Computing Professional Identity for the Economic Graph
•Download as PPTX, PDF•
4 likes•1,829 views
Strata New York 2014
Recommended
Recommended
More Related Content
Similar to Computing Professional Identity for the Economic Graph
Similar to Computing Professional Identity for the Economic Graph (20)
Recently uploaded
Recently uploaded (20)
Computing Professional Identity for the Economic Graph
- 1. Computing Professional Identity for the Economic Graph
- 2. Agenda 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 3. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 4. About me ©2013 LinkedIn Corporation. All Rights Reserved. 4 Vitaly Gordon
- 5. About me ©2013 LinkedIn Corporation. All Rights Reserved. 5
- 6. About me ©2013 LinkedIn Corporation. All Rights Reserved. 6
- 7. About me ©2013 LinkedIn Corporation. All Rights Reserved. 7
- 8. About me ©2013 LinkedIn Corporation. All Rights Reserved. 8
- 9. About me ©2013 LinkedIn Corporation. All Rights Reserved. 9
- 10. About me @bigdatasc /in/vitalygordon ©2013 LinkedIn Corporation. All Rights Reserved. 10
- 11. What’s in it for you? ©2013 LinkedIn Corporation. All Rights Reserved. 11
- 12. What’s in it for you? ©2013 LinkedIn Corporation. All Rights Reserved. 12 1. You will learn about how LinkedIn takes a massive vision and breaks it down to small data problems
- 13. What’s in it for you? ©2013 LinkedIn Corporation. All Rights Reserved. 13 1. You will learn about how LinkedIn takes a massive vision and breaks it down to small data problems 2. You will learn about how hard cleaning data can be
- 14. What’s in it for you? ©2013 LinkedIn Corporation. All Rights Reserved. 14 1. You will learn about how LinkedIn takes a massive vision and breaks it down to small data problems 2. You will learn about how hard cleaning data can be 3. You will learn why LinkedIn needs endorsements
- 15. What’s in it for me? ©2013 LinkedIn Corporation. All Rights Reserved. 15
- 16. What’s in it for me? ©2013 LinkedIn Corporation. All Rights Reserved. 16
- 17. What’s in it for me? ©2013 LinkedIn Corporation. All Rights Reserved. 17 @bigdatasc
- 18. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 19. ©2013 LinkedIn Corporation. All Rights Reserved. 19 Create economic opportunity for every professional in the world
- 20. ©2013 LinkedIn Corporation. All Rights Reserved. 20
- 21. ©2013 LinkedIn Corporation. All Rights Reserved. 21 • CEO • Chief Executive Officer • CEO and Founder • CEO & Co-founder • President and CEO • Owner
- 22. ©2013 LinkedIn Corporation. All Rights Reserved. 22 • IBM • International Business Machines • International Bus. Machines • IBM Research • IBM T.J. Watson Research Center • IBM Canada • IBM India
- 23. ©2013 LinkedIn Corporation. All Rights Reserved. 23 • UCLA • University of California, Los Angeles • UC Los Angeles • The Anderson School of Management
- 24. ©2013 LinkedIn Corporation. All Rights Reserved. 24
- 25. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 26. Why Do We Need Identity Standardization? ©2013 LinkedIn Corporation. All Rights Reserved. 26
- 27. Why Do We Need Identity Standardization? ©2013 LinkedIn Corporation. All Rights Reserved. 27
- 28. Why Do We Need Identity Standardization? ©2013 LinkedIn Corporation. All Rights Reserved. 28
- 29. ©2013 LinkedIn Corporation. All Rights Reserved. 29
- 30. Text Based Solution Applies acronym expansion (e.g. vp -> vice president) Applies abbreviation expansion (e.g. sr. -> senior) Select the most common standard titles Selects standard sub strings (e.g. software engineer and tech lead in search -> [software engineer, tech lead]) ©2013 LinkedIn Corporation. All Rights Reserved. 30
- 31. Problems with a Text Based Approach ©2013 LinkedIn Corporation. All Rights Reserved. 31 Senior Software Engineer Software Engineer
- 32. Problems with a Text Based Approach ©2013 LinkedIn Corporation. All Rights Reserved. 32 Software Engineer Software Developer Programmer
- 33. Problems with a Text Based Approach ©2013 LinkedIn Corporation. All Rights Reserved. 33 Architect
- 34. ©2013 LinkedIn Corporation. All Rights Reserved. 34
- 35. ©2013 LinkedIn Corporation. All Rights Reserved. 35
- 36. ©2013 LinkedIn Corporation. All Rights Reserved. 36
- 37. ©2013 LinkedIn Corporation. All Rights Reserved. 37
- 38. 38 Profile Inferred Skills Endorsements Skill Vectors
- 39. 39 Profile Inferred Skills Endorsements Skill Vectors 30% 25% 20% 15% 10% 5% 0% Data Mining Hadoop Machine Learning Java Algorithms Python MapReduce Data Science
- 40. 40 Profile Inferred Skills Endorsements Skill Vectors 30% 25% 20% 15% 10% 5% 0% Data Mining Hadoop Machine Learning Java Algorithms Python MapReduce Data Science http://www.slideshare.net/s_shah/strata-endorsements
- 44. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 45. Normalization ©2013 LinkedIn Corporation. All Rights Reserved. 45
- 46. Normalization 46
- 47. Clustering ©2013 LinkedIn Corporation. All Rights Reserved. 47
- 48. Clustering 48 • Each topic is a distribution over words • Each document is a mixture of corpus-wide topics • Each word is drawn from one of those topics
- 51. Anomaly Detection 51 http://www.slideshare.net/tdunning/strata-2014-anomaly-detection
- 52. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 53. Summary ©2013 LinkedIn Corporation. All Rights Reserved. 60 1. User generated content from 300M members, creates 300M problems
- 54. Summary ©2013 LinkedIn Corporation. All Rights Reserved. 61 1. User generated content from 300M members, creates 300M problems 2. Data cleaning is so much more than filtering out empty values
- 55. Summary ©2013 LinkedIn Corporation. All Rights Reserved. 62 1. User generated content from 300M members, creates 300M problems 2. Data cleaning is so much more than filtering out empty values 3. Try to be creative and work around difficult language problems
- 56. 1 Introduction 2 LinkedIn’s Vision 3 Computing Professional Identity 4 Selected Topics 5 Summary 6 Final Words
- 57. We’re building the next big thing
- 58. We’re building the next big thing Join Us
- 59. We’re building the next big thing Join Us!
- 60. We’re building the next big thing Join Us! DJ Patil Gary Flake Beau Cronin
Editor's Notes
- Computing Professional Identity for the Economic Graph
- How do you evaluate that people do the same thing?
- The crowdsourcing turkers left very confused
- Clustering titles is like clustering geography, it depends on the context
- Elephants can run, but that’s not what you should use them for