Skills, Reputation, and Search
Download as PPTX, PDF24 likes45,167 views
The document outlines LinkedIn's strategy for enhancing skills discovery and endorsement through data-driven algorithms and social proof mechanisms. It highlights the relationships between skills and job titles, the implementation of user-centric interfaces, and the growth achieved through skill endorsements. Overall, LinkedIn aims to connect talent with opportunities by leveraging a comprehensive skills tagging and recommendation system.
Skills, Reputation, and Search
- 1. Skills, Reputation, and Search Pete Skomoroch Principal Data Scientist, LinkedIn
- 2. Vision: Create Economic Opportunity for Every Professional 2 Location
- 3. LinkedIn: The Professional Profile of Record ©2012 LinkedIn Corporation. All Rights Reserved. 3 200+MMembers 200M Member Profiles
- 4. LinkedIn Search: Connecting Talent with Opportunity 4
- 5. Skills Correlated with the Job Title “Data Scientist” 5
- 6. Skills Related to “Big Data” 6
- 9. 9
- 14. Reputation: Building the Endorsement Graph 14
- 15. 15 Viral Growth: 1 Billion Endorsements in 5 Months
- 16. How Did We Gather this Data? 16 1. Desire + Social Proof 2. Viral Loops + Network Effects 3. Data Foundation + Recommendation Algorithms
- 17. 17 1) Desire & Social Proof
- 18. A endorses B B notified B “accepts” endorsement B endorses C B endorses D Endorsement recommendations Email NotificationNews Feed 2) Viral Loops & Network Effects
- 19. 3) Data Foundation: Skills & Suggested Skills 19
- 20. Data Foundation: LinkedIn Skills 20
- 21. Social Tagging Accelerates Adoption Suggested endorsements Skill recommendations Skill marketing ©2012 LinkedIn Cororation. All Rights Reserved. Virality only
- 22. Outline 22 Skill discovery Skill tagging Skill recommendations Suggested endorsements
- 23. Skill Discovery: Unsupervised Topics from Profiles 23 Extract
- 24. Topic Clustering & Phrase Sense Disambiguation 24
- 25. Deduplication Signals from Mechanical Turk 25
- 26. Sample Task for Mechanical Turk Workers 26
- 28. Outline 28 Skill discovery Skill tagging Skill recommendations Suggested endorsements
- 29. Lead designer and engineer for the implementation of a user- centric, fully-configurable UI for data aggregation and reporting. Developed over 20 SaaS custom applications using Python, Javascript and RoR. Tagging Skill Phrases Tagging: Extract potential skill phrases from text Standardize unambiguous phrase variants 29 JavaScript RoR SaaS Python ror rubyonrails ruby on rails development ruby rails ruby on rail Ruby on Rails Document (ex: Profile) Tokenization Skills Tagger Phrases (up to 6 words) Skills Classifier Skills (unordered) Skills (ranked by relevance)
- 30. Outline 30 Skill discovery Skill tagging Skill recommendations Suggested endorsements
- 31. Skill Inference How suggested/inferred skills work: – The skill likelihood is a conditional model – Probabilities are combined using a Naïve Bayes Classifier If you are an engineer at Apple, you probably know about iPhone Development. 31 Profile Extract attributes - Company ID - Title ID - Groups ID - Industry ID - … Skills Classifier Skills (ranked by likelihood) Feature Vectors
- 37. Skill Recommendations for Your LinkedIn Profile 37 49% Conversion 4% Conversion
- 38. Outline 38 Skill discovery Skill tagging Skill recommendations Suggested endorsements
- 39. Social Tagging via Skill Endorsements 39
- 40. Social Tagging Accelerates Adoption Skill endorsements Skill recommendations Skill marketing ©2012 LinkedIn Cororation. All Rights Reserved.
- 41. Data Amplifies Desire 41 1. Desire + Social Proof 2. Viral Loops + Network Effects 3. Data Catalyst + Recommendation Algorithms
- 42. Over 58 Million Profiles are now Tagged with Skills 42
- 43. All This Data Flows Back Into Our Lucene Index 43
- 44. Helping us Connect Talent & Opportunity 44 Location
- 45. Questions? We’re hiring: data.linkedin.com @peteskomoroch ©2012 LinkedIn Corporation. All Rights Reserved. 45