«Recrut.ink»: a startup based on personnel selection using artificial intelligence (AI)
stack
Python, Pytorch
service
AI model development
development period
11 months
Today, we want to tell you about an interesting startup that our team tried to implement in 2019.
Recrut.ink is a unique personnel recruitment service based on artificial intelligence, taking into account the manager's psychotype.
This project is based on a scientific approach that uses methods for diagnosing stable personality traits, such as the "Big Five" and Raymond Cattell's 16-factor questionnaire.
Recrut.ink is a unique personnel recruitment service based on artificial intelligence, taking into account the manager's psychotype.
This project is based on a scientific approach that uses methods for diagnosing stable personality traits, such as the "Big Five" and Raymond Cattell's 16-factor questionnaire.
Project goal
There is a problem in the world regarding personnel selection for companies. These problems are confirmed by statistics provided by Glassdoor.
According to the research:
According to the research:
- On average, the HR department spends 83.3 hours analyzing a single candidate's resume
- Reviewing a single resume takes only 5-6 seconds
- Conducting 4-6 interviews requires over 250 phone calls
- More than half of the funds spent on recruiting go to recruiters, despite the fact that 65% of resumes are ignored
Additionally, studies conducted by Monster, Projecttimes, and BLS indicate:
- 89% of employers check candidates' social media profiles before inviting them for an interview
- The success of projects in 60-70% of cases depends on time and resource management (PCPM)
- Every fifth employee leaves the company due to various psychological aspects of interaction with their boss
Thus, our team came up with a solution to this problem:
Eliminate the human factor by using an AI model to automatically invite candidates for interviews and select specialists based on the manager's psychotype. While ensuring that the relevance of employee selection exceeds 90%.
Eliminate the human factor by using an AI model to automatically invite candidates for interviews and select specialists based on the manager's psychotype. While ensuring that the relevance of employee selection exceeds 90%.
What does recrut.ink offer?
- Reduction of financial costs on recruiters and labor costs for selecting quality workers by at least 90%
- Increase in team efficiency by 30-40%
How does the platform work for employers?
- Company registration
- Job description and link to manager's profile
- 5 ideal candidates invited for an interview via email
How does the platform work for job seekers?
- An Email arrived
- Confirmed
- Played a game
How does the platform work?
1
The service automatically analyzes the job description and determines the manager's psychotype
2
Selects the best resumes from millions
3
Automatically determines a person's psychotype based on their social media profile
4
Checks the manager's Google Calendar and sends an invitation
5
If confirmed, schedules the meeting in the manager's calendar
Tasks
To avoid lengthy psychological tests, the AI model should analyze the candidate's psychological profile based on their provided social network profile, choosing from options like LinkedIn, Facebook, or Twitter.
We outlined the tasks needed to implement such extensive functionality:
We outlined the tasks needed to implement such extensive functionality:
- A model based on Cattell’s methodology, focusing on the Lexical Hypothesis
- Collecting user data: information from social networks, resumes, and the TIPI test
- Using semantic differentials to understand expectations from work
- Creating a candidate's psychological profile based on data from TIPI, semantic differentials, and Cambridge Analytica models
- Matching resumes and employees according to requirements and personal traits
Process
- Gathering and analyzing candidate dataFirst, we gather information from candidates’ social networks and resumes, then we analyze their personality traits using the TIPI test and Charles Osgood's semantic differential method.
- Consideration and creation of psychological profilesBased on the analysis results, our AI model creates a psychological profile for each candidate, considering both their personality traits and their work expectations.
- Matching and combinationNext, after comparing the psychological profile with the job requirements, we make recommendations based on the comparison, taking into account both professional skills and personal aspects, to find the best match between the candidate and the project.
- Candidate analysis using Cattell's methodIn developing our artificial intelligence model, we relied on Raymond Cattell's methodology, specifically the Lexical Hypothesis, which posits that the most important individual differences are reflected in language concepts.
- AI Model training and functionalityThen, we trained the AI model to analyze text data from social networks according to this methodology. This involved extracting key words and concepts related to individual traits.
Result
Ultimately, we aimed to develop an online platform with our integrated AI model, which would generate a candidate's psychological profile based on the following data: TIPI, semantic differentials, and Cambridge Analytica models.
Thanks to this, the AI could not only match resumes to vacancies but also pair employees with managers, reducing staff turnover rates and improving workplace morale.
However, due to funding cuts, this project has been temporarily put on hold!
Thanks to this, the AI could not only match resumes to vacancies but also pair employees with managers, reducing staff turnover rates and improving workplace morale.
However, due to funding cuts, this project has been temporarily put on hold!
✦ Schedule your consultation right now
and learn more about how the implementation of IT solutions can help your business become better