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.

Aws community day keynote

147 views

Published on

Images provide a richer set of information when building a search query for certain categories like fashion and furniture

According to Gartner's reports, brands with websites that support voice and visual search are expected to increase their digital commerce revenue by 30 percent by 2021.

In this session, I will show you how to build a visual search platform using AWS Rekognition, AWS Lambda, AWS API Gateway, and other managed AWS services

Published in: Engineering

Aws community day keynote

  1. 1. Samuel James | 09.09.2019 Community Day 2019 Sponsors Build a Powerful Recommendation Engine Using Image Recognition Technology on AWS

  2. 2. About Architrave Gmbh PropTech Company of the year 2018 Over 3,900 managed assets worth €80 billion Over €12 billion in annual transaction volume (including Germany's largest single transactions: Sony Centre 2017 and Frankfurt Omni Tower 2018) ! Berlin ! Frankfurt! Dresden
  3. 3. What This Talk is Not About Recommender Systems’ Algorithms
  4. 4. Agenda Recommendation system Why recommender systems are important How recommendation engines work Leveraging on AWS Rekognition for product recommendation Demo
  5. 5. What Is Recommendation ? Recommendation is about providing relevant content to the user based on knowledge of the user, content, and interactions between the user and items.
  6. 6. !6
  7. 7. !7 According to McKinsey & Company, 35% of Amazon.com’s revenue is generated by its recommendation engine
  8. 8. !8 "Netflix saves up to $1 billion a year via its personalised recommendations” 
 
 – Business Insider
  9. 9. !9 Personalised recommendations drive sales
  10. 10. Recommendation Phases Data Collection Data Storage Data Analysis Data Filtering
  11. 11. Collaborative Filtering Content-Based Filtering Hybrid Filtering Data Filtering Techniques
  12. 12. Collaborative Filtering Interactions of users with products (like movies watched, products viewed, products bought etc.
  13. 13. Collaborative Filtering Technique in a Retail Site
  14. 14. Content-based Filtering Focuses on properties of items. Similarity of items is determined by measuring the similarity in their properties.
  15. 15. Content-Based Filtering Technique in a Retail Site
  16. 16. Hybrid Filtering Combines collaborative filtering and content-based filtering.
  17. 17. !17 Leveraging on AWS Rekognition API for analysis of unstructured data like images
  18. 18. AWS Rekognition at a Glance
  19. 19. !19
  20. 20. !20
  21. 21. !21 DEMO
  22. 22. Using S3 Batch Operations
  23. 23. Handling new Uploads
  24. 24. !24
  25. 25. !25 How the visual search works
  26. 26. !26
  27. 27. Lessons Learned Building with AWS reduces your development time You don't need to be AI experts to have AI capability in your app Build a repeatable and reusable infrastructure with AWS
  28. 28. !28 Thanks!
 Questions? Contact
 
 Architrave GmbH Bouchéstraße 12, Building 1A, 12435 Berlin Samuel James
 
 Samuel James Email: james@architrave.de @samuelabiodunj

×