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

Build a serverless recommendation engine in 72 hours

Build a serverless recommendation engine in 72 hours

1fec00b719cf2b0d32ec9430bb85a9a4?s=128

Samuel James

October 16, 2019
Tweet

Transcript

  1. Build a serverless recommendation engine in 72 hours @samueljabiodun |

    Samuel James
  2. @samueljabiodun Who Am I? − AWS Solutions Architect (Associate) −

    Software Engineer @ Architrave Gmbh ✦ PropTech company of the year 2018 ✦ Over €12 billion in annual transaction volume (including Germany's largest single transactions: Sony Centre 2017 & Frankfurt Omni Tower 2018) ✦ Over 3,900 managed assets worth €80 billion
 − Technical Author @ HitSubscribe
  3. @samueljabiodun “At some point we’re going to see the first

    billion-dollar startup with a single employee, the founder, and that engineer will be using serverless." James Governor Co-founder at RedMonk
  4. @samueljabiodun In the beginning …

  5. @samueljabiodun Physical Machine ❏ Install and configure tons of packages

    to get your application up and run ❏ Very Expensive ❏ Scaling was an hassle ❏ Maintenance was still a problem
  6. @samueljabiodun

  7. @samueljabiodun Code Runtime OS Hardware Physical Servers

  8. @samueljabiodun Code Runtime OS Hardware Physical Servers Code Runtime OS

    Hardware Virtual Machines Code Runtime OS Hardware Code Runtime OS Hardware Serverless Containers
  9. @samueljabiodun Code Runtime OS Hardware Serverless Serverless
 …computing model that

    allows you to build and run code at scale without thinking about servers or infrastructures
  10. @samueljabiodun Serverless and PaaS
 What is the difference?

  11. @samueljabiodun − Scaling − Composition − Idle State Why PaaS

    Is Not Serverless (FaaS)
  12. @samueljabiodun − Scaling − Composition − Idle State Why PaaS

    Is Not Serverless (FaaS)
  13. @samueljabiodun Business Logic

  14. @samueljabiodun − Scaling − Composition − Idle State Why PaaS

    Is Not Serverless (FaaS)
  15. @samueljabiodun Why going serverless? − No server provisioning − Pay

    for usage only − Infinite scale − No server management − Quicker time to market − Monitoring and logging out of the box
  16. @samueljabiodun "There is no silver bullet. There are always options

    and the options have consequences”
 - Ben Horowitz
  17. @samueljabiodun Use cases − Data processing (Images, Videos etc) −

    Scalable static websites − Mobile backends − Real-time analysis − IoTs − Event streaming applications − Multi-lingual applications − And more…
  18. @samueljabiodun Serverless Recommendation Engine

  19. @samueljabiodun

  20. @samueljabiodun

  21. @samueljabiodun Recommendation is about suggesting relevant products to your users

    based on the knowledge you have users, products, and users' interactions with your products
  22. @samueljabiodun Recommendation is all about data

  23. @samueljabiodun

  24. @samueljabiodun 
 According to McKinsey & Company, 35% of Amazon.com’s

    revenue is generated by its recommendation engine.
  25. @samueljabiodun "Netflix saves up to $1 billion a year via

    its personalised recommendations” 
 
 – Business Insider
  26. @samueljabiodun Personalised recommendations drive sales

  27. @samueljabiodun Data Collection Data Storage Data Analysis Data Filtering Recommendation

    Phases
  28. @samueljabiodun Data Filtering Techniques − Collaborative Filtering − Content-Based Filtering

    − Hybrid Filtering
  29. @samueljabiodun Collaborative Filtering Interactions of users with products (like movies

    watched, products viewed, products bought etc.
  30. @samueljabiodun Collaborative Filtering Technique in a Retail Site

  31. @samueljabiodun

  32. @samueljabiodun

  33. @samueljabiodun Content-based Filtering Focuses on properties of items. Similarity of

    items is determined by measuring the similarity in their properties.
  34. @samueljabiodun Content-based Filtering Technique in a Retail Site

  35. @samueljabiodun AWS Rekognition At A Glance

  36. @samueljabiodun

  37. @samueljabiodun 
 Analysing existing (millions, billions of) objects on S3

    using AWS Batch
  38. @samueljabiodun

  39. @samueljabiodun Hybrid Filtering Combines collaborative filtering and content- based filtering

  40. @samueljabiodun Learn about your users Gain insights in to your

    products
  41. @samueljabiodun Users do search for products too, how about adding

    a visual search?
  42. @samueljabiodun

  43. @samueljabiodun DEMO

  44. @samueljabiodun

  45. @samueljabiodun Summary − Serverless reduces your development time − With

    Serverless, you do not need to be an AI expert to have AI capabilities in your app
  46. @samueljabiodun

  47. @samueljabiodun Thanks!
 Questions?