Rabota.ru launched a service for recommending vacancies of 16 neural networks and collaborative models. The technology tracks the behavior of job applicants and employers and gives them recommendations to find a job or a specialist faster. A representative of the platform told RB.RU about this.
The more the applicant interacts with the site, the better and more accurately the recommendations will fit. The updated recommender system includes five main types:
-
Analysis and recommendation of the best offers on the site.
Such recommendations are available to users who do not yet have a resume and experience of interacting with the Rabota.ru service. The model analyzes the behavior of all users, and based on this, collections are formed, for example, “Jobs for women” or “Recent jobs”. -
Action recommendation model
It analyzes all the user’s actions, thanks to which the service accurately selects the relevant recommendations for him. -
Vacancies suitable for resume
Based on the skills described in the resume, salary expectations and other parameters, the model selects the appropriate openings and offers them to the applicant. -
Recommended work based on previous applications
Most of all, this type of recommendation is suitable for representatives of labor specialties who respond to a large number of different vacancies with a short resume: drivers, couriers, loaders, etc. -
Analysis by resume and actions on the site.
This approach combines the action recommendation model and summary-based recommendations.
The company itself said that the technology has no analogues among HR technology products and increases the conversion rate in response by 8 pp
Author:
karina pardaeva
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
