Build a serverless recommendation engine in 72 hours

Build a serverless recommendation engine in 72 hours @samueljabiodun |
Samuel James

@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

@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

@samueljabiodun In the beginning …

@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

@samueljabiodun

@samueljabiodun Code Runtime OS Hardware Physical Servers

@samueljabiodun Code Runtime OS Hardware Physical Servers Code Runtime OS
Hardware Virtual Machines Code Runtime OS Hardware Code Runtime OS Hardware Serverless Containers

@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

@samueljabiodun Serverless and PaaS  What is the difference?

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

@samueljabiodun Business Logic

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

@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

@samueljabiodun "There is no silver bullet. There are always options
and the options have consequences”  - Ben Horowitz

@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…

@samueljabiodun Serverless Recommendation Engine

@samueljabiodun

@samueljabiodun Recommendation is about suggesting relevant products to your users
based on the knowledge you have users, products, and users' interactions with your products

@samueljabiodun Recommendation is all about data

@samueljabiodun

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

@samueljabiodun "Netflix saves up to $1 billion a year via
its personalised recommendations”     – Business Insider

@samueljabiodun Personalised recommendations drive sales

@samueljabiodun Data Collection Data Storage Data Analysis Data Filtering Recommendation
Phases

@samueljabiodun Data Filtering Techniques − Collaborative Filtering − Content-Based Filtering
− Hybrid Filtering

@samueljabiodun Collaborative Filtering Interactions of users with products (like movies
watched, products viewed, products bought etc.

@samueljabiodun Collaborative Filtering Technique in a Retail Site

@samueljabiodun

@samueljabiodun Content-based Filtering Focuses on properties of items. Similarity of
items is determined by measuring the similarity in their properties.

@samueljabiodun Content-based Filtering Technique in a Retail Site

@samueljabiodun AWS Rekognition At A Glance

@samueljabiodun

@samueljabiodun   Analysing existing (millions, billions of) objects on S3
using AWS Batch

@samueljabiodun

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

@samueljabiodun Learn about your users Gain insights in to your
products

@samueljabiodun Users do search for products too, how about adding
a visual search?

@samueljabiodun

@samueljabiodun DEMO

@samueljabiodun

@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

@samueljabiodun

@samueljabiodun Thanks!  Questions?

Build a serverless recommendation engine in 72 ...

Build a serverless recommendation engine in 72 hours

More Decks by Samuel James

Other Decks in Technology

Featured

Transcript