From applicant tracking system to applicant ranking system

Today we live in an increasingly digital and hyper-connected world, where both organizations and individuals feel the need to manage, convey and better monitor the flow of incoming and outcoming information.

Hence the growing need to be always connected in real-time; a need that has helped the multiplication of communication tools and channels, a blast of social networks with a consequent increase in the amount of data and information to be managed.
A global phenomenon that has had a significant impact on the world of recruiting, especially in recent years.

Only a few years ago, the recruitment took place exclusively through the publishing of ads in the newspaper, which generated paper applications.
Today the talent acquisition process has completely changed: job offers are online 7 days a week and visible all over the world. This generates a huge amount of information that requires cutting-edge tools and processes, far from the simple use of emails and or paper to collect the CVs received.

In an increasingly digital perspective, organizations have started to use technological tools to optimize talent acquisition and better manage CVs: ATS.

The Applicant Tracking System (ATS) is a tool able of building up candidates’ database that can be consulted on demand in a quick and effective way, optimizing the time and resources to dedicate to recruitment.

However, the needs of the HR sector are experiencing a constant evolution, which requires the adoption of increasingly innovative tools; for this reason, we are no more talking about ATS but about ARS: Applicant Ranking System.

With ARS we refer to a modern version of tracking; The advantage over using a classic ATS is the ability to sort candidates by automatically acquired skills – make a “ranking” – compared to one or more searches / job offers.

Traditional ATS have the ability to search for profiles by filters and keywords (Boolean search). This system, although representing an epochal transition with respect to the manual management of the curricula, turns out to be outdated by the need to have an increasingly pertinent group of candidates.

The technology we use in JobAArch is based on artificial intelligence, capable of matching profiles and job advertisements in 6 languages (Italian, English, French, German, Spanish, Portuguese), even when the language of the CV is different from the one of the offer.

It is a system developed to ensure relevance to semantic analysis, reducing error margins and increasing the content that can be processed by the machine.

The result? A greater relevance and depth in the reading of candidates’ skills for a better association between professional tags and reference roles.

To better understand the potential of the applicant ranking system – compared to an applicant tracking system – let’s see some examples together:

• Large volumes of candidates. If I receive large volumes of applications for a job offer, I no longer need to process them all. The matching engine will not show profiles that don’t fit with the selection, but only the relevant ones will be sorted in descending order (from 100% scaling compatibility). In this way we will have an optimization of time and resources and a greater process effectiveness.
• The semantic engine is supportive even when the problem is no longer the quantity but the quality of the CVs received; this is because the system is able to read the tasks performed by the candidates without the need for them to be traced back to a specific “job title”.
  For example, let’s imagine professional profiles with great skills that, however, are not very experienced in writing a CV.
  In a classic ATS system, these candidates would be penalized or not even identified.
  Same story for young talents with just a single work experience, whose job titles are too specific, and will not be reflected externally.
  In the job market, these candidates will tend to use the job title that has been given to them in the past, thus risking not being found.
  Also, in this case, artificial intelligence will solve the problem by reading the tasks performed and the skills acquired (beyond the specific role), identifying the skills sought.

Time and efficiency are the drives that lead us to develop Applicant Ranking System systems such as JobArch.