Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

ML & Automation in SEO - Traffic Think Tank Conference 2019

281 views

Published on

What is Machine Learning?
How can you use it to make your job more efficient?
What are the necessary tools and resources you need to get started?
Explore ways you can automate various SEO tasks today!

Published in: Education
  • Be the first to comment

ML & Automation in SEO - Traffic Think Tank Conference 2019

  1. 1. Machine Learning & Automation In SEO Britney Muller Senior Data Scientist @ Moz
  2. 2. #TTTLIVE19 74% of online consumers get frustrated when content appears that has nothing to do with their interests. 1. It already effects the work that you do. 2. You should be able to speak intelligently about it. 3. Level up by adding it to your arsenal. Why You Should Care About ML: –
  3. 3. #TTTLIVE19
  4. 4. #TTTLIVE19
  5. 5. #TTTLIVE19
  6. 6. #TTTLIVE19
  7. 7. #TTTLIVE19
  8. 8. #TTTLIVE19
  9. 9. #TTTLIVE19
  10. 10. #TTTLIVE19 bit.ly/tf-for-poets
  11. 11. #TTTLIVE19
  12. 12. #TTTLIVE19
  13. 13. #TTTLIVE19
  14. 14. #TTTLIVE19
  15. 15. #TTTLIVE19
  16. 16. #TTTLIVE19 65% Probability this is Rand!
  17. 17. #TTTLIVE19 Automated Image Optimization
  18. 18. #TTTLIVE19 ML is everywhere!
  19. 19. #TTTLIVE19 1. Let’s break down Machine Learning 2. How can you apply ML to SEO 3. Tools & Resources
  20. 20. #TTTLIVE19 What is Machine Learning? •Machine Learning is a subset of AI that combines statistics & programming to give computers the ability to “learn” without explicitly being programmed.
  21. 21. #TTTLIVE19 Supervised vs. Unsupervised
  22. 22. #TTTLIVE19 Three Common Models:
  23. 23. #TTTLIVE19
  24. 24. But, how do ML models get smarter?
  25. 25. #TTTLIVE19 The Loss Function:
  26. 26. #TTTLIVE19 Overfitting is a common problem:
  27. 27. #TTTLIVE19
  28. 28. #TTTLIVE19
  29. 29. #TTTLIVE19 10 Year Challenge
  30. 30. #TTTLIVE19 1. Let’s break down Machine Learning 1. How can you apply ML to SEO 1. Tools & Resources
  31. 31. #TTTLIVE19
  32. 32. #TTTLIVE19
  33. 33. #TTTLIVE19
  34. 34. Writing Meta Descriptions Sucks
  35. 35. #TTTLIVE19
  36. 36. #TTTLIVE19
  37. 37. #TTTLIVE19
  38. 38. #TTTLIVE19 New Auto Generated Previous Google Generated
  39. 39. #TTTLIVE19 @jroakes @GraysonParks Grayson Parks Writer, programmer, constant learner. Digital marketer, husband, golden retriever owner. Words and data are my passions. #SEO @AdaptPartners GraysonParks.com JR Oakes Love working with smart people on smart things. Tech SEO Director at @adaptpartners codeseo.io
  40. 40. #TTTLIVE19
  41. 41. #TTTLIVE19 1. Assist with deploying AWS Lambda. --Several steps will affect the cost & security. 2. Extract the content of the webpage using the library Goose3 (a Python library w/BeautifulSoup). 3. Summarize the content using summa (or another summarizing library/model) 4. Create a Lambda Function. a. Package the files for AWS Lambda & install the dependencies (in this case Goose3 and summa, etc) into a folder along with what is called a handler file. The handler file is what Lambda calls to run your script. b. Here is the packaged Lambda function (including the dependencies): https://s3.amazonaws.com/ap-lambda-functions/meta_summa.zip 5. Once the zip file is deployed to AWS as a Lambda function, you should get a URL to access the API that looks like: https://XXXXXXXX.execute-api.us-east-1.amazonaws.com/v1/ap_meta_descriptions Find a developer familiar with AWS to:
  42. 42. #TTTLIVE19 function pageDescription(url, length) { if (typeof length == 'undefined' || !length || length < 1){ var endpoint = 'https://XXXXXXXX.execute-api.us-east-1.amazonaws.com/v1/ap_meta_descriptions?url=' + url; }else{ var endpoint = 'https://XXXXXXXX.execute-api.us-east-1.amazonaws.com/v1/ap_meta_descriptions?url=' + url + "&len=" + length; } var response = UrlFetchApp.fetch(endpoint); var text = response.getContentText(); var data = JSON.parse(text); if (data){ return data.meta_description } } Copy & Paste like a badass in GSheets! =pageDescription(A2, 150)
  43. 43. #TTTLIVE19
  44. 44. #TTTLIVE19 Use Text Summarization Algorithms to Help Aid the Writing of Meta Descriptions (GitHub Repo)
  45. 45. #TTTLIVE19 Podcasts
  46. 46. #TTTLIVE19 The average podcast listener consumes 7 different podcasts a week. -https://www.podcastinsights.com/podcast-statistics/
  47. 47. #TTTLIVE19
  48. 48. #TTTLIVE19 JSON Output example (jq to parse)
  49. 49. #TTTLIVE19
  50. 50. #TTTLIVE19
  51. 51. #TTTLIVE19
  52. 52. #TTTLIVE19
  53. 53. #TTTLIVE19 Finding ranking opportunities Title tag optimization Keyword opportunity gaps Client reports Finding common question opportunities Content creation Log file analysis Parsing text into entities (insurance ex) GSC data analysis Rich customer understanding Traffic predictions Ranking factor probabilities User engagement insights Marketplace Creation Other SEO Opportunities with Machine Learning:
  54. 54. #TTTLIVE19 1. Let’s break down Machine Learning 1. How can you apply ML to SEO 1. Tools & Resources
  55. 55. #TTTLIVE19 Collect & clean dataset Build your model Train Evaluate Predict Most of the work A few lines of code One line One line One line Steps To Build Your First ML Model:
  56. 56. #TTTLIVE19
  57. 57. #TTTLIVE19
  58. 58. #TTTLIVE19
  59. 59. #TTTLIVE19
  60. 60. #TTTLIVE19
  61. 61. #TTTLIVE19
  62. 62. #TTTLIVE19 CPU > GPU > FPGAs > TPU Flexibility< ------------------------------------------- > Power
  63. 63. #TTTLIVE19 Search ‘Harvard CS109’ in GitHub Google CodeLabs – Break things!!! Colab Notebooks OR Jupyter Notebooks Learn With Google AI Image-net.org (don’t forget it’s racist tho!) Kaggle Getting Started Resources
  64. 64. #TTTLIVE19 Yearning Learning (free book preview by Andre Ng) Neural Networks & Deep Learning Correlation vs Causation (by Dr. Pete!) Exploring Word2Vec The Zipf Mystery BigML Targeting Broad Queries in Search Project Mosaic Books How to eliminate bias in data driven marketing TensorFlow Dev Summit 2018 [videos] NLP Sentiment Analysis Talk 2 Books The Shallowness of Google Translate TF-IDF LSI LDA Learn Python Massive Open Online Courses Coursera Machine Learning RAY by Professors at UC Berkeley Advanced Resources
  65. 65. #TTTLIVE19 What did we learn? ➢ Machine Learning combines statistics & programming ➢ A model is only as good as its training data!!!! ➢ Avoid overfitting. ➢ YOU can create a ML model today!!! ➢ ML will help scale SEO tasks & allow us to evolve as SEOs
  66. 66. #TTTLIVE19 Thank you! @BritneyMuller britney@moz.com

×