23
Towards a Big Data Recommender Engine For Online and Offline Marketplaces Martin Kahr (Blanc-Noir) Christoph Trattner (Know-Center)

Towards a Big Data Recommender Engine for Online and Offline Marketplaces

Embed Size (px)

DESCRIPTION

Recommender systems aim at helping users to find relevant information in an overloaded information space. Although there are well known methods (Content-based, Collaborative Filtering, Matrix Factorization) and libraries to implement, evaluate and extend recommenders (Apache Mahout, Graphlab, MyMediaLite, among others), the deployment of a real-time recommender from scratch which considers a combination of algorithms and various data sources (e.g., social, transactional, and location) remains unsolved. In this talk, we report on the challenges towards such a recommender systems in the context of online of offline marketplaces. In particular, we describe our solution in terms of the requirements, the data model and algorithms that allows modularity and extensibility, as well as the system architecture to facilitate the scaling of our approach to big data for online and offline marketplaces.

Citation preview

Page 1: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

Towards a Big Data Recommender

EngineFor Online and Offline Marketplaces

Martin Kahr (Blanc-Noir)

Christoph Trattner (Know-Center)

Page 2: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

INHALT

Background and Introduction About Blanc-Noir│ Our Vision │ What we do

Partnership with Know-CenterPartnership │ Challenge and Goal│ Output

Recommender Enginexxxx │ xxxx

Q&A

Page 3: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

ABOUT BLANC-NOIR

Headquarter: Graz (Austria)

Subsidiaries: Ingolstadt (Germany)

Vienna, Klagenfurt,

Founded: 2012

Experience: More than 18 years in IT & Marketing

Employees: 60

Page 4: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

ABOUT BLANC-NOIR

Blanc-Noir combines Know-How in

marketing and technology

to create innovative and trendsetting

solutions for online and stationary

trade.

Page 5: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

OUR VISION

We want to change the buying

behavior of customers and to realize

a unique and sustainable shopping

experience.

Page 6: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

WHAT WE DO

• We develop analogue and digital marketing

strategies and campaigns

• Consulting, conception and programming of

E-Commerce and Multi-Channel platforms.

• Development of powerful promotion tools to

increase customer loyalty and shopping

experience.

• Pioneer in the area of Location Based Marketing

and Beacon-Technology

• Cross-Channel Order-Management System

Page 7: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

WHAT WE DO (EXAMPLES)

Digital Loyality CardOn- and offline collection and redeem

of bonus points

Mobil

PaymentNFC, Beacon

(Bluetooth 4.0)

Endless-aisleMobile catalogue and

Mobil shopping

Page 8: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

WHAT WE DO (EXAMPLES)

App for sellers

• Sales support

• Customer service

• Product information

• Endless-aisle

• Cross- & Upsell

• Coupon via Blue-tooth

to customer´s mobile

Page 9: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

PARTNERSHIP 1+1=3

By combining the resources and

competences of Know-Center with our

market-driven input,

we are able to realize a tailored and state-of-

the art solution that provides competitive

advantages for us and our clients.

Page 10: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

Unique shopping experience and higher conversions

assumes:

• Understanding and analytics of customer needs,

behaviour and preferences based on historic and live

transactions

• Personalized and real-time communication across all

customer touch points

• No spam - Only relevant and useful information

OUR CHALLENGE AND GOAL

Knowing what the customer

thinks, and desires!

Page 11: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

OUTPUT

Cross-Channel

customer understanding

and realtime targeting

Page 12: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

How did we manage to handle this

challenge?

Page 13: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

RECOMMENDER SYSTEMS

Page 14: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

14

Page 15: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

WHY SOLR?

• „High-performance, full-featured text search engine library“

… but more precise …

• „High-performance, fully-featured token matching and scoring library“

[Grainger, 2012]

… which provides ….

– full-text searches (content-based)

– powerful queries (e.g., MoreLikeThis or Facets)

– (near) real-time data updates (no pre/re-calculations)

– easy schema updates (social data integration)

• Established open-source software (Apache license) with big

community

15

Page 16: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

THE FRAMEWORK

Page 17: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

HOW does the thing perform?

Dataset of virtual world SecondLife: Marketplace and social data

17

Page 18: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

FOLLOW-UP (2)

Page 19: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

RECSIUM FRAMEWORK

Page 20: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

...CURRENTLY WORKING ON

• Location-based services shopping malls, train-

stations

• Technology: iBeacons

• Task: indoor navigation, indoor marketing, etc...

Page 21: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

...CURRENTLY WORKING ON

Page 22: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

DEMO - RECSIUM

http://recsium.know-center.tugraz.at/recsium/

Page 23: Towards a Big Data Recommender Engine for Online and Offline Marketplaces

ANY QUESTIONS?

THANK YOU