What Are the Pros of a Machine Learning Matching System for HR?
First of all, finding a valuable job is a life goal for most people. But it’s not only the employees who have a challenge. Similarly, employers face the problem of finding the best candidate. What happens if they’re assisted by machine learning?
Work Service wanted to speed up the recruitment process, starting with a recommendation platform. First, it should be connected with CVs. After that, job offers are sorted and matched with the potential candidates. It helps to automate recruiters’ work and save time. One of the challenges was to exclude candidates who didn’t have the required experience or skills.
RESULTS OF MACHINE LEARNING ACTIONS
In order to fulfil the needs, we created a system which processed job offers in batch mode. Firstly, all of the possibilities was analyzed and focused on geolocalization and preparing map/graphs of the skills, education and roles. After that, we created an application to label CVs and job offers. When that was done, we worked on automatic data extractions (like skills or education and experience) from CV. Finally, the candidate recommendation system was working as machine learning in both ways: from job offer to candidate and from candidate to job offer.
The next step in the process is an initial job interview with the candidate run on the phone by an AI bot. Based on this, extra information about the candidate is collected effortlessly. The AI bot is connected with RMS system. This system has been developed in Java by Stermedia since 2015.
Here are the results based on CV/Job offer from skills extraction, in numbers:
6000 skills and 3000 positions
3000 education entities
10 models of artificial intelligence
100 000+ models fitted for parameters optimization
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.
The premium team is undoubtedly the main asset of Stermedia. Their developers have a problem-solving and proactive attitude. Communication with Stermedia was smooth and efficient.
I am one of the team members of WorkService’s project. It’s great to feel that my work improves HR experts’ life quality and lets them work more efficiently.
We recommend systems in models:
- Clustering (k-means)
- Topic modeling (NEF, LDA)
- Classification (xgBOOST)
- Recommendation (FM, xgBOOST)
Intelligence solutions which were used:
- Text lemmatization and normalization
- HTML tags treatment also misspelling treatment
- Word2Vec (a numerical representation of text)
- Brand classification of candidate and skills extraction
Python, k-means, knn, NEF, LDA, PCA, Factorization Machines, xgBoost, word2vec, levenshtein distance, django, Django Rest Framework, d3.js, ggplot
ABOUT WORK SERVICE
Work Service is the biggest HR company in Poland. It specializes in the field of personnel consulting, restructuring in the area of HR, recruitment and employee outsourcing. Work Service decided to start supporting companies that are struggling with the issue presented above. In order to achieve this, their goal was to create a best-matching system. This would make them stand out by providing innovative solutions for employers and employees. First, they thought about machine learning and came to us!