use cases for graph visualization

Post on 22-Jan-2017

65 Views

Category:

Software

1 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Use cases for Graph Visualization

Corey Lanum & Sam Duby

The session will start at the top of the hour

16th August 2016

● Introductions

● Overview of use cases

● How to visualize graphs

○ Understanding terror networks

○ Tips for visualizing social networks

○ Detecting fraud with graphs

● Q&A - submit via the Citrix panel

Agenda

Reminder: This session is being recorded. Feel free to share!

Introductions

Sam Duby - Technical Sales EMEA

New to Cambridge Intelligence, looking after new &

existing customers in the EMEA region.

sam@cambridge-intelligence.com

Corey Lanum - Americas Manager

Manages US office and relationships with customers

in US, Canada and APAC area.

corey@cambridge-intelligence.com

Author of Visualizing Graph Data - quote ‘vgdweb’ for 39% off.

Purpose of Visualization

● To better understand the structure of the data

you are collecting

● To better understand the relationships

contained in the data you are collecting

Why Visualize Networks

● Some graph problems aren’t solved by visualization, for example recommendation engines

● Graph data is inherently visual

● Accessible by non-scientists

● Can convey a deeper understanding of the data

Who Uses Graph Visualization

Finance and Insurance● Fraud discovery and investigation

● Regulatory compliance

Information Technology

● Network topology

● Risk assessment

Government

● Defense and intelligence

● Law enforcement

Oil and Gas

● Physical infrastructure

Understanding Terror Networks

● In 2004, Marc Sageman assembled a series of tables of 176 known communications and meetings between Al-Qaeda members and sympathizers.

● The communications take place between individuals so can be treated as a matrix

● Communications can be assembled into an association matrix - showing who knows each other by making marks in a grid

● This can be binary, either there’s a link or not, or weighted, with values on those connections

We’re starting to get some value out of this data, but what about when we want to visualize it?

Understanding Terror Networks

● The problem with Social Network data is often too much data to visualize

● Data can be useful to identify influencers, groups, propagation throughout the network of information

● SNA centrality measures, Social Network Analysis can be particularly useful here.

● Twitter and public Facebook tweets/posts/likes can be downloaded via Netlytic, a free tool for SNA data. Commercial options are more robust.

Social Networks - Identify Influencers

Review Fraud

● User written reviews are critical to online commerce

● Sites like Amazon, Yelp, TripAdvisor all put their reviews front-and-center to drive sales and site visits

● One study showed a 19% increase in revenue for a 1 star increase in average rating on Yelp

● This creates an ‘unhealthy ecosystem’ of fraudsters looking to artificially inflate or deflate reviews of products

● The volume makes it difficult to read each review individually

● Graph visualization can help

● I have not done this for my book

Review Fraud

● First, we need to format the review data as a graph

● The nodes will be the concrete things in our data○ First, the products/businesses being

reviewed○ Second, the review itself, which has

the date/time of the review submission and the star rating as a property

○ Third, the known properties of the reviewer such as device fingerprint, IP address, and e-mail address

● The edges represent the links between the reviewer, the review, and the business

Review Fraud

● Let’s zoom in to identify suspicious patterns● On the left, we have used the KeyLines timebar to zoom in to

reviews only posted on a single day● On the right, we see multiple negative reviews of a restaurant that

day from users with no other activity ever. Is this legitimate or an attempt to defame?

Any Questions?

@CambridgeIntel Cambridge-Intelligence.com

info@cambridge-intelligence.com

top related