Build a Powerful Recommendation Engine Using Image Recognition - - PowerPoint PPT Presentation

▶
build a powerful recommendation engine using image
SMART_READER_LITE
LIVE PREVIEW

Build a Powerful Recommendation Engine Using Image Recognition - - PowerPoint PPT Presentation

Jan 05, 2024 227 likes •523 views

Build a Powerful Recommendation Engine Using Image Recognition Technology on AWS Samuel James | 09.09.2019 Community Day 2019 Sponsors About Architrave Gmbh PropTech Company of the year 2018 Over 3,900 managed assets worth

slide-1
SLIDE 1

Samuel James | 09.09.2019

Community Day 2019 Sponsors

Build a Powerful Recommendation Engine Using Image Recognition Technology on AWS


slide-2
SLIDE 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
slide-3
SLIDE 3

What This Talk is Not About

Recommender Systems’ Algorithms

slide-4
SLIDE 4

Agenda

Recommendation system Why recommender systems are important How recommendation engines work Leveraging on AWS Rekognition for product recommendation Demo

slide-5
SLIDE 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.

slide-6
SLIDE 6

6

slide-7
SLIDE 7

7

According to McKinsey & Company, 35% of Amazon.com’s revenue is generated by its recommendation engine

slide-8
SLIDE 8

8

"Netflix saves up to $1 billion a year via its personalised recommendations” 
 


– Business Insider

slide-9
SLIDE 9

9

Personalised recommendations drive sales

slide-10
SLIDE 10

Recommendation Phases

Data Collection Data Storage Data Analysis Data Filtering

slide-11
SLIDE 11

Collaborative Filtering Content-Based Filtering Hybrid Filtering

Data Filtering Techniques

slide-12
SLIDE 12

Collaborative Filtering

Interactions of users with products (like movies watched, products viewed, products bought etc.

slide-13
SLIDE 13

Collaborative Filtering Technique in a Retail Site

slide-14
SLIDE 14

Content-based Filtering

Focuses on properties of items. Similarity of items is determined by measuring the similarity in their properties.

slide-15
SLIDE 15

Content-Based Filtering Technique in a Retail Site

slide-16
SLIDE 16

Hybrid Filtering

Combines collaborative filtering and content-based filtering.

slide-17
SLIDE 17

17

Leveraging on AWS Rekognition API for analysis of unstructured data like images

slide-18
SLIDE 18

AWS Rekognition at a Glance

slide-19
SLIDE 19

19

slide-20
SLIDE 20

20

slide-21
SLIDE 21

21

DEMO

slide-22
SLIDE 22

Using S3 Batch Operations

slide-23
SLIDE 23

Handling new Uploads

slide-24
SLIDE 24

24

slide-25
SLIDE 25

25

How the visual search works

slide-26
SLIDE 26

26

slide-27
SLIDE 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

slide-28
SLIDE 28

28

Thanks!


Questions?

Contact
 


Architrave GmbH Bouchéstraße 12, Building 1A, 12435 Berlin

Samuel James
 


Samuel James Email: james@architrave.de @samuelabiodunj