SlideShare una empresa de Scribd logo
1 de 15
Our Experiments
With Food Recommendations
40K+
35K+
M +
Home Feed
Personalized Dish
Collections
Cross SellMenu
Recommendations
Restaurant First View Item First View
Understanding Customer
Understanding Restaurants
& Food Items
Taste Profile
Dish
Cuisine
Pure Veg/ Pure non-veg 
Offers
Popular
Exclusive
Brand
CFT
Ratings
Healthy
Taste Profile
Veg/non-Veg
Single/ Family
Explorer
Cravers
Price Affinity
Offer Affinity
Weekend/Weekdays
Home/Work
Health Quotients
Speed
Brand centric
Match Marking
Hyperlocal Serviceability
Restaurant
Stress
Speed
What it so Hard about these Recsys
Accurate
vs
Diversity
Discovery
vs
Repeat
Freshness
vs
Stability
Serendipitous
vs
Explainable
Data
Interactions
Orders
Ratings
Comment
s
Items
Dish
Family
Cuisine
Family
Menus
images
Collaborative Filtering ( Implicit data, MF
methods)
R1 R2 R3 - - - Rn
C1 10 30 ? 89 10
C2 ? ? ? 9 30
-
-
15 40 ? ?
Cn ? ? ? 11 56
 Order from
Restaurant.
 Ordered Dish, Cuisine,
Category, Collection,
Widgets, Tags
 Menu Visits to the
Restaurant
 Visit on the
collection/Widgets
 Cart addition from
Restaurant
 Cart addition of an
item.
 Search Restaurant
 Search Cuisine, Dish,
Item etc
 Cart clear on items.
 Time spent on menu.
 Time spent on cart.
Cost
Restaurant/ Dish / Cuisine / Tags
Content based
People
Generally like
similar Items
Recommend
similar
restaurant/Items
Similarity
?
Taste Profile/
Cost / Brand …
Topic
visualization
Demo
Truffle
KFC
Mac D
0.87 Burge
r King
Biggie
s
Burge
r 'n'
More
Bundar
0.89
0.84
0.85
Cafe
Thulp
0.92
0.84
0.89
Leon
Grill
0.72
Understanding Food Catalog
Machine learning
models
• SVM's
• Logistic Regression
• Word embedding
Text
• item name
• Descriptions
• Recipes
• ingredients
• reviews
• Rest driven Cat, sub-
cat,
Images
• Item image,
• Restaurants image Dish
Cuisine
Category
Veg/Non-veg
Healthy/Non-Healthy
Spicy/ calories
12
'penne’, 'spaghetti’, 'macaroni’, 'ravioli',
'fusilli’, 'bechamel’, 'lasagne’ 'arabiatta',
'arrabbiata’ ‘alfredo’, 'pomodoro’, 'lasagna',
'fettuccine’ ‘pesto’ 'risotto', 'fettuccini’,
model.most_similar(["pasta”])
model.similarity('chapatti', 'chapati')
0.89
Journey
Collaborativ
e Filtering
( Implicit
feedback )
Content
Based
Hybrid
Learning to
Rank
( Content/
Customer
information
DNN Based
methods
(
Embedding,
DCF, RNN)
Evolution of Recommendation Systems
@Swiggy
Home Feed
Dish
Discovery
( Personalized
Collections)
Page
Generation
Page
Generation
Real Time
context
Data Gang

Más contenido relacionado

La actualidad más candente

Overview of recommender system
Overview of recommender systemOverview of recommender system
Overview of recommender systemStanley Wang
 
Learned Embeddings for Search and Discovery at Instacart
Learned Embeddings for  Search and Discovery at InstacartLearned Embeddings for  Search and Discovery at Instacart
Learned Embeddings for Search and Discovery at InstacartSharath Rao
 
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...Balázs Hidasi
 
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Xavier Amatriain
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender SystemsRoelof van Zwol
 
Factorization Machines and Applications in Recommender Systems
Factorization Machines and Applications in Recommender SystemsFactorization Machines and Applications in Recommender Systems
Factorization Machines and Applications in Recommender SystemsEvgeniy Marinov
 
Conversion Models: A Systematic Method of Building Learning to Rank Training ...
Conversion Models: A Systematic Method of Building Learning to Rank Training ...Conversion Models: A Systematic Method of Building Learning to Rank Training ...
Conversion Models: A Systematic Method of Building Learning to Rank Training ...Lucidworks
 
Recommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model TrainingRecommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model TrainingCrossing Minds
 
The Art & Science of Ad Optimization
The Art & Science of Ad OptimizationThe Art & Science of Ad Optimization
The Art & Science of Ad OptimizationUpsight
 
Netflix Recommendations Feature Engineering with Time Travel
Netflix Recommendations Feature Engineering with Time TravelNetflix Recommendations Feature Engineering with Time Travel
Netflix Recommendations Feature Engineering with Time TravelFaisal Siddiqi
 
Recommender Systems: Advances in Collaborative Filtering
Recommender Systems: Advances in Collaborative FilteringRecommender Systems: Advances in Collaborative Filtering
Recommender Systems: Advances in Collaborative FilteringChangsung Moon
 
Recommendation system
Recommendation system Recommendation system
Recommendation system Vikrant Arya
 
[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systems[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systemsFalitokiniaina Rabearison
 
3 lessons from 9 years of locomotive offers: Data based user segmentation and...
3 lessons from 9 years of locomotive offers: Data based user segmentation and...3 lessons from 9 years of locomotive offers: Data based user segmentation and...
3 lessons from 9 years of locomotive offers: Data based user segmentation and...GameCamp
 
Recommender systems using collaborative filtering
Recommender systems using collaborative filteringRecommender systems using collaborative filtering
Recommender systems using collaborative filteringD Yogendra Rao
 
Scala Data Pipelines @ Spotify
Scala Data Pipelines @ SpotifyScala Data Pipelines @ Spotify
Scala Data Pipelines @ SpotifyNeville Li
 

La actualidad más candente (20)

Overview of recommender system
Overview of recommender systemOverview of recommender system
Overview of recommender system
 
Learned Embeddings for Search and Discovery at Instacart
Learned Embeddings for  Search and Discovery at InstacartLearned Embeddings for  Search and Discovery at Instacart
Learned Embeddings for Search and Discovery at Instacart
 
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
GRU4Rec v2 - Recurrent Neural Networks with Top-k Gains for Session-based Rec...
 
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
 
Programmatic Advertising Success
Programmatic Advertising SuccessProgrammatic Advertising Success
Programmatic Advertising Success
 
Learn to Rank search results
Learn to Rank search resultsLearn to Rank search results
Learn to Rank search results
 
Factorization Machines and Applications in Recommender Systems
Factorization Machines and Applications in Recommender SystemsFactorization Machines and Applications in Recommender Systems
Factorization Machines and Applications in Recommender Systems
 
Conversion Models: A Systematic Method of Building Learning to Rank Training ...
Conversion Models: A Systematic Method of Building Learning to Rank Training ...Conversion Models: A Systematic Method of Building Learning to Rank Training ...
Conversion Models: A Systematic Method of Building Learning to Rank Training ...
 
Recommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model TrainingRecommender Systems from A to Z – Model Training
Recommender Systems from A to Z – Model Training
 
The Art & Science of Ad Optimization
The Art & Science of Ad OptimizationThe Art & Science of Ad Optimization
The Art & Science of Ad Optimization
 
Apps flyer
Apps flyerApps flyer
Apps flyer
 
Netflix Recommendations Feature Engineering with Time Travel
Netflix Recommendations Feature Engineering with Time TravelNetflix Recommendations Feature Engineering with Time Travel
Netflix Recommendations Feature Engineering with Time Travel
 
Recommender Systems: Advances in Collaborative Filtering
Recommender Systems: Advances in Collaborative FilteringRecommender Systems: Advances in Collaborative Filtering
Recommender Systems: Advances in Collaborative Filtering
 
Recommendation system
Recommendation system Recommendation system
Recommendation system
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systems[Final]collaborative filtering and recommender systems
[Final]collaborative filtering and recommender systems
 
3 lessons from 9 years of locomotive offers: Data based user segmentation and...
3 lessons from 9 years of locomotive offers: Data based user segmentation and...3 lessons from 9 years of locomotive offers: Data based user segmentation and...
3 lessons from 9 years of locomotive offers: Data based user segmentation and...
 
Recommender systems using collaborative filtering
Recommender systems using collaborative filteringRecommender systems using collaborative filtering
Recommender systems using collaborative filtering
 
Scala Data Pipelines @ Spotify
Scala Data Pipelines @ SpotifyScala Data Pipelines @ Spotify
Scala Data Pipelines @ Spotify
 

Similar a Our Experiments With Food Recommendations

10 marketing healthy menu options
10 marketing healthy menu options10 marketing healthy menu options
10 marketing healthy menu optionsPearl Jamaldin
 
E suade business proposal
E suade business proposalE suade business proposal
E suade business proposalKelly James
 
Claritas B A S E S Restaurant Audit Report
Claritas  B A S E S  Restaurant  Audit  ReportClaritas  B A S E S  Restaurant  Audit  Report
Claritas B A S E S Restaurant Audit Reportguest1f8179
 
Gourmet ads 2014
Gourmet ads 2014Gourmet ads 2014
Gourmet ads 2014AdCMO
 
BASES M346 Case Competition Final
BASES M346 Case Competition FinalBASES M346 Case Competition Final
BASES M346 Case Competition FinalShelby Fletcher
 
Week 6 The Menu And Menu Planning 2 2552
Week 6 The Menu And Menu Planning  2 2552Week 6 The Menu And Menu Planning  2 2552
Week 6 The Menu And Menu Planning 2 2552Pavit Tansakul
 
Branding & Positioning of Knorr soup
Branding & Positioning of Knorr soupBranding & Positioning of Knorr soup
Branding & Positioning of Knorr soupSolaman Badsha
 
Worksite wellness ppt presentation 2015
Worksite wellness ppt presentation 2015Worksite wellness ppt presentation 2015
Worksite wellness ppt presentation 2015jbergstrand
 
Workplace wellness ppt presentation_Healthy Eating
Workplace wellness ppt presentation_Healthy EatingWorkplace wellness ppt presentation_Healthy Eating
Workplace wellness ppt presentation_Healthy Eatingjbergstrand
 
Applebees Pitch Brief
Applebees Pitch BriefApplebees Pitch Brief
Applebees Pitch BriefCubeyou Inc
 
Determine Accurate Recipe Costs For Your Food & Beverage Operations
Determine Accurate Recipe Costs For Your Food & Beverage OperationsDetermine Accurate Recipe Costs For Your Food & Beverage Operations
Determine Accurate Recipe Costs For Your Food & Beverage OperationsReturn On Ingredients
 

Similar a Our Experiments With Food Recommendations (20)

A Culinary Perspective on Menu Development
A Culinary Perspective on Menu DevelopmentA Culinary Perspective on Menu Development
A Culinary Perspective on Menu Development
 
10 marketing healthy menu options
10 marketing healthy menu options10 marketing healthy menu options
10 marketing healthy menu options
 
E suade business proposal
E suade business proposalE suade business proposal
E suade business proposal
 
Claritas B A S E S Restaurant Audit Report
Claritas  B A S E S  Restaurant  Audit  ReportClaritas  B A S E S  Restaurant  Audit  Report
Claritas B A S E S Restaurant Audit Report
 
Chilis Presentation
Chilis PresentationChilis Presentation
Chilis Presentation
 
Gourmet ads 2014
Gourmet ads 2014Gourmet ads 2014
Gourmet ads 2014
 
Marketing Michigan Products: A Step by Step Guide
Marketing Michigan Products: A Step by Step GuideMarketing Michigan Products: A Step by Step Guide
Marketing Michigan Products: A Step by Step Guide
 
BASES M346 Case Competition Final
BASES M346 Case Competition FinalBASES M346 Case Competition Final
BASES M346 Case Competition Final
 
Back to deliverables
Back to deliverablesBack to deliverables
Back to deliverables
 
Week 6 The Menu And Menu Planning 2 2552
Week 6 The Menu And Menu Planning  2 2552Week 6 The Menu And Menu Planning  2 2552
Week 6 The Menu And Menu Planning 2 2552
 
Branding & Positioning of Knorr soup
Branding & Positioning of Knorr soupBranding & Positioning of Knorr soup
Branding & Positioning of Knorr soup
 
2016_copy_CIA_SupermarketRD_B-Ruhs
2016_copy_CIA_SupermarketRD_B-Ruhs2016_copy_CIA_SupermarketRD_B-Ruhs
2016_copy_CIA_SupermarketRD_B-Ruhs
 
Worksite wellness ppt presentation 2015
Worksite wellness ppt presentation 2015Worksite wellness ppt presentation 2015
Worksite wellness ppt presentation 2015
 
Workplace wellness ppt presentation_Healthy Eating
Workplace wellness ppt presentation_Healthy EatingWorkplace wellness ppt presentation_Healthy Eating
Workplace wellness ppt presentation_Healthy Eating
 
Meal preparation
Meal preparationMeal preparation
Meal preparation
 
Hot 103-Chapter 05
Hot 103-Chapter 05Hot 103-Chapter 05
Hot 103-Chapter 05
 
Food and beverage management 1
Food and beverage management 1Food and beverage management 1
Food and beverage management 1
 
Culture Change
Culture ChangeCulture Change
Culture Change
 
Applebees Pitch Brief
Applebees Pitch BriefApplebees Pitch Brief
Applebees Pitch Brief
 
Determine Accurate Recipe Costs For Your Food & Beverage Operations
Determine Accurate Recipe Costs For Your Food & Beverage OperationsDetermine Accurate Recipe Costs For Your Food & Beverage Operations
Determine Accurate Recipe Costs For Your Food & Beverage Operations
 

Último

Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxLoriGlavin3
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 

Último (20)

Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptxMerck Moving Beyond Passwords: FIDO Paris Seminar.pptx
Merck Moving Beyond Passwords: FIDO Paris Seminar.pptx
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 

Our Experiments With Food Recommendations

Notas del editor

  1. Today I am  going to talk about our experiments with Food Discovery & Recommendation @ Swiggy. I will talk about what are the major challenges, will share some interesting insights and lessons learned in the process. Now let’s take a min to understand what is Swiggy, can we please have a  quick show of hands how many of you actually use Swiggy ??
  2. 2 So ppl have some idea what swiggy does. Swiggy is a 3 way market place where you have millions of customers, Thousands of rest partners, and Delivery Partners. These are the  pillars of the echo systems and if you want to solve any problem it’s going to impact all of these. When you start Swiggy app we need to come up with the best recommendation for all the serviceable & available options, So there are problems related to relevance, Personalization, Search & Discovery.  The moment you figured it out what you want to eat and place the order, assignment of this order, Batching , ETA predictions all these are equally difficult problems.
  3. 2 Formally a recommendation system problem is to come up with a utility function that can predict the customer’s  likelihood of purchase from the list of Items, and these items could be movies in case of netflix, music in case of spotify, etc. We currently have these 2 views of the world. One is a restaurant centric view where we have restaurant feed, Also some personalized collection/ Smart filters. This contributes to ~60% of the orders. At the same time we are also venturing into a Dish/Item first view where we recently released Dish Discovery in Bangalore. The idea here is to predict the dish themes and show personalized collection based on these themes for you. If you show a story like this to a customer who loves pizzas you have remove lot of friction from the journey, He can click on this story and will get all the best pizza cater to his taste. This is a great experience.   We have few recommendations at menu and few on cart like Cross sell (Smart enough to understand what you have in cart & if you have a main course it will recommend a dessert/ Drinks We have few recommendations at menu and few on cart like Cross sell / Meal completions.
  4. 3 Secret ingredient Now if you want to  abstract out the idea of any recommendation system it comes down to Matchmaking b\w customer and the items that you sell. The secret recipe of any good recommendation system is to understand your customer well and in our case we want to know what kind of food/dish/cuisine he likes, is he a vegetarian, does he tries different restaurants or generally like to order from the same. Same goes for the understanding of the catalog, We do have an unstructured  catalog so we do need a way to understand more about the restaurants and the food taxonomy. We do want to understand what is the taste profile of restaurant, What cuisines it serves, Is it costly ? , Is it healthy ? etc.
  5. 4 Still the big question could be what is so niche about this problem, the answer lies here, where the recommendation can’t be looked without these factors. Swiggy is a hyperlocal business which adds a lot more complexities to the problem, We are constrained by our supply & availability.  The need is to make a balance of demand & supply. See most of the world class recommendation systems don’t suffer from these problems as much as we do. Think about the best recommendation like amazon, Netflix. They have more or less static supply and do not suffer from all these dimensions of a hyper local business such as Swiggy. You are looking for Pizza options & we are constrained by serviceability we still want to show  the possible alternatives. In food delivery ppl do care about the speed so we need to give some weights to the faster options. You also want to consider the stress at the Restaurant ( Real time model ) when you are recommending. If we do not consider these factors in our recommendation systems then these systems will be suboptimal. These are some other factors to consider when designing recsys.   Diversity Consider this, I know you are a biryani guy.  Shall we show all the biryani restaurants in your feed ??   it’s just too much exploit and we need to provide some diversity to give you different choices and it’s proven that it adds value. Repeat vs Discovery again very similar kind of choice, We know top 10 restaurant that you generally order from, Is it a good recommendation to show just these ?? ohh yes !! In general recsys ( spatially content engines ) tends to ignore repeat. You want ppl to watch new movies, New articles, Songs. While in case of Swiggy where people tend to order a lot more from the same restaurants over and over again, So we do need to have a balance b\w repeat vs explore. Now this is crucial choice and kinda definition of Discovery ( Search Vs discovery Search is an explicit query. given your historic profile I can show you what are the items you may like but what about this that a  Serendipitous item that you don’t know even exists,  finds you that is the real discovery !! So it’s easy to show you all the deserts you liked in the past and a unique indian dessert delicacy finds you is the real discovery. )    
  6. 1
  7. 3 Let’s quickly talk about the datasets available to build all these recommendation systems. There are these two major philosophies in recommendation system, ppl similar to you (Some form of CF based methods), ppl generally like similar items (Content based methods ). We also started with CF based approach, For these methods you need to build a customer - Item (rest ) matrix,  You can build using explicit data/ It has been seen that you are better of using implicit data which is available in large volumes. We are using matrix factorization based method like ALS, SVD,  L2R (Wrap) Generally these methods are defined for explicit rating prediction, In a  classic paper by stephan rendle (et all ) they defined some of these methods for implicit feedback. Now these methods are good start because you do not need to understand your items. On the other hand, it’s kind of biased towards popularity suffers from cold start think about a new customer he will not get a meaningful recommendation out of this, Same goes for a new restaurant that will start with a very low position and will be there always.
  8. 2 To solve for some of these, ppl go for content based method which solves for cold start and long tail. What is content and similarity. Generally it’s done on the metadata  provided on items , like in case of movies it will genres or in case of news articles it will be content, Title etc. You will build a vector out of these & will calculate some similarity. Similarly To understand our restaurant we could have used the data provided by them like menu, item categorization, primary tags, but we realize 1. This is not standard taxonomy. 2. In many cases,  the order patterns on online food delivery differs from general understanding of the restaurant. Some call themselves a cafe place but it’s actually a sandwich  place , Few restaurant call themselves a multi cuisine ?? We took a different path and build this understanding of restaurants on ordered items as proxy for meta, So we took order item from a rest as a dummy document and run LDA on that and we go something like this.
  9. 3 What is the content and what is the similarity. To understand about these restaurant we could have used the data provided by them like menu but we realize 1. This is not standard taxonomy. Some call themselves a pizza place but it’s actually a Italian place some A2B call themselves  a multi cuisine  it is but really ??  someone call there  pizza pizza some other call them main course so  So we took order item from a rest as a dummy document and run LDA on that and we go something like this.  Here in this visualization we are showing all the topic themes and it came out surprisingly well .  There are the major topics/food themes exist in Swiggy you can see how bountifully it decided veg vs non-veg & these desert  3 Any restaurant can be projected into these dimension and you will get a taste profile vector. Some of the example of similarity based on this are here. 
  10. 1 These are the major topics/food themes that exist in Swiggy, You can see how nicely  it seperates veg vs non-veg & these desert, If you zoom to a topic it talks about what kind of words it represents and hence what food theme. Any restaurant can be projected into these dimension and you will get a taste profile vector. Some of the example of similarity based on this are here. We clearly see how much similar is MacD to Burger King. So if you have already ordered from Truffle there is a good chance that you will see bundar in your feed list. This kind of solves for rest first recommendation but to get item first view (Dish Discovery) we need a standard categorization (Enrichments).
  11. This kind of solve for rest  recommendation but what about  item first view we still have a non standard taxonomy which we standardize with the help of few food experts.  We have some meta regarding the food items like name ,description , recipe and when we did basic text/image classification we saw some nice results.  2
  12. We also did some early experiments with word embedding, We took orders as proxy of the basic unit and run a Word2vec on this. again quite interestingly if you see, it lists down all the pastas when you look for “pasta”  it captures conceptually very similar items, spell variations etc. Also there is an example of how dal makhni, dal Bukhara and kali dal are nothing but conceptually very similar.
  13. So this is a summary of all the work done and in pipeline. We started with Matrix factorization methods, We have content based methods ,We have done few experiments with hybrid of CF + Content. We also tried Learning to rank with adding content as features and with multi objectives we also have few experiments in Deep learning based method  like item embeddings etc.
  14. Similarly Swiggy recommendations are also moving from just home feed to non-linear Dish discovery to generating an entire app filed with different collections and how to add real time context and change the recommendations accordingly.