Recommended
Recommended
More Related Content
Similar to Using Interaction Signals for Job Recommendation
Similar to Using Interaction Signals for Job Recommendation (20)
Recently uploaded
Recently uploaded (20)
Using Interaction Signals for Job Recommendation
- 1. Using Interaction Signals for Job Recommendation Benjamin Kille, Fabian Abel, Balázs Hidasi, Sahin Albayrak| SIREMTI | 13 November 2015
- 2. Agenda – Looking for a Job: now and then – Data Description – User Inquiry – Findings – Conclusion and Outlook Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 2/26
- 3. Problem Description Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 3/26 http://peacechild.org/wp-content/uploads/2015/09/Youth-unemployment.jpg
- 4. Traditional Method to Look for a Job Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 4/26 http://www.businessreviewaustralia.com/public/uploads/large/large_article_im640_newspaper_ad_2.jpg
- 5. Tends in Job Seeking Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 5/26 Use of print media decreases Professionals predominantly use – Online job offer collectors – Online business networks Trend leads to – Higher volume of job offers to process for professionals – Higher volume of candidates to deal with for employers – Reciprocal selection problem Weitzelet al. (2015). Bewerbungspraxis 2015 – Eine empirische Studie mit 7000 Stellensuchenden und Karriereinteressierten im Internet. http://3.bp.blogspot.com/-Tm8S-4mJcdQ/Tx2Y-ND1flI/AAAAAAAACcM/l6fPkkR9RMI/s1600/information_overload_hydrant.jpg
- 6. Reciprocal Selection Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 6/26 Professional: – reduce job offers to manageable size – remove irrelevant job offers – keep relevant job offers Recruiter: – reduce list of candidates to manageable pool – keep candidates with required skills – keep candidates likely to respond – remove candidates lacking necessary skills Ideally: match needs of both parties
- 7. How do we select job offers/candidates? 1. learn a modell representing professionals’ requirements – curriculum vitae/skills – location – preferences 2. apply modell to available job offers 3. present suggestions to professionals 4. observe how professionals react 5. adjust modell to improve suggestions (repeat) Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 7/26
- 8. Types of Feedback We track users ... ... clicking on ... bookmarking ... replying to suggested job offers Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 8/26
- 9. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 9/26
- 10. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 10/26
- 11. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 11/26
- 12. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 12/26
- 13. Which Type of Feedback should we use? What can a click tell us? What can a bookmark tell us? What can replies tell us? Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 13/26
- 14. A User Inquiry – How satisfied are users with their job recommendations? – Collect ratings for job recommendations Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 14/26
- 15. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 15/26
- 16. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 16/26
- 17. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 17/26
- 18. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 18/26
- 19. What Type of Feedback Tells us Most? Idea: Check which kind of Feedback correlates best with ratings: – ratings ~ clicks – ratings ~ bookmarks – ratings ~ replies Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 19/26
- 20. Relation: ratings ~ clicks Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 20/26 clicks ratings 1 2 3 4 5 6 7 8 9 10 12345
- 21. Relation: ratings ~ bookmarks Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 21/26 Ratings for Bookmarked Jobs (μ = 3.6) rating Density 0 1 2 3 4 5 0.00.10.20.30.40.5
- 22. Relation: ratings ~ replies Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 22/26 replies ratings 1 2 3 4 5 6 7 8 12345
- 23. Signal Comparison Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 23/26 clicks ratings 1 2 3 4 5 6 7 8 9 10 12345 Ratings for Bookmarked Jobs (μ = 3.6) rating Density 0 1 2 3 4 5 0.00.10.20.30.40.5 replies ratings 1 2 3 4 5 6 12345
- 24. Conclusion and Outlook feedback is necessary to improve recommendations analysis of three signals: – clicks à few clicks might be misleading – bookmarks à filter bad suggestions; concentrate on medium preferences – replies à most accurately reflect preferences next steps – implement a recommendation strategy that learns with replies – A/B testing to verify suitability Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 24/26
- 25. Questions? Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 25/26
- 26. Using Interaction Signals for Job Recommendation | Benjamin Kille | SIREMTI 2015 slide 26/26 Benjamin Kille (TU Berlin) Competence Center Information Retrieval & Machine Learning Institute of Commercial Information Technology and Quantitative Methods benjamin.kille@tu-berlin.de @bennykille http://crowdrec.eu http://xing.com