transforming your data: a worked example

Post on 23-Jan-2018

153 Views

Category:

Technology

2 Downloads

Preview:

Click to see full reader

TRANSCRIPT

09:00-09:30 09:30-10:15

10:15-11:00 11:00-11:30 11:30-12:30

12:30-13:30 13:30-17:00

Breakfast and RegistrationThe Connected Data Imperative: Why Graphs

Transform Your Data: A Worked ExampleBreakEnterprise Ready: A Look at Neo4j in Production LunchHands-On Training Session

Agenda

APRIL 26, 2017SANTA CLARA

Transform Your Data

Neo4j Graph Day - Santa Clara 2017William Lyon@lyonwj

A Worked Example

William LyonDeveloper Relations Engineer @neo4j

will@neo4j.com @lyonwj lyonwj.com

Agenda

• Graph database - developer perspective• (relational)-[:TO]->(graph)• Use cases• Fraud Detection• Recommendations

• Developer tooling

Neo4j

Graph Database

• Property graph data model• (open)Cypher query language• Native graph processing• Language drivers• Open source

neo4j.com

Graph Data Model

Labeled Property Graph Model

Labeled Property Graph Model

The Graph

https://github.com/johnymontana/neo4j-datasets/tree/master/yelp

The Graph

https://www.youtube.com/watch?v=kSZHFlBDIfM

The Graph

https://github.com/johnymontana/mattermark-graphql-neo4j

The Graph

https://github.com/neo4j-meetups/modeling-worked-example

The Graph

https://neo4j.com/sandbox-v2/

openCypher

(queryLanguage)-[:FOR]->(graphs)

http://www.opencypher.org/

Cypher

https://neo4j.com/sandbox-v2/

Use Case: Fraud Detection

Organized in groups Synthetic Identities Stolen Identities Hijacked Devices

Who Are Today’s Fraudsters?

Fraud Rings and Synthetic Identities

ACCOUNT HOLDER 2

Modeling a fraud ring as a graph

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

ACCOUNT HOLDER 2

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

CREDIT CARD

BANKACCOUNT

BANKACCOUNT

BANKACCOUNT

PHONE NUMBER

UNSECURED LOAN

SSN 2

UNSECURED LOAN

Modeling a fraud ring as a graph

ACCOUNT HOLDER 2

ACCOUNT HOLDER 1

ACCOUNT HOLDER 3

CREDIT CARD

BANKACCOUNT

BANKACCOUNT

BANKACCOUNT

ADDRESS

PHONE NUMBER

PHONE NUMBER

SSN 2

UNSECURED LOAN

SSN 2

UNSECURED LOAN

Modeling a fraud ring as a graph

https://neo4j.com/graphgist/9d627127-003b-411a-b3ce-f8d3970c2afa?ref=solutions

https://neo4j.com/graphgists/

Credit Card Fraud

(relational)-[:TO]->(graph)

FROM RDBMS TO GRAPHS

Northwind

Northwind - the canonical RDBMS Example

( )-[:TO]->(Graph)

( )-[:IS_BETTER_AS]->(Graph)

Starting with the ER Diagram

Locate the Foreign Keys

Drop the Foreign Keys

Find the JOIN Tables

(Simple) JOIN Tables Become Relationships

Attributed JOIN Tables -> Relationships with Properties

As a Graph

https://github.com/neo4j-contrib/neo4j-apoc-procedures/blob/master/readme.adoc

Northwind

Northwind

Neo4j Language Drivers

Neo4j Drivers

https://neo4j.com/developer/language-guides/

POWERING AN APP

Simple App

Simple App

Simple Python Code

Simple Python Code

Simple Python Code

Simple Python Code

https://neo4j.com/developer/

Use Case: Personalized Recommendations

Recommendations drive user engagement

“35 percent of what consumers purchase on Amazon and 75 percent of what they watch on Netflix come from product recommendations”

http://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers

Product Recommendations

Effective product recommendation algorithms has become the new standard in online retail — directly affecting revenue streams and the shopping experience.

Logistics/DeliveryRouting recommendations allows companies to save money on routing and delivery, and provide better and faster service.

Promotion recommendations

Building powerful personalized promotion engines is another area within retail that requires input from multiple data sources, and real-time, session based queries, which is an ideal task to solve with Neo4j.

Today Recommendation Engines are At the Core of Digitization in Retail

Powerful recommendation engines rely on the connections between multiple

sources of data

Powerful recommendation engines rely on the connections between multiple

sources of data

Dreamhouse Series 15% off

Dreamhouse Series 15% off

The Store

Search

Hi, loginMy Account

People who bought Side Table also bought:

Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

Mobile Brick & Mortar

Multi-Channel

Web

The Store

People who bought Side Table also bought: Similar product in from Home Office Series:

Hi, loginMy AccountSearch

Dreamhouse Series 15% off Dreamhouse Series 15% off

All departments Living room | Kitchen | Hallway | Lightning | Bedroom | Garden | Home Office Space

Tr a c k O r d e r s |   G i f t C a r d s |  S t o r e fin d e r | C r e d i t C a r d | G r o c e r y P i c k u p |  H e l p

Wood Side Table

$110Green Side Table

$135Walnut Side Table

$120Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

Product Recommendations

Dreamhouse Series 15% off

Dreamhouse Series 15% off

The Store

Search

Hi, loginMy Account

People who bought Side Table also bought:

Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

Mobile Brick & MortarWeb

The Store

People who bought Side Table also bought: Similar product in from Home Office Series:

Hi, loginMy AccountSearch

Dreamhouse Series 15% off Dreamhouse Series 15% off

All departments Living room | Kitchen | Hallway | Lightning | Bedroom | Garden | Home Office Space

Tr a c k O r d e r s |   G i f t C a r d s |  S t o r e fin d e r | C r e d i t C a r d | G r o c e r y P i c k u p |  H e l p

Wood Side Table

$110Green Side Table

$135Walnut Side Table

$120Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

The Store

People who bought Side Table also bought: Similar product in from Home Office Series:

Hi, loginMy AccountSearch

Dreamhouse Series 15% off Dreamhouse Series 15% off

All departments Living room | Kitchen | Hallway | Lightning | Bedroom | Garden | Home Office Space

Tr a c k O r d e r s |   G i f t C a r d s |  S t o r e fin d e r | C r e d i t C a r d | G r o c e r y P i c k u p |  H e l p

Wood Side Table

$110Green Side Table

$135Walnut Side Table

$120Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

Personalized Promotions Personalized Real-Time Recommendations

Personalized Real-Time Recommendations

The Store

People who bought Side Table also bought: Similar product in from Home Office Series:

Hi, loginMy AccountSearch

Dreamhouse Series 15% off Dreamhouse Series 15% off

All departments Living room | Kitchen | Hallway | Lightning | Bedroom | Garden | Home Office Space

Tr a c k O r d e r s |   G i f t C a r d s |  S t o r e fin d e r | C r e d i t C a r d | G r o c e r y P i c k u p |  H e l p

Wood Side Table

$110Green Side Table

$135Walnut Side Table

$120Coffee Table

$235Low Book Shelf

$150Bed Side Table

$90

Data-Model (Expressed as

a graph)

Category

Category

Product

Product

Product

Collaborative FilteringAn algorithm that considers users interactions with products, with the

assumption that other users will behave in similar ways.

Algorithm Types

Content BasedAn algorithm that considers

similarities between products and categories of products.

Customer

Customer

Product

Product

Product

Category Price ConfigurationsLocation

Silos & Polyglot Persistence

Purchase ViewReviewReturn In-store PurchasesInventory

Products Customers / Users

Location

Purchases

RELATIONAL DB WIDE COLUMN STORE

Views

DOCUMENT STORE

User Review

RELATIONAL DB

In-Store Purchase

Shopping Cart

KEY VALUE STORE

Product Catalogue

DOCUMENT STORE

Purchases

RELATIONAL DB WIDE COLUMN STORE

Views

DOCUMENT STORE

User Review

RELATIONAL DB

In-Store Purchase

Shopping Cart

KEY VALUE STORE

Product Catalogue

DOCUMENT STORE

Silos & Polyglot Persistence

Category Price ConfigurationsLocation Purchase ViewReviewReturn In-store PurchasesInventory

Products Customers / Users

Location

Purchases

RELATIONAL DB WIDE COLUMN STORE

Views

DOCUMENT STORE

User Review

RELATIONAL DB

In-Store Purchase

Shopping Cart

KEY VALUE STORE

Product Catalogue

DOCUMENT STORE

Category Price ConfigurationsLocation

Polyglot Persistence

Purchase ViewReviewReturn In-store PurchasesInventory LocationCategory Price ConfigurationsLocation Purchase ViewReviewReturn In-store PurchasesInventory

Products Customers / Users

Location

Data Lake

Purchases

RELATIONAL DB

Product Catalogue

DOCUMENT STORE WIDE COLUMN STORE

Views

DOCUMENT STORE

User Review

RELATIONAL DB

In-Store Purchase

Shopping Cart

KEY VALUE STORE

Recommendations require an operational workload — it’s in the moment, real-time!

Good for Analytics, BI, Map ReduceNon-Operational, Slow Queries

Purchases

RELATIONAL DB

Product Catalogue

DOCUMENT STORE WIDE COLUMN STORE

Views

DOCUMENT STORE

User Review

RELATIONAL DB

In-Store Purchase

Shopping Cart

KEY VALUE STORE

Connector

Drivers: Java |  JavaScript |  Python |  .Net |  PHP |  Go |  Ruby

Apps and Systems

Real-Time Queries

Using Data Relationships for Recommendations

Content-based filtering Recommend items based on what users have liked in the past

Collaborative filtering Predict what users like based on the similarity of their behaviors, activities and preferences to others

Movie

Person

Person

RATED

SIMILARITY

rating: 7

value: .92

Collaborative Filtering

Collaborative Filtering

Collaborative Filtering

Collaborative Filtering

Link prediction

In Cypher

In Cypher

Basic initial approach. Improvements:- aggregate across all purchases- scoring / normalize- compute similarity metrics

Content Filtering

Content Filtering

Content Filtering w/ Cypher

Content Filtering - Concept Hierarchy

Content Filtering - Concept Hierarchy

Content Filtering - Concept Hierarchy

Content Filtering - Concept Hierarchy w/ Cypher

Content Filtering - Concept Hierarchy w/ Cypher

Basic initial approach. Improvements:- aggregate across all purchases- cold start- variable length concept hierarchy- tag similarity / clusters

Neo4j Sandbox

neo4jsandbox.com

Want to learn more?

graphdatabases.com neo4j.com/sandbox

(you)-[:HAVE]->(?)(?)<-[:ANSWERS]-(will)

09:00-09:30 09:30-10:15

10:15-11:00 11:00-11:30 11:30-12:30

12:30-13:30 13:30-17:00

Breakfast and RegistrationThe Connected Data Imperative: Why Graphs

Transform Your Data: A Worked ExampleBreakEnterprise Ready: A Look at Neo4j in Production LunchHands-On Training Session

Agenda

APRIL 26, 2017SANTA CLARA

top related