tdwi exec 16 case study: linkedin voices of the member – a scalable analytics platform to create...

16
Case Study: LinkedIn Voices of the Member – A Scalable Analytics Platform to Create a Customer-First Environment Feb 2, 2016 Weidong Zhang Manager of Data & Analytics LinkedIn Chi-Yi Kuan Director of Business Analytics LinkedIn

Upload: chi-yi-kuan

Post on 14-Apr-2017

168 views

Category:

Internet


0 download

TRANSCRIPT

Page 1: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Case Study: LinkedIn Voices of the Member – A Scalable Analytics Platform to Create a

Customer-First Environment

Feb 2, 2016

Weidong ZhangManager of Data & Analytics

LinkedIn

Chi-Yi KuanDirector of Business Analytics

LinkedIn

Page 2: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Agenda

§  Introduction of LinkedIn business §  Introduction of Voices: a home-grown advanced analytics

platform to listen to our members §  Overview of end-to-end technologies that power Voices

platform §  Case Study: how we build a member first environment &

what we are working towards

2

Page 3: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Who are we?

www.linkedin.com/in/chiyikuan

Chi-Yi Kuan

•  Director, Business Analytics & Data Mining •  Big data evangelist and practitioner

www.linkedin.com/in/weidongzhang1

Weidong Zhang

•  Manager, Data & Analytics •  Build big data and analytics products

Page 4: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Create economic opportunity for every member of the

global workforce

Our vision

Page 5: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Create economic opportunity

Realize your dream job

Find work Be great at what you do

Page 6: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

LinkedIn’s BIG data

Page 7: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

7

Customer Care Tickets 2015-05-30

NPS – feedback 2015-06-03

In-app review 2015-06-03

App store review 2015-06-06

WHAT ARE PEOPLE SAYING? 380+ million members = a lot of data

Page 8: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

8

The impact of our Voices analytics platform

Developed game-changing solutions to drive Voice of Member impact

Improved analytics efficiency with unstructured data by 20X

Drove end-to-end technological integration on big data and embedding NLP solutions

Piloting operational solutions to scale advanced analytics impact for broader organization

Page 9: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Voices - A tool to listen to our members on what they are talking about LinkedIn and our products

9

Member “Voices” Internal & External

VOMC Transform Member Experiences

Page 10: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

How does Voices alleviate data wrangling pain points?

10

Member info

•  Identity •  Behavior •  Social

Social data

Customer feedback

•  Customer service •  Group updates •  Network updates

Survey results

Relevance solution

Topic mining

Classification engine

What’s trending

Products

Sentiments

Value Propositions

PYMK Group

Home Page Mobile Inbox

Identity Network

Hire Market Sell

Page 11: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

11

Trending Insights

§  Multi-channel, automatic intelligent solutions to provide trending information and help drive business actions

Machine Generated

Topics

Influencer/Top Executive Posts

Product Launch/ PR Events, etc.

What’s trending

Page 12: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

12

LinkedIn Hadoop Ecosystem

HDFS

Map-Reduce Spark Tez

Pig Hive Scalding

YARN AZK

AB

AN

Page 13: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

13

3 Major Design Principles for Voices Platform

Scalability Availability Easy to Use

Process Platform

Data Systems

Application Framework

Kafka, Hadoop, Spark Gobblin

Elasticsearch, NoSql Phoenix, Elasticsearch, Highcharts

Page 14: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

14

E2E Technologies that power Voices platform to achieve game-changing solutions

Page 15: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

Case Study: LinkedIn’s customer support has evolved into an intelligence platform…

Scaling to have a broader impact across LinkedIn

▪  GCO cases ▪  Issue resolution ▪  Support focused

▪  Internal data (GCO, surveys, site feedback)

▪  App review ▪  LI.com ▪  Social data

▪  Product insight ▪  Member insight ▪  Launch tracking

▪  Social sentiment ▪  Brand tracking ▪  Viral mentions

Reactive Multi-channel Intelligent Predictive

Support Feedback Insights Anticipation

15

Page 16: tdwi Exec 16 Case Study: LinkedIn Voices of the Member –  A Scalable Analytics Platform to Create a Customer-First Environment

…breaks down into sentiment and drivers…

4

(For LI data ) deep dive into MLC segmentation…

6

…geographic locations…

5

…and audience segmentation…

7

…generates automatic reporting, alerts and escalations…

8

…and close the feedback loop with support and PR solutions

9

This is what the future could look like From the first time we pick up an isolated comment…

1

Machine determines if there is significant reach…

2

…and whether it is a trending topic…

3

16