By employing this type of model, “predictive analytics-based HR platforms can detect employees’ skill gaps, enabling companies to make evidence-based decisions about workforce upskilling,” says Koptelov.
But it can also identify future leaders, he says.
“Machine learning models applied in HR can provide deeper insight into employees’ performance and skills, which can help organizations to spot candidates for management positions.”
