• English (en) uk flag arrow_right

    The global remote work community tends to interact in English. Switching languages might impact your visibility.

  • Search
  • Jobs/gigs
  • Publish a job
  • Your jobs (posted or applied)
  • Preferences
  • Your genome
  • Signals
  • Messages
  • Torre's product roadmap
  • Request features
  • API for developers
  • Help
Torre’s Job-Matching Model
How do we suggest and rank candidates
Our algorithm evaluates and assigns scores to every existing candidate or job listing within our database. The scoring process is driven by the job description, which acts as a query generator. We then compare the attributes of a person’s genome to see how well the candidate is able to perform the requirements of the jobs. Analyzing this data we come up with a score range, the more data we have the smaller and more accurate the range.
We use the scores and some other features to make sure we only show candidates who are able to do the job. To be able to perform a job you need to pass the minimum requirements of the job. Often we use the score previously calculated and use a threshold that’s calculated by analyzing millions of previous matches.
The final stage involves ranking the candidates in descending order of suitability, with the "highest potential match" candidates taking the top positions and gradually descending to "lower potential matches." The accumulated scores and overall compatibility with the job description determine this order. For ranking, we use more features than for filtering and scoring because there are some aspects of the job that are not necessarily required but make a difference between a good candidate and an amazing candidate.
Certainty calculations
Our approach to candidate evaluation recognizes that many factors influence a candidate's ability to excel in a job, and sometimes, certain pieces of information may be missing. To address this, we use the concept of 'uncertainty' into our matching algorithm. This concept comes into play when a candidate's profile lacks information about specific requirements for a job. Rather than making assumptions, our algorithm assesses the likelihood of whether the candidate possesses the unlisted skills or qualifications. Instead of presenting a definitive single score, we offer a range - a lower and upper bound - that reflects our prediction's possible variance regarding the candidate's capability to meet the job requirements. This method offers a more nuanced and realistic view of a candidate's potential fit, acknowledging that profiles may not always capture every skill or experience a candidate possesses. By providing this range, we offer employers a more comprehensive understanding while respecting the inherent uncertainties in the candidate evaluation process.
Scoring/filtering features
3.1. Skills proficiency
Representing the user's skills and their respective proficiencies.
3.2. Language fluency validation
Representing the user's language fluency, linked to the recommendation algorithm.
3.3. Salary validation
Representing the user's salary expectations, linked to the recommendation algorithm.
3.4. Organization size validation
Representing the user's preferred company size, linked to the recommendation algorithm.
3.5. Timezone validation
Representing the user's timezone, linked to the recommendation algorithm.
3.6. Location validation
Representing the user's location, linked to the recommendation algorithm.
Ranking-only features
4.1. Connectivity
Representing the user's connectivity requirements, linked to the recommendation algorithm.
4.2. Behavioral similarity
Indicating the user's behavioral characteristics, linked to the recommendation algorithm.
4.3. Years of experience
Representing the user's work experience, linked to the recommendation algorithm.
4.4. Self-awareness
Reflecting the user's self-awareness attributes, linked to the recommendation algorithm.
4.5. Recommendation weight
Indicating the user's weighting preferences for recommendations.
4.6. Genome completion
Representing genetic or personal attributes.
4.7. Screening questions
Representing the job specific requirement that are not part of the job description yet.
Total ranking/scoring formula
Taking into account the comprehensive range of factors outlined earlier, we have meticulously trained a machine-learning algorithm using an extensive dataset encompassing millions of applications, mutual matches, invitations, hires, and disqualifications. This model is expertly optimized to prioritize the most promising candidates at the top of the list, significantly reducing the time required for candidate review. Importantly, we continuously refine and optimize the model to maintain its efficacy and accuracy. Currently, we are utilizing a random forest model, renowned for its robustness and effectiveness in complex scenarios like candidate ranking. The strengths of this model in our context are manifold:
  1. Complex pattern recognition: Random forests excel at detecting intricate and non-linear relationships among variables. In terms of candidate ranking, this capability allows the model to evaluate how various elements of a candidate's profile synergistically affect their suitability for a position.

  2. Resistance to overfitting: Due to its ensemble approach, which amalgamates multiple decision trees, a random forest model is less prone to overfitting. This trait is vital in recruitment, ensuring consistent performance across diverse and new candidate profiles.

  3. Insightful feature analysis: The model offers insightful analyses on which aspects of a candidate's profile (like particular skills or experiences) are most predictive of their fit for a role, aiding recruiters in making more informed decisions.

  4. Versatility with data types: Random forests adeptly handle both numerical and categorical data, a common scenario in candidate profiles, thereby providing a holistic assessment.

  5. Scalability with large datasets: This model type remains efficient even with large-scale data, a usual occurrence in recruitment with extensive candidate pools.

  6. Interpretability and ease of use: Despite its complexity, the random forest model is relatively straightforward to interpret, an important feature for ensuring transparency and trust in recruitment processes.

Through ongoing optimization, our random forest model adapts to evolving hiring criteria and candidate pool dynamics, ensuring sustained precision in ranking candidates.
Open features for ranking
In line with our commitment to FAIR , we are dedicated to providing candidates with transparency and empowerment. Our goal is to assist them in securing the most fulfilling job opportunities. To ensure that everyone has an equitable chance, we focus on equipping candidates with the knowledge and tools they need to optimize their resumes and enhance their appeal in the job market. To this end, we have made the workings of our feature calculations and overall scoring algorithms completely transparent to all users. This openness allows candidates to understand precisely why and how they are ranked in our system. More importantly, it provides them with actionable insights into what aspects of their profiles they can improve or emphasize to increase their attractiveness to potential employers. By demystifying the ranking process, we not only foster a sense of trust and fairness but also empower candidates to take informed steps toward achieving their career aspirations. Our approach ensures that each individual is equipped with the knowledge to present themselves in the best possible light in the competitive job market.
We place utmost importance on the privacy of candidates, companies, and talent seekers in every aspect of our matching process and algorithmic operations. To empower candidates with control over their privacy, our platform features a dedicated section in the preferences where they can adjust their privacy settings. When a candidate chooses to deactivate their visibility, we guarantee that their profile will not be displayed in any section of the platform to talent seekers. This feature is essential for candidates who wish to discreetly explore job opportunities. By enabling this setting, candidates can confidently and privately search for jobs, ensuring they can do so with complete peace of mind and security. Also, the compensation requirements of candidates can be hidden from talent seekers in the preferences section of the platform. Even though not recommended, we also provide the option for talent seekers to hide compensation details on jobs. Hiding compensation means we won’t highlight the job compensation anywhere for candidates to see.
Fair artificial intelligence.
We’re committed to it.
Fair artificial intelligence.