With its unmatched database of career and education histories, now incorporating some 690 million total member profiles, LinkedIn is in a unique position to change the recruitment industry as we know it, and ensure that the right people are matched to the right job, improving outcomes for both recruiters and job seekers.
But LinkedIn also needs to tread carefully with this. Using its dataset, LinkedIn can formulate highly accurate candidate recommendations based on similar roles and industries, but it could also, unwittingly, reinforce existing biases – highlighting more men than women for a position, for example, which an algorithm might infer based on how the company has hired in the past.
That’s part of LinkedIn’s broader focus moving forward, but this week, LinkedIn has outlined a new update to its recruitment algorithms which has seen it significantly improve response rates, and subsequent hiring activity.
As explained by LinkedIn:
“To address [recruitment efficiency], we built the Qualified Applicant (QA) AI model, which learns the kinds of applicant skills and experience that a hirer is looking for based on the hirer’s engagement with past candidates. We use the model to help our members find jobs for which they have the best chance to hear back from, and to reduce the likelihood of our hirers overlooking promising applicants by highlighting those who are a great fit.”
The update couldn’t come at a better time – with more people now looking for new roles as a result of the impacts of COVID-19, some recruiters are seeing significant increases in job applications, while candidates can find it demoralizing to be applying to many roles and not hearing much back.
LinkedIn’s system, as noted, used each company’s past history to improve this:
“Qualified Applicant is an AI model that aims to predict how likely a member is to hear back if he or she applies for a particular job. Formally, we try to predict the probability of a positive recruiter action, conditional on a given member applying to a given job.”
This is not the first time LinkedIn has experimented with applicant recommendations, and seen improved results. Last February, LinkedIn added new A1-facilitated candidate recommendations within its Recruiter platform, while in 2018, LinkedIn also sought to provide job seekers with more context on job ads by adding a Skills Match listing to each.
Those are more recent, evolving options to help improve recruitment outcomes, but even back in 2014, LinkedIn was experimenting with tools that could predict your future career path based on your noted interests and traits.
Which sounds kind of far-fetched, that an AI system might be able to map out where you’ll be best suited based on a few data points. But LinkedIn, with such a huge database, may be able to do just that, while independent research has shown that AI-based job candidate recommendations often lead to better hires than inherently biased human managers.
Again, this is an element that LinkedIn needs to approach with caution, but based on the results of this latest update, its systems are certainly improving.
“We have deployed this model across three LinkedIn business lines – Job Seekers, Premium, and Recruiter – and observed significant metrics gains in all three. On the seeker side, we highlight job search results if a member’s profile is a good match for the job (Quality Match product). For Premium members, we additionally showcase jobs for which the member would be more competitive than the other applicants (Top Applicant product). Finally, hirers using LinkedIn Recruiter benefit from a smarter ranking of applicants, as well as receive notifications when members with a very high match score apply for their jobs.”
Indeed, LinkedIn says that its new systems have, in some elements, lead to double-digit increases in click-through rates, and significant improvements in hiring accuracy.
It’s another, small step in this respect, as LinkedIn gradually moves towards optimizing the use of its hugely valuable data banks.
You can read more details about the latest LinkedIn recruitment system update here.