Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Data Science - lets put some netflix into jobmensa.de

Data Science - lets put some netflix into jobmensa.de

My first talk at Jobmensa.de about the basics of data science and how we can use it to enhance user experience and recruiting workflow at our startup.

Steven

June 12, 2015
Tweet

More Decks by Steven

Other Decks in Programming

Transcript

  1. 1. WHAT IS MY BACKGROUND 2. WHAT IS DATA SCIENCE

    3. WHY SHOULD WE USE IT 4. WHAT IS MACHINE LEARNING 5. WHICH CONCEPTS COULD WE USE 6. WHAT IS VERY IMPORTANT 7. PROFIT 3
  2. DATA ANALYTICS OF GENES WITH R/RUBY DATA CRAWLER FOR AUTOMATIC

    MODEL ADAPTIONS WITH PYTHON BEING A SCIENTIST ;-) 12
  3. 14

  4. 22

  5. 24

  6. Rank applicants according to their job fit — PROFIT 47

    First student on the list, was the best fit
  7. 48

  8. 53

  9. 54

  10. 59

  11. 61

  12. 63

  13. 64

  14. 68

  15. 74

  16. 75

  17. 79

  18. 80

  19. MACHINE LEARNING is the science of getting computers to learn

    from data and act without explicitly programmed 88
  20. 92

  21. 93

  22. 96

  23. 97

  24. 101

  25. 102

  26. 104

  27. job_id payment_hourl y keyword_1 keyword_2 exp_german exp_english exp_french … 11

    19 1 0 1 1 0 7 20 1 0 0 0 3 10 0 0 0 0 0 … … … … … … … 105
  28. 106

  29. 108

  30. 109

  31. 110

  32. 111

  33. 112

  34. 113

  35. 127

  36. 132

  37. i.e. most of a company’s jobs are very similar every

    favorated job creates a own list similar to it. liked jobs are used to fill the pool with more jobs the user can favorate 150
  38. 158

  39. 163

  40. 171

  41. 1. Sharon Pande, (2011),"E-recruitment creates order out of chaos at

    SAT Telecom” 3. Wenxing Hong, (2013),“Dynamic User Profile-Based Job Recommender System” 5. Yao Lu, (2012 - École Polytechnique Fédérale de Lausanne), “Analyzing User Patterns to Derive Design Guidelines for Job Seeking and Recruiting Website” 7. Al Mamunur Rashid, (2002 - University of Minnesota), “Getting to Know You: Learning New User Preferences in Recommender Systems” 8. http://berkeleysciencereview.com/article/first-rule-data-science/ 9. Craig Milroy, (2015), “Chief Data Officer: Evolution to the Chief Analytics Officer and Data Science” 172
  42. 173