Case studies

What Are the Pros of a Machine Learning Matching System for HR?

Finding a valuable job is a life goal for most of the people in the world. However, not only employees have the challenge to find a job at the best possible company, but also employers are facing the problem of matching the best candidate for the role they offer. Our client, Work Service decided to support companies that are struggling with such an issue. Its goal was to create the best matching system.




Work Service wanted to speed up the recruitment process by preparing a recommendation platform connected with resumes. Job offers are sorted and matched with a potential candidate. It helps to automate recruiters’ work and save time which can be dedicated to different activities in the company. One of the challenges was to exclude candidates without needed experience, educational background or skills.



Based on this need, Stermedia created a system processing job offers in batch mode. We analyzed all of the possibilities and focused on:

  • geolocalization
  • preparing map/graph of the skillseducation, and roles
  • creating the application to labeling from CVs and job offers
  • automatic data extractions (like skills, education, and experience) from CV
  • application to extract skills manually
  • initial phone job interview with the candidate run by a AI bot; based on it, extra information about the candidate is collected effortlessly
  • AI bot is connected with RMS system which has been developed in Java by Stermedia since 2015
  • candidates recommendation system working as Machine Learning in both ways:  

job offer -> candidate and candidate -> job offer

Deep learning experts from Stermedia done a great job giving us depth analysis of social media (eg. LinkedIn, Twitter, Github, etc.) in terms of search candidates for the job, the initial automatic verification data profile, forecasting changes of job, combining profiles of the same person.

Piotr Adamczyk


As the result can be distinguished CV/Job offer skills extraction in followed numbers:

  • 6000 skills

  • 3000 positions

  • 3000 education entities

  • 10 models of artificial intelligence

  • 100 000+ models fitted for parameters optimization

Recommender system – technically

  • Text lemmatization and normalization
  • HTML tags treatment
  • Misspelling treatment
  • Word2Vec (a numerical representation of text)
  • Brand classification of candidate
Recommender system in models:

  • Clustering (k-means)
  • Topic modeling (NEF, LDA)
  • Classification (xgBOOST)
  • Recommendation (FM, xgBOOST)
Python, k-means, knn, NEF, LDA, PCA, Factorization Machines, xgBoost, word2vec, levenshtein distance, django, Django Rest Framework, d3.js, ggplot
Being a part of this project combining machine learning and human resources was a great experience. I’m glad that the HR specialist could work more efficiently thanks to Work Service platform.
Piotr Giedziun

Data Scientist, Stermedia

Let's talk about your project

Leave us a message so we can understand your idea and goal.
In the next step, we will focus on requirements and provide a quotation.

Marta Miszczak
See also

Here’s a place where dialogue starts.

Let's talk!