SlideShare a Scribd company logo
1 of 44
Download to read offline
Making Meaningful Restaurant
Recommendations @OpenTable
Sudeep Das, PhD
Data Scientist
OpenTable
@datamusing
CONFIDENTIAL 2
• Over 32,000 restaurants worldwide
• more than 885 million diners seated since 1998,
representing more than $30 billion spent at partner
restaurants
• Over 17 million diners seated every month
• OpenTable has seated over 254 million diners via a
mobile device. Almost 50% of our reservations are
made via a mobile device
• OpenTable currently has presence in US, Canada,
Mexico, UK, Germany and Japan
• OpenTable has nearly 600 partners including Bing,
Facebook, Google, TripAdvisor, Urbanspoon, Yahoo
and Zagat.
3
OpenTable
the world’s leading provider of online restaurant
reservations
At OpenTable
we aim to power
the best dining
experiences!
Ingredients of a
magical experience
Understanding the diner Understanding the restaurant
Building up a profile of you as a
diner from explicit and implicit
signals - information you have
provided, reviews you have written,
places you have dined at etc.
What type of restaurant is it?
What dishes are they known for?
Is it good for a date night/ family
friendly/ has amazing views etc.
What’s trending?
Connecting the dots
we have a wealth
of data
32 million reviews
diner
requests and
notes
menus
external
ratings,
searches and
transactions
images
Making meaningful
recommendations
diner-restaurant
Interactions
restaurant metadata
The basic ingredients
user metadata
ratings|searches|reviews
…
cuisine|price range|hours|topics
…
user profile
There are various approaches to
making meaningful recommendations
Nearest neighbor approaches in user-user or item-item space
Collaborative Filtering based on explicit/implicit interactions
Content-based approach leveraging restaurant metadata
Factorization machines that include interactions, metadata, as well as context.
10
Recommendations: Restaurant Similarity
Matrix Factorization:
Implicit preferences
Restaurant_1 Restaurant_2 … Restaurant_M
Diner_1 50 ? … 100
Diner_2 ? 1 … ?
… … … …
Diner_N 3 30 … 1
Implicit Preferences (Hu, Koren, Volinsky 2008)
Confidence Matrix
Binary
Preference
Matrix
14
Ensemble parameter is a function of the
user support
Purely Similarity
Purely Model based
Weighted mean inverse rank
¯a = ↵ 1
r1
+ (1 ↵) 1
r2
15
Mining the
wealth of
textual data
for cold start
and beyond …
Content Based Approach
• Comes in very handy for cold start where users have very few interactions
Very useful for cold
start where users
have very few
interactions.
Given a few
interactions we can
find similar
restaurants.
Bayesian
information retrieval
approach.
Content
based
approach
18
Our reviews are rich and verified,
and come in all shapes and sizes
Superb!
This really is a hidden gem and I'm not sure I want to
share but I will. :) The owner, Claude, has been here
for 47 years and is all about quality, taste, and not
overcharging for what he loves. My husband and I
don't often get into the city at night, but when we do
this is THE place. The Grand Marnier Souffle' is the
best I've had in my life - and I have a few years on the
life meter. The custard is not over the top and the
texture of the entire dessert is superb. This is the only
family style French restaurant I'm aware of in SF. It
also doesn't charge you an arm and a leg for their
excellent quality and that also goes for the wine list.
Soup, salad, choice of main (try the lamb shank) and
choice of dessert - for around $42 w/o drinks.
Many restaurants have thousands of reviews.
Word2Vec: Word Embeddings
[1] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient Estimation of Word Representations in Vector
Space. In Proceedings of Workshop at ICLR, 2013.
[2] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Distributed Representations of Words
and Phrases and their Compositionality. In Proceedings of NIPS, 2013.
[3] Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. Linguistic Regularities in Continuous Space Word
Representations. In Proceedings of NAACL HLT, 2013.
“We've [been here for afternoon tea multiple times, and each time] we
find it very pleasant”
[ 0.00513298, 0.10313627, 0.0773475 , ..., -0.07634512, 0.00877244, 0.04441034]Vec[tea]=
‘teas', ‘empress', ‘scones', ‘iced’, 'fortnum', ‘salon', ‘teapot', ‘teapots', ‘savories', ‘afternoon',
‘earlgrey' ….
model.most_similar(‘tea’ ):
20
bouillabaisse
muscles
diavalo
linguini
clams
mussels
diavlo
pescatore
risotto
linguine
pescatora
seafood
rissoto
diabolo
mussles
ciopino
swordfish
mussel
fettuccine
gumbo
brodetto
ciopinno
capellini
cockles
langostines
cannelloni
rockfish
bisques
diavolo
cockle
stew
shrimp
prawns
fettucine
cardinale
bouillabaise
pasta
jambalaya
chippino
Early explorations with Word2vec:
Find synonyms for “cioppino”
21
Early explorations with word2vec:
pairings
Halibut: Chardonnay
Lamb: ?
22
Early explorations with word2vec:
pairings
Halibut: Chardonnay
Lamb: Zinfandel
23
Early explorations with word2vec:
pairings
Halibut: Chardonnay
Lamb: Zinfandel
24
Sushi of Gari,
Gari Columbus, NYC
Masaki Sushi
Chicago
Sansei Seafood Restaurant & Sushi
Bar, Maui
A restaurant like your favorite one but in a
different city.
Find the “synonyms” of the restaurant in question, then filter by location!
Akiko’s, SF
San Francisco Maui Chicago New York
'
Downtown upscale sushi experience with sushi bar
25
Harris’
Steakhouse in
Downtown area
~v(Harris’) + ~v(jazz)
Broadway
Jazz Club
Steakhouse
with live jazz
~v(Harris’) + ~v(patio)
~v(Harris’) + ~v(scenic) Celestial
Steakhouse
Steakhouse
with a view
Patio at Las
Sendas
Steakhouse
with amazing
patio
Translating restaurants
via concepts
Going beyond
the metadata
with Topic
Modeling
27
We expect diner reviews to be broadly
composed of a handful of broad themes
Food &
Drinks
Ambiance Service
Value for
Money
Special
occasions
This motivated diving into the reviews with topic modeling
28
We applied non-
negative matrix
factorization to
learn topics …
• stopword removal
• vectorization
• TFIDF
• NNMF
29
Topics fell nicely into categories
DrinksFood Ambiance
30
Topics fell nicely into categories
ServiceValue Occasions
Our topics reveal the unique aspects of each
restaurant without having to read the reviews …
Each review
for a given
restaurant
has certain
topic
distribution
Combining
them, we
identify the
top topics
for that
restaurant.
0
0.5
1
Topic 01 Topic 02 Topic 03 Topic 04 Topic 05
0
0.5
1
Topic 01 Topic 02 Topic 03 Topic 04 Topic 05
0
0.5
1
Topic 01 Topic 02 Topic 03 Topic 04 Topic 05
review 1
review 2
review N
.
.
.
0
0.5
1
Topic 01 Topic 02 Topic 03 Topic 04 Topic 05
Restaurant
Looking at the
topics and the top
reviews associated
with it , we know
Espetus
Churrascaria is
not just about
meat and steak,
but has good salad
as well! The service
is top notch, its kid
friendly, and
people go for
special occasions,
…
Content Based Approach
• Comes in very handy for cold start where users have very few interactions
Very useful for cold
start where users
have very few
interactions.
Given a few
interactions we can
find similar
restaurants.
Bayesian
information retrieval
approach.
Content
based
approach
+ Topic Weights
Adding value
beyond just
making the
recommendation
35
We leveraged food and drink related topics to
expand our corpus of dishes and drinks
Most dishes are usually 1-grams
(“tiramisu”) 2-grams (“pork cutlets”) or
3-grams (“lemon ricotta pancake”)
For each restaurant, we perform an N-gram
analysis of the reviews within the scope of food
topics and surface candidate dish tags
We were able to generate several
thousands of dish tags using this
methodology!
EDINBURGH
MANCHESTER
YORK
SHIRE
KENT
LONDON
37
Sentiments - we use ratings as labels
for positive and negative sentiments
Ingredients of a stellar experience
38
Sentiments - we use ratings as labels
for positive and negative sentiments
Ingredients of a terrible experience
39
The model knows that “to die for”, “crispy”, “moist”
are actually indicative of positive sentiment when it
comes to food!
•The lobster and avocado eggs Benedict are to die for.
• We finished out meal with the their blackberry bread pudding which was so moist and
tasty.
•The pork and chive dumplings were perfectly crispy and full of flavor.
•I had the Leg of Lamb Tagine and it was "melt in-your-mouth" wonderful.
•… we did our best with the scrumptious apple tart and creme brulee.
•My husband's lamb porterhouse was a novelty and extremely tender.
•We resisted ordering the bacon beignets but gave in and tried them and were glad we
did---Yumm! …
40
41
We also
learn
restaurant
specific
attributes
from
review text
We learn features
using one vs. all
Logistic
Regression with
L1 regularization
via a mech turk
curated labeled
set.
For outdoor seating features include obvious ones such as ‘outdoor’, ‘patio’, as
well as ‘raining’, ‘sunny’, ‘smoke’, etc. …
42
Dish+Attribute tags and topics can
be used to enhance user profiles
• Rendle (2010) www.libfm.org
Including everything + context:
Factorization Machines
W
ORK
IN
PROGRESS
CONFIDENTIAL
keep in touch
@datamusing

More Related Content

What's hot

Time, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsTime, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsYves Raimond
 
Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014Erik Bernhardsson
 
Movie lens recommender systems
Movie lens recommender systemsMovie lens recommender systems
Movie lens recommender systemsKapil Garg
 
How netflix manages petabyte scale apache cassandra in the cloud
How netflix manages petabyte scale apache cassandra in the cloudHow netflix manages petabyte scale apache cassandra in the cloud
How netflix manages petabyte scale apache cassandra in the cloudVinay Kumar Chella
 
Recommending and Searching (Research @ Spotify)
Recommending and Searching (Research @ Spotify)Recommending and Searching (Research @ Spotify)
Recommending and Searching (Research @ Spotify)Mounia Lalmas-Roelleke
 
Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Mounia Lalmas-Roelleke
 
Collaborative Filtering with Spark
Collaborative Filtering with SparkCollaborative Filtering with Spark
Collaborative Filtering with SparkChris Johnson
 
Context Aware Recommendations at Netflix
Context Aware Recommendations at NetflixContext Aware Recommendations at Netflix
Context Aware Recommendations at NetflixLinas Baltrunas
 
Building Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyBuilding Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyVidhya Murali
 
Recent Trends in Personalization at Netflix
Recent Trends in Personalization at NetflixRecent Trends in Personalization at Netflix
Recent Trends in Personalization at NetflixJustin Basilico
 
Cohort Analysis at Scale
Cohort Analysis at ScaleCohort Analysis at Scale
Cohort Analysis at ScaleBlake Irvine
 
Machine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta LakeMachine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta LakeDatabricks
 
Recommender Systems - A Review and Recent Research Trends
Recommender Systems  -  A Review and Recent Research TrendsRecommender Systems  -  A Review and Recent Research Trends
Recommender Systems - A Review and Recent Research TrendsSujoy Bag
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixJustin Basilico
 
Introduction to Recommendation Systems
Introduction to Recommendation SystemsIntroduction to Recommendation Systems
Introduction to Recommendation SystemsTrieu Nguyen
 
Recommendation system
Recommendation systemRecommendation system
Recommendation systemAkshat Thakar
 
The Data Lake Engine Data Microservices in Spark using Apache Arrow Flight
The Data Lake Engine Data Microservices in Spark using Apache Arrow FlightThe Data Lake Engine Data Microservices in Spark using Apache Arrow Flight
The Data Lake Engine Data Microservices in Spark using Apache Arrow FlightDatabricks
 
Recommendation system for ecommerce
Recommendation system for ecommerceRecommendation system for ecommerce
Recommendation system for ecommerceTu Pham
 

What's hot (20)

Time, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsTime, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender Systems
 
Data Mining: Association Rules Basics
Data Mining: Association Rules BasicsData Mining: Association Rules Basics
Data Mining: Association Rules Basics
 
Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014
 
Movie lens recommender systems
Movie lens recommender systemsMovie lens recommender systems
Movie lens recommender systems
 
How netflix manages petabyte scale apache cassandra in the cloud
How netflix manages petabyte scale apache cassandra in the cloudHow netflix manages petabyte scale apache cassandra in the cloud
How netflix manages petabyte scale apache cassandra in the cloud
 
Recommending and Searching (Research @ Spotify)
Recommending and Searching (Research @ Spotify)Recommending and Searching (Research @ Spotify)
Recommending and Searching (Research @ Spotify)
 
Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Metrics, Engagement & Personalization
Metrics, Engagement & Personalization
 
Collaborative Filtering with Spark
Collaborative Filtering with SparkCollaborative Filtering with Spark
Collaborative Filtering with Spark
 
Context Aware Recommendations at Netflix
Context Aware Recommendations at NetflixContext Aware Recommendations at Netflix
Context Aware Recommendations at Netflix
 
Building Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyBuilding Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at Spotify
 
Recent Trends in Personalization at Netflix
Recent Trends in Personalization at NetflixRecent Trends in Personalization at Netflix
Recent Trends in Personalization at Netflix
 
Cohort Analysis at Scale
Cohort Analysis at ScaleCohort Analysis at Scale
Cohort Analysis at Scale
 
Machine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta LakeMachine Learning Data Lineage with MLflow and Delta Lake
Machine Learning Data Lineage with MLflow and Delta Lake
 
Recommender Systems - A Review and Recent Research Trends
Recommender Systems  -  A Review and Recent Research TrendsRecommender Systems  -  A Review and Recent Research Trends
Recommender Systems - A Review and Recent Research Trends
 
Lessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at NetflixLessons Learned from Building Machine Learning Software at Netflix
Lessons Learned from Building Machine Learning Software at Netflix
 
Introduction to Recommendation Systems
Introduction to Recommendation SystemsIntroduction to Recommendation Systems
Introduction to Recommendation Systems
 
Recommendation system
Recommendation systemRecommendation system
Recommendation system
 
The Data Lake Engine Data Microservices in Spark using Apache Arrow Flight
The Data Lake Engine Data Microservices in Spark using Apache Arrow FlightThe Data Lake Engine Data Microservices in Spark using Apache Arrow Flight
The Data Lake Engine Data Microservices in Spark using Apache Arrow Flight
 
Recommendation system for ecommerce
Recommendation system for ecommerceRecommendation system for ecommerce
Recommendation system for ecommerce
 
Recent Trends in Personalization at Netflix
Recent Trends in Personalization at NetflixRecent Trends in Personalization at Netflix
Recent Trends in Personalization at Netflix
 

Viewers also liked

Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsBuhwan Jeong
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
Deep Learning through Examples
Deep Learning through ExamplesDeep Learning through Examples
Deep Learning through ExamplesSri Ambati
 
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vecword2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec👋 Christopher Moody
 
KDD 2016勉強会 Deep crossing
KDD 2016勉強会 Deep crossingKDD 2016勉強会 Deep crossing
KDD 2016勉強会 Deep crossing正志 坪坂
 
A Graph-based Clustering Scheme for Identifying Related Tags in Folksonomies
A Graph-based Clustering Scheme for Identifying Related Tags in FolksonomiesA Graph-based Clustering Scheme for Identifying Related Tags in Folksonomies
A Graph-based Clustering Scheme for Identifying Related Tags in FolksonomiesSymeon Papadopoulos
 
orderbird - NOAH16 Berlin
orderbird - NOAH16 Berlinorderbird - NOAH16 Berlin
orderbird - NOAH16 BerlinNOAH Advisors
 
Python as part of a production machine learning stack by Michael Manapat PyDa...
Python as part of a production machine learning stack by Michael Manapat PyDa...Python as part of a production machine learning stack by Michael Manapat PyDa...
Python as part of a production machine learning stack by Michael Manapat PyDa...PyData
 
Making fashion recommendations with human-in-the-loop machine learning
Making fashion recommendations with human-in-the-loop machine learningMaking fashion recommendations with human-in-the-loop machine learning
Making fashion recommendations with human-in-the-loop machine learningBrad Klingenberg
 
Yelp vs Opentable - Restaurant Reservations
Yelp vs Opentable - Restaurant Reservations Yelp vs Opentable - Restaurant Reservations
Yelp vs Opentable - Restaurant Reservations Apoorv Kulkarni
 
Graph Based Clustering
Graph Based ClusteringGraph Based Clustering
Graph Based ClusteringSSA KPI
 
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...Spark Summit
 
OpenTable Timeline Presentation by Mitesh M Motwani
OpenTable Timeline Presentation by Mitesh M MotwaniOpenTable Timeline Presentation by Mitesh M Motwani
OpenTable Timeline Presentation by Mitesh M MotwaniMitesh M Motwani
 
OpenTable Competitive Strategy Analysis
OpenTable Competitive Strategy AnalysisOpenTable Competitive Strategy Analysis
OpenTable Competitive Strategy AnalysisFernando Pernica
 
No Reservation? No Problem! OpenTable and Marketing Cloud at Your Service
No Reservation? No Problem! OpenTable and Marketing Cloud at Your ServiceNo Reservation? No Problem! OpenTable and Marketing Cloud at Your Service
No Reservation? No Problem! OpenTable and Marketing Cloud at Your ServiceSalesforce Marketing Cloud
 
TFUG#3 Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方
TFUG#3  Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方TFUG#3  Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方
TFUG#3 Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方Masato Taruishi
 
Hyperoptとその周辺について
Hyperoptとその周辺についてHyperoptとその周辺について
Hyperoptとその周辺についてKeisuke Hosaka
 
WebDB Forum 2016 gunosy
WebDB Forum 2016 gunosyWebDB Forum 2016 gunosy
WebDB Forum 2016 gunosyHiroaki Kudo
 
新たなRNNと自然言語処理
新たなRNNと自然言語処理新たなRNNと自然言語処理
新たなRNNと自然言語処理hytae
 

Viewers also liked (20)

Deep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applicationsDeep learning - Conceptual understanding and applications
Deep learning - Conceptual understanding and applications
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
Deep Learning through Examples
Deep Learning through ExamplesDeep Learning through Examples
Deep Learning through Examples
 
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vecword2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec
 
KDD 2016勉強会 Deep crossing
KDD 2016勉強会 Deep crossingKDD 2016勉強会 Deep crossing
KDD 2016勉強会 Deep crossing
 
A Graph-based Clustering Scheme for Identifying Related Tags in Folksonomies
A Graph-based Clustering Scheme for Identifying Related Tags in FolksonomiesA Graph-based Clustering Scheme for Identifying Related Tags in Folksonomies
A Graph-based Clustering Scheme for Identifying Related Tags in Folksonomies
 
orderbird - NOAH16 Berlin
orderbird - NOAH16 Berlinorderbird - NOAH16 Berlin
orderbird - NOAH16 Berlin
 
Python as part of a production machine learning stack by Michael Manapat PyDa...
Python as part of a production machine learning stack by Michael Manapat PyDa...Python as part of a production machine learning stack by Michael Manapat PyDa...
Python as part of a production machine learning stack by Michael Manapat PyDa...
 
Making fashion recommendations with human-in-the-loop machine learning
Making fashion recommendations with human-in-the-loop machine learningMaking fashion recommendations with human-in-the-loop machine learning
Making fashion recommendations with human-in-the-loop machine learning
 
Yelp vs Opentable - Restaurant Reservations
Yelp vs Opentable - Restaurant Reservations Yelp vs Opentable - Restaurant Reservations
Yelp vs Opentable - Restaurant Reservations
 
Graph Based Clustering
Graph Based ClusteringGraph Based Clustering
Graph Based Clustering
 
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...
Using Data Science to Transform OpenTable Into Your Local Dining Expert-(Pabl...
 
OpenTable Timeline Presentation by Mitesh M Motwani
OpenTable Timeline Presentation by Mitesh M MotwaniOpenTable Timeline Presentation by Mitesh M Motwani
OpenTable Timeline Presentation by Mitesh M Motwani
 
OpenTable Competitive Strategy Analysis
OpenTable Competitive Strategy AnalysisOpenTable Competitive Strategy Analysis
OpenTable Competitive Strategy Analysis
 
No Reservation? No Problem! OpenTable and Marketing Cloud at Your Service
No Reservation? No Problem! OpenTable and Marketing Cloud at Your ServiceNo Reservation? No Problem! OpenTable and Marketing Cloud at Your Service
No Reservation? No Problem! OpenTable and Marketing Cloud at Your Service
 
TFUG#3 Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方
TFUG#3  Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方TFUG#3  Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方
TFUG#3 Retty流 「2200万ユーザさんを支える機械学習基盤」 の作り方
 
Topic Models
Topic ModelsTopic Models
Topic Models
 
Hyperoptとその周辺について
Hyperoptとその周辺についてHyperoptとその周辺について
Hyperoptとその周辺について
 
WebDB Forum 2016 gunosy
WebDB Forum 2016 gunosyWebDB Forum 2016 gunosy
WebDB Forum 2016 gunosy
 
新たなRNNと自然言語処理
新たなRNNと自然言語処理新たなRNNと自然言語処理
新たなRNNと自然言語処理
 

Similar to Recsys 2015: Making Meaningful Restaurant Recommendations at OpenTable

Using Data Science to Transform OpenTable Into Your Local Dining Expert
Using Data Science to Transform OpenTable Into Your Local Dining ExpertUsing Data Science to Transform OpenTable Into Your Local Dining Expert
Using Data Science to Transform OpenTable Into Your Local Dining ExpertPablo Delgado
 
Articles Category: Cooking-Tips - ArticleSnatch.com
Articles Category: Cooking-Tips - ArticleSnatch.comArticles Category: Cooking-Tips - ArticleSnatch.com
Articles Category: Cooking-Tips - ArticleSnatch.com8webdesigner
 
Playbill sense of urgency final-update-2
Playbill sense of urgency final-update-2Playbill sense of urgency final-update-2
Playbill sense of urgency final-update-2Angela Johnson
 
Food and beverages assignment
Food and beverages assignmentFood and beverages assignment
Food and beverages assignmentAmit Akki
 
Yire fabre banqueting
Yire fabre banquetingYire fabre banqueting
Yire fabre banquetingYire Fabre
 
Strategy deck
Strategy deckStrategy deck
Strategy deckJon Lidz
 
Seabear Plans Book
Seabear Plans BookSeabear Plans Book
Seabear Plans BookKara Wexler
 
Eeatons - A global marketing strategy for a Jamaican brand
Eeatons - A global marketing strategy for a Jamaican brandEeatons - A global marketing strategy for a Jamaican brand
Eeatons - A global marketing strategy for a Jamaican brandLéa Coubray
 
SRG hospitality and the New Normal 3.2020
SRG hospitality and the New Normal  3.2020SRG hospitality and the New Normal  3.2020
SRG hospitality and the New Normal 3.2020amyshipley8
 
SRG Hospitality and the New Normal 3.2020
SRG Hospitality and the New Normal  3.2020SRG Hospitality and the New Normal  3.2020
SRG Hospitality and the New Normal 3.2020amyshipley8
 
SRG Hospitality and the New Normal 3.2020
SRG Hospitality and the New Normal  3.2020SRG Hospitality and the New Normal  3.2020
SRG Hospitality and the New Normal 3.2020amyshipley8
 
Delight Food Approach Document
Delight Food Approach DocumentDelight Food Approach Document
Delight Food Approach DocumentDaniel Shaw
 
Some Essay About New York City
Some Essay About New York CitySome Essay About New York City
Some Essay About New York CityErin Sanders
 
Inspiration for Hospitality Clients, Partners and Friends
Inspiration for Hospitality Clients, Partners and FriendsInspiration for Hospitality Clients, Partners and Friends
Inspiration for Hospitality Clients, Partners and FriendsLiz Seelye
 
Grandionce crumpets
Grandionce crumpetsGrandionce crumpets
Grandionce crumpetsamanji1
 
Grandionce crumpets
Grandionce crumpetsGrandionce crumpets
Grandionce crumpetsamanji1
 
NACE Presentation: Customer Insight
NACE Presentation: Customer Insight NACE Presentation: Customer Insight
NACE Presentation: Customer Insight Julie Niesen
 
Chado christina jung
Chado christina jungChado christina jung
Chado christina jungxtina0616
 

Similar to Recsys 2015: Making Meaningful Restaurant Recommendations at OpenTable (20)

Using Data Science to Transform OpenTable Into Your Local Dining Expert
Using Data Science to Transform OpenTable Into Your Local Dining ExpertUsing Data Science to Transform OpenTable Into Your Local Dining Expert
Using Data Science to Transform OpenTable Into Your Local Dining Expert
 
Articles Category: Cooking-Tips - ArticleSnatch.com
Articles Category: Cooking-Tips - ArticleSnatch.comArticles Category: Cooking-Tips - ArticleSnatch.com
Articles Category: Cooking-Tips - ArticleSnatch.com
 
Playbill sense of urgency final-update-2
Playbill sense of urgency final-update-2Playbill sense of urgency final-update-2
Playbill sense of urgency final-update-2
 
Food and beverages assignment
Food and beverages assignmentFood and beverages assignment
Food and beverages assignment
 
Yire fabre banqueting
Yire fabre banquetingYire fabre banqueting
Yire fabre banqueting
 
Strategy deck
Strategy deckStrategy deck
Strategy deck
 
Seabear Plans Book
Seabear Plans BookSeabear Plans Book
Seabear Plans Book
 
Eeatons - A global marketing strategy for a Jamaican brand
Eeatons - A global marketing strategy for a Jamaican brandEeatons - A global marketing strategy for a Jamaican brand
Eeatons - A global marketing strategy for a Jamaican brand
 
SRG hospitality and the New Normal 3.2020
SRG hospitality and the New Normal  3.2020SRG hospitality and the New Normal  3.2020
SRG hospitality and the New Normal 3.2020
 
SRG Hospitality and the New Normal 3.2020
SRG Hospitality and the New Normal  3.2020SRG Hospitality and the New Normal  3.2020
SRG Hospitality and the New Normal 3.2020
 
SRG Hospitality and the New Normal 3.2020
SRG Hospitality and the New Normal  3.2020SRG Hospitality and the New Normal  3.2020
SRG Hospitality and the New Normal 3.2020
 
Delight Food Approach Document
Delight Food Approach DocumentDelight Food Approach Document
Delight Food Approach Document
 
Some Essay About New York City
Some Essay About New York CitySome Essay About New York City
Some Essay About New York City
 
revelnolaportfolio
revelnolaportfoliorevelnolaportfolio
revelnolaportfolio
 
Inspiration for Hospitality Clients, Partners and Friends
Inspiration for Hospitality Clients, Partners and FriendsInspiration for Hospitality Clients, Partners and Friends
Inspiration for Hospitality Clients, Partners and Friends
 
Seabear Plans Book
Seabear Plans BookSeabear Plans Book
Seabear Plans Book
 
Grandionce crumpets
Grandionce crumpetsGrandionce crumpets
Grandionce crumpets
 
Grandionce crumpets
Grandionce crumpetsGrandionce crumpets
Grandionce crumpets
 
NACE Presentation: Customer Insight
NACE Presentation: Customer Insight NACE Presentation: Customer Insight
NACE Presentation: Customer Insight
 
Chado christina jung
Chado christina jungChado christina jung
Chado christina jung
 

Recently uploaded

Credit Card Fraud Detection: Safeguarding Transactions in the Digital Age
Credit Card Fraud Detection: Safeguarding Transactions in the Digital AgeCredit Card Fraud Detection: Safeguarding Transactions in the Digital Age
Credit Card Fraud Detection: Safeguarding Transactions in the Digital AgeBoston Institute of Analytics
 
jll-asia-pacific-capital-tracker-1q24.pdf
jll-asia-pacific-capital-tracker-1q24.pdfjll-asia-pacific-capital-tracker-1q24.pdf
jll-asia-pacific-capital-tracker-1q24.pdfjaytendertech
 
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...Payal Garg #K09
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives23050636
 
Seven tools of quality control.slideshare
Seven tools of quality control.slideshareSeven tools of quality control.slideshare
Seven tools of quality control.slideshareraiaryan448
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRajesh Mondal
 
Rolex Watch - Design Decision Analysis.
Rolex Watch -  Design Decision Analysis.Rolex Watch -  Design Decision Analysis.
Rolex Watch - Design Decision Analysis.zeddstock
 
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...Identify Customer Segments to Create Customer Offers for Each Segment - Appli...
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...ThinkInnovation
 
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证zifhagzkk
 
Case Study 4 Where the cry of rebellion happen?
Case Study 4 Where the cry of rebellion happen?Case Study 4 Where the cry of rebellion happen?
Case Study 4 Where the cry of rebellion happen?RemarkSemacio
 
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...Obat Aborsi 088980685493 Jual Obat Aborsi
 
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样wsppdmt
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样jk0tkvfv
 
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证pwgnohujw
 
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...yulianti213969
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Klinik kandungan
 
社内勉強会資料_Object Recognition as Next Token Prediction
社内勉強会資料_Object Recognition as Next Token Prediction社内勉強会資料_Object Recognition as Next Token Prediction
社内勉強会資料_Object Recognition as Next Token PredictionNABLAS株式会社
 
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptx
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptxChapter 1 - Introduction to Data Mining Concepts and Techniques.pptx
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptxkusamee0
 
What is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationWhat is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationmuqadasqasim10
 

Recently uploaded (20)

Credit Card Fraud Detection: Safeguarding Transactions in the Digital Age
Credit Card Fraud Detection: Safeguarding Transactions in the Digital AgeCredit Card Fraud Detection: Safeguarding Transactions in the Digital Age
Credit Card Fraud Detection: Safeguarding Transactions in the Digital Age
 
jll-asia-pacific-capital-tracker-1q24.pdf
jll-asia-pacific-capital-tracker-1q24.pdfjll-asia-pacific-capital-tracker-1q24.pdf
jll-asia-pacific-capital-tracker-1q24.pdf
 
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...
Unsatisfied Bhabhi ℂall Girls Vadodara Book Esha 7427069034 Top Class ℂall Gi...
 
Displacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second DerivativesDisplacement, Velocity, Acceleration, and Second Derivatives
Displacement, Velocity, Acceleration, and Second Derivatives
 
Seven tools of quality control.slideshare
Seven tools of quality control.slideshareSeven tools of quality control.slideshare
Seven tools of quality control.slideshare
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for Research
 
Rolex Watch - Design Decision Analysis.
Rolex Watch -  Design Decision Analysis.Rolex Watch -  Design Decision Analysis.
Rolex Watch - Design Decision Analysis.
 
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...Identify Customer Segments to Create Customer Offers for Each Segment - Appli...
Identify Customer Segments to Create Customer Offers for Each Segment - Appli...
 
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证
如何办理(Dalhousie毕业证书)达尔豪斯大学毕业证成绩单留信学历认证
 
Case Study 4 Where the cry of rebellion happen?
Case Study 4 Where the cry of rebellion happen?Case Study 4 Where the cry of rebellion happen?
Case Study 4 Where the cry of rebellion happen?
 
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...
Jual Obat Aborsi Lhokseumawe ( Asli No.1 ) 088980685493 Obat Penggugur Kandun...
 
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样
如何办理澳洲拉筹伯大学毕业证(LaTrobe毕业证书)成绩单原件一模一样
 
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
如何办理(UCLA毕业证书)加州大学洛杉矶分校毕业证成绩单学位证留信学历认证原件一样
 
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
原件一样(UWO毕业证书)西安大略大学毕业证成绩单留信学历认证
 
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
obat aborsi Tarakan wa 081336238223 jual obat aborsi cytotec asli di Tarakan9...
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
 
社内勉強会資料_Object Recognition as Next Token Prediction
社内勉強会資料_Object Recognition as Next Token Prediction社内勉強会資料_Object Recognition as Next Token Prediction
社内勉強会資料_Object Recognition as Next Token Prediction
 
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptx
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptxChapter 1 - Introduction to Data Mining Concepts and Techniques.pptx
Chapter 1 - Introduction to Data Mining Concepts and Techniques.pptx
 
Abortion pills in Riyadh Saudi Arabia (+966572737505 buy cytotec
Abortion pills in Riyadh Saudi Arabia (+966572737505 buy cytotecAbortion pills in Riyadh Saudi Arabia (+966572737505 buy cytotec
Abortion pills in Riyadh Saudi Arabia (+966572737505 buy cytotec
 
What is Insertion Sort. Its basic information
What is Insertion Sort. Its basic informationWhat is Insertion Sort. Its basic information
What is Insertion Sort. Its basic information
 

Recsys 2015: Making Meaningful Restaurant Recommendations at OpenTable

  • 1. Making Meaningful Restaurant Recommendations @OpenTable Sudeep Das, PhD Data Scientist OpenTable @datamusing
  • 3. • Over 32,000 restaurants worldwide • more than 885 million diners seated since 1998, representing more than $30 billion spent at partner restaurants • Over 17 million diners seated every month • OpenTable has seated over 254 million diners via a mobile device. Almost 50% of our reservations are made via a mobile device • OpenTable currently has presence in US, Canada, Mexico, UK, Germany and Japan • OpenTable has nearly 600 partners including Bing, Facebook, Google, TripAdvisor, Urbanspoon, Yahoo and Zagat. 3 OpenTable the world’s leading provider of online restaurant reservations
  • 4. At OpenTable we aim to power the best dining experiences!
  • 5. Ingredients of a magical experience Understanding the diner Understanding the restaurant Building up a profile of you as a diner from explicit and implicit signals - information you have provided, reviews you have written, places you have dined at etc. What type of restaurant is it? What dishes are they known for? Is it good for a date night/ family friendly/ has amazing views etc. What’s trending? Connecting the dots
  • 6. we have a wealth of data 32 million reviews diner requests and notes menus external ratings, searches and transactions images
  • 8. diner-restaurant Interactions restaurant metadata The basic ingredients user metadata ratings|searches|reviews … cuisine|price range|hours|topics … user profile
  • 9. There are various approaches to making meaningful recommendations Nearest neighbor approaches in user-user or item-item space Collaborative Filtering based on explicit/implicit interactions Content-based approach leveraging restaurant metadata Factorization machines that include interactions, metadata, as well as context.
  • 11.
  • 12.
  • 13. Matrix Factorization: Implicit preferences Restaurant_1 Restaurant_2 … Restaurant_M Diner_1 50 ? … 100 Diner_2 ? 1 … ? … … … … Diner_N 3 30 … 1 Implicit Preferences (Hu, Koren, Volinsky 2008) Confidence Matrix Binary Preference Matrix
  • 14. 14 Ensemble parameter is a function of the user support Purely Similarity Purely Model based Weighted mean inverse rank ¯a = ↵ 1 r1 + (1 ↵) 1 r2
  • 15. 15
  • 16. Mining the wealth of textual data for cold start and beyond …
  • 17. Content Based Approach • Comes in very handy for cold start where users have very few interactions Very useful for cold start where users have very few interactions. Given a few interactions we can find similar restaurants. Bayesian information retrieval approach. Content based approach
  • 18. 18 Our reviews are rich and verified, and come in all shapes and sizes Superb! This really is a hidden gem and I'm not sure I want to share but I will. :) The owner, Claude, has been here for 47 years and is all about quality, taste, and not overcharging for what he loves. My husband and I don't often get into the city at night, but when we do this is THE place. The Grand Marnier Souffle' is the best I've had in my life - and I have a few years on the life meter. The custard is not over the top and the texture of the entire dessert is superb. This is the only family style French restaurant I'm aware of in SF. It also doesn't charge you an arm and a leg for their excellent quality and that also goes for the wine list. Soup, salad, choice of main (try the lamb shank) and choice of dessert - for around $42 w/o drinks. Many restaurants have thousands of reviews.
  • 19. Word2Vec: Word Embeddings [1] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient Estimation of Word Representations in Vector Space. In Proceedings of Workshop at ICLR, 2013. [2] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of NIPS, 2013. [3] Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. Linguistic Regularities in Continuous Space Word Representations. In Proceedings of NAACL HLT, 2013. “We've [been here for afternoon tea multiple times, and each time] we find it very pleasant” [ 0.00513298, 0.10313627, 0.0773475 , ..., -0.07634512, 0.00877244, 0.04441034]Vec[tea]= ‘teas', ‘empress', ‘scones', ‘iced’, 'fortnum', ‘salon', ‘teapot', ‘teapots', ‘savories', ‘afternoon', ‘earlgrey' …. model.most_similar(‘tea’ ):
  • 21. 21 Early explorations with word2vec: pairings Halibut: Chardonnay Lamb: ?
  • 22. 22 Early explorations with word2vec: pairings Halibut: Chardonnay Lamb: Zinfandel
  • 23. 23 Early explorations with word2vec: pairings Halibut: Chardonnay Lamb: Zinfandel
  • 24. 24 Sushi of Gari, Gari Columbus, NYC Masaki Sushi Chicago Sansei Seafood Restaurant & Sushi Bar, Maui A restaurant like your favorite one but in a different city. Find the “synonyms” of the restaurant in question, then filter by location! Akiko’s, SF San Francisco Maui Chicago New York ' Downtown upscale sushi experience with sushi bar
  • 25. 25 Harris’ Steakhouse in Downtown area ~v(Harris’) + ~v(jazz) Broadway Jazz Club Steakhouse with live jazz ~v(Harris’) + ~v(patio) ~v(Harris’) + ~v(scenic) Celestial Steakhouse Steakhouse with a view Patio at Las Sendas Steakhouse with amazing patio Translating restaurants via concepts
  • 27. 27 We expect diner reviews to be broadly composed of a handful of broad themes Food & Drinks Ambiance Service Value for Money Special occasions This motivated diving into the reviews with topic modeling
  • 28. 28 We applied non- negative matrix factorization to learn topics … • stopword removal • vectorization • TFIDF • NNMF
  • 29. 29 Topics fell nicely into categories DrinksFood Ambiance
  • 30. 30 Topics fell nicely into categories ServiceValue Occasions
  • 31. Our topics reveal the unique aspects of each restaurant without having to read the reviews … Each review for a given restaurant has certain topic distribution Combining them, we identify the top topics for that restaurant. 0 0.5 1 Topic 01 Topic 02 Topic 03 Topic 04 Topic 05 0 0.5 1 Topic 01 Topic 02 Topic 03 Topic 04 Topic 05 0 0.5 1 Topic 01 Topic 02 Topic 03 Topic 04 Topic 05 review 1 review 2 review N . . . 0 0.5 1 Topic 01 Topic 02 Topic 03 Topic 04 Topic 05 Restaurant
  • 32. Looking at the topics and the top reviews associated with it , we know Espetus Churrascaria is not just about meat and steak, but has good salad as well! The service is top notch, its kid friendly, and people go for special occasions, …
  • 33. Content Based Approach • Comes in very handy for cold start where users have very few interactions Very useful for cold start where users have very few interactions. Given a few interactions we can find similar restaurants. Bayesian information retrieval approach. Content based approach + Topic Weights
  • 34. Adding value beyond just making the recommendation
  • 35. 35 We leveraged food and drink related topics to expand our corpus of dishes and drinks Most dishes are usually 1-grams (“tiramisu”) 2-grams (“pork cutlets”) or 3-grams (“lemon ricotta pancake”) For each restaurant, we perform an N-gram analysis of the reviews within the scope of food topics and surface candidate dish tags We were able to generate several thousands of dish tags using this methodology!
  • 37. 37 Sentiments - we use ratings as labels for positive and negative sentiments Ingredients of a stellar experience
  • 38. 38 Sentiments - we use ratings as labels for positive and negative sentiments Ingredients of a terrible experience
  • 39. 39 The model knows that “to die for”, “crispy”, “moist” are actually indicative of positive sentiment when it comes to food! •The lobster and avocado eggs Benedict are to die for. • We finished out meal with the their blackberry bread pudding which was so moist and tasty. •The pork and chive dumplings were perfectly crispy and full of flavor. •I had the Leg of Lamb Tagine and it was "melt in-your-mouth" wonderful. •… we did our best with the scrumptious apple tart and creme brulee. •My husband's lamb porterhouse was a novelty and extremely tender. •We resisted ordering the bacon beignets but gave in and tried them and were glad we did---Yumm! …
  • 40. 40
  • 41. 41 We also learn restaurant specific attributes from review text We learn features using one vs. all Logistic Regression with L1 regularization via a mech turk curated labeled set. For outdoor seating features include obvious ones such as ‘outdoor’, ‘patio’, as well as ‘raining’, ‘sunny’, ‘smoke’, etc. …
  • 42. 42 Dish+Attribute tags and topics can be used to enhance user profiles
  • 43. • Rendle (2010) www.libfm.org Including everything + context: Factorization Machines W ORK IN PROGRESS