Building multi-modal recommendation engines using search engines

1©MapR Technologies 2013- Confidential

Introduction to MahoutAnd How To Build a Recommender

Topic For Today

What is recommendation? What makes it different? What is multi-model recommendation? How can I build it using common household items?

Oh … Also This

Detailed break-down of a live machine learning system running with Mahout on MapR

With code examples

I may have to summarize

just a bit

Part 1:5 minutes of background

Part 2:5 minutes: I want a pony

Part 1:5 minutes of background

What Does Machine Learning Look Like?

O(κ k d + k3 d) = O(k2 d log n + k3 d) for small k, high qualityO(κ d log k) or O(d log κ log k) for larger k, looser quality

But tonight we’re going to show you how to keep it simple yet powerful…

Recommendations as Machine Learning

Recommendation: – Involves observation of interactions between people taking action (users)

and items for input data to the recommender model– Goal is to suggest additional appropriate or desirable interactions– Applications include: movie, music or map-based restaurant choices;

suggesting sale items for e-stores or via cash-register receipts

Part 2:How recommenders work

(I still want a pony)

Recommendations

Recap:Behavior of a crowd helps us understand what individuals will do

Recommendations

Alice got an apple and a puppy

Charles got a bicycle

Charles

Recommendations

Alice got an apple and a puppy

Charles got a bicycle

Bob got an apple

Charles

Recommendations

What else would Bob like??

Charles

Recommendations

A puppy, of course!

Charles

You get the idea of how recommenders work… (By the way, like me, Bob also wants a pony)

Recommendations

What if everybody gets a pony?

Charles

Amelia What else would you recommend for Amelia?

Recommendations

Charles

AmeliaIf everybody gets a pony, it’s not a very good indicator of what to else predict...

Problems with Raw Co-occurrence

Very popular items co-occur with everything (or why it’s not very helpful to know that everybody wants a pony…)– Examples: Welcome document; Elevator music

Very widespread occurrence is not interesting as a way to generate indicators – Unless you want to offer an item that is constantly desired, such as razor

blades (or ponies)

What we want is anomalous co-occurrence– This is the source of interesting indicators of preference on which to

base recommendation

Get Useful Indicators from Behaviors

1. Use log files to build history matrix of users x items– Remember: this history of interactions will be sparse compared to all

potential combinations

2. Transform to a co-occurrence matrix of items x items

3. Look for useful co-occurrence by looking for anomalous co-occurrences to make an indicator matrix

– Log Likelihood Ratio (LLR) can be helpful to judge which co-occurrences can with confidence be used as indicators of preference

– RowSimilarityJob in Apache Mahout uses LLR

Log Files

Charles

Log Files

Log Files and Dimensions

Things

u1 Alice

BobCharles

History Matrix: Users by Items

Charles

✔ ✔ ✔

✔ ✔

Co-occurrence Matrix: Items by Items

How do you tell which co-occurrences are useful?.

Co-occurrence Matrix: Items by Items

Use LLR test to turn co-occurrence into indicators…

Co-occurrence Binary Matrix

Spot the Anomaly

A not A

B 13 1000

not B 1000 100,000

A not A

not B 0 2

A not A

not B 0 10,000

A not A

B 10 0

not B 0 100,000

What conclusion do you draw from each situation?

Spot the Anomaly

Root LLR is roughly like standard deviations In Apache Mahout, RowSimilarityJob uses LLR

A not A

B 13 1000

not B 1000 100,000

A not A

not B 0 2

A not A

not B 0 10,000

A not A

B 10 0

not B 0 100,000

0.90 1.95

4.52 14.3

What conclusion do you draw from each situation?

Co-occurrence Matrix

Recap: Use LLR test to turn co-occurrence into indicators

Indicator Matrix: Anomalous Co-Occurrence

✔✔

Result: The marked row will be added to the indicator field in the item document…

Indicator Matrix

id: t4title: puppydesc: The sweetest little puppy ever.keywords: puppy, dog, pet

indicators: (t1)

That one row from indicator matrix becomes the indicator field in the Solr document used to deploy the recommendation engine.

Note: data for the indicator field is added directly to meta-data for a document in Solr index. You don’t need to create a separate index for the indicators.

Internals of the Recommender Engine

Looking Inside LucidWorks

What to recommend if new user listened to 2122: Fats Domino & 303: Beatles?

Recommendation is “1710 : Chuck Berry”

Real-time recommendation query and results: Evaluation

Search-based Recommendations

Sample document– Merchant Id– Field for text description– Phone– Address– Location

– Indicator merchant id’s– Indicator industry (SIC) id’s– Indicator offers– Indicator text– Local top40

Sample query– Current location– Recent merchant descriptions– Recent merchant id’s– Recent SIC codes– Recent accepted offers– Local top40

Original data and meta-data

Derived from cooccurrence and cross-occurrence analysis

Recommendation query

For example

Users enter queries (A)– (actor = user, item=query)

Users view videos (B)– (actor = user, item=video)

ATA gives query recommendation– “did you mean to ask for”

BTB gives video recommendation– “you might like these videos”

The punch-line

BTA recommends videos in response to a query– (isn’t that a search engine?)– (not quite, it doesn’t look at content or meta-data)

Real-life example

Query: “Paco de Lucia” Conventional meta-data search results:– “hombres del paco” times 400– not much else

Recommendation based search:– Flamenco guitar and dancers– Spanish and classical guitar– Van Halen doing a classical/flamenco riff

Real-life example

Hypothetical Example

Want a navigational ontology? Just put labels on a web page with traffic– This gives A = users x label clicks

Remember viewing history– This gives B = users x items

Cross recommend– B’A = label to item mapping

After several users click, results are whatever users think they should be

Nice. But we can do better?

A Quick Simplification

Users who do h (a vector of things a user has done)

Also do r

User-centric recommendations(transpose translates back to things)

Item-centric recommendations(change the order of operations)

A translates things into users

Symmetry Gives Cross Recommentations

Conventional recommendations with off-line learning

Cross recommendations

things

thingtype 1

thingtype 2

Part 3:What about that worked example?

http://bit.ly/18vbbaT

SolRIndexerSolR

IndexerSolrindexing

Cooccurrence(Mahout)

Item meta-data

Indexshards

Complete history

Analyze with Map-Reduce

SolRIndexerSolR

IndexerSolrsearchWeb tier

Item meta-data

Indexshards

User history

Deploy with Conventional Search System

Me, Us

Ted Dunning, Chief Application Architect, MapRCommitter PMC member, Mahout, Zookeeper, DrillBought the beer at the first HUG

MapRDistributes more open source components for HadoopAdds major technology for performance, HA, industry standard API’s

InfoHash tag - #maprSee also - @ApacheMahout @ApacheDrill

@ted_dunning and @mapR

Building multi-modal recommendation engines using search engines

Technology

Playing The Search Engines · Playing The Search Engines or Hacking The Box Frédéric Philipp Thiele / Prof. Hendrik Speck Suma e.V. - Gemeinnütziger Verein zur Förderung der Suchmaschinen-Technologie

Search Engines Chapter 2 Summary

Investigating the Relevance of Sponsored Results for Web Ecommerce Queries Keywords Web search engines, sponsored search, sponsored results, sponsored

محركات البحث Search Engines ادلة البحث Search Directories الباحثات الشاملة Meta Search Engines البوبات العامة Portals البوبات

Microsoft Academic Search - Moravian Library · an hour ago - Search Engine Land: News & Info About SEO PPC SEM Search Engines & Search Marketing Need to get rid of problematic or

Recommendation System - WUNCA · 2017-08-11 · Recommendation Single Search KMUTT-LM : Smart Information Analysis System Phase I Phase II Phase III SIAS1-Mobi SIAS2-Analis SIAS3-Xplore

Lecture 1: 마이크로프로세서소개및설명 - CBNU · 과제중간발표 ... – Cell phones – Human genome project – World Wide Web – Search Engines • Computers are

EPL660: Information Retrieval and Search Engines Lab 3 · EPL660: Information Retrieval and Search ... • This will start up a SolrCloud cluster with embedded ZooKeeper (cloud management

Similar Document Search and Recommendation Vidhya Govindaraju, Krishnan Ramanathan HP Labs, Bangalore, India JOURNAL OF EMERGING TECHNOLOGIES IN WEB INTELLIGENCE

Introduction into Search Engines and Information Retrieval

Search Engines - UMY

Chedong Why Search Engines Like Blog

Search engines overview

Search Engines - dg3rtljvitrle.cloudfront.netdg3rtljvitrle.cloudfront.net/slides/chap10.pdf · Search Engines Information ... car cat chicago china christmas church city clouds color

Complementing search engines with online web mining agents ... fileMotivationAnsätzeMenczers AgentsErgebnisse Outline 1 Motivation Eine kleine Geschichte des Information Retrieval

How to build the next 1000 search engines?!

Tópicos Especiais I: Engines Engines 3D

Indexing, vector spaces, search engines

Εύρεση ∆ιαχείριση Πληροφορίαςστον ...delab.csd.auth.gr/.../lectures/ir_spring07_lec07_1in1.pdf · 2007-04-27 · 3. Search engines make aggregation

Measuring the quality of web search engines