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 of the people. But not only employees have challenge. Similarly, employers are facing the problem of matching the best candidate. What happens if they will be connect by machine learning?
ABOUT WORK SERVICE
Work Service is the biggest HR company in Poland. It specializes in the field of personnel consulting, as well as restructuring in the area of HR also recruitment and employee outsourcing. They decided to support companies which are struggling with issue presented above. In order to they needs goal was to create the best matching system. To stand out by providing innovative solutions for employers and employees. First, they thought about machine learning and came to us!
Work Service wanted to speed up the recruitment process starting with recommendation platform. First, It should be connected with resumes. After that, job offers are sorted and matched with a potential candidate. It helps to automate recruiters’ work and save time. One of the challenges was to exclude candidates without needed experience or skills.
RESULTS OF MACHINE LEARNING ACTIONS
In order to they need, we created a system processing job offers in batch mode.
Firstly, we analyzed all of the possibilities and focused on geolocalization and preparing map/graph of the skills, education and roles.
After that we created the application to labeling from CVs and job offers.
When that was done, we worked on automatic data extractions (like skills or education and experience) from CV
Finally, candidates recommendation system working as machine learning in both ways:
job offer -> candidate and candidate -> job offer
Next step is initial phone job interview with the candidate run by an AI bot. Based on it, extra information about the candidate is collected effortlessly.
After all, AI bot is connect with RMS system. System developing in Java by Stermedia since 2015.
As the result can be distinguish CV/Job offer skills extraction in numbers:
- 6000 skills and 3000 positions
- 3000 education entities
- 10 models of artificial intelligence
- 100 000+ models fitted for parameters optimization
TECHNICAL SIDE OF THE PROJECT
Summarizing, we use intelligence solutions such as:
- 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
To conclude, we recommend system in models:
- Clustering (k-means)
- Topic modeling (NEF, LDA)
- Classification (xgBOOST)
- Recommendation (FM, xgBOOST)