I spoke at the first Kaizen Data Science Conference, San Francisco, Sep 2016 on one of Instacart's recommendation systems. Also covers innovative ways of using data science to solve interdisciplinary problems. - Sharath Rao
Instacart has revolutionized grocery shopping by bringing groceries to your door in a little as an hour. Behind the scenes, Instacart uses machine learning for everything from routing shoppers to ranking search results. In this talk, Jeremy will cover their recent tech blog post, Deep Learning with Emojis (not Math) ( https://tech.instacart.com/deep-learning-with-emojis-not-math-660ba1ad6cdc ), which details how Instacart is using Keras and Tensorflow to predict the sequence that shoppers will pick items in stores. Jeremy will discuss the data collection, mobile technology and deep learning architectures Instacart is applying to enable on-demand grocery delivery.
DataEngConf 2017 - Machine Learning Models in ProductionSharath Rao
- Integrating machine learning models into customer workflows
- Economies of scope with data products
- Using a shared features store for reusing features across models
What is a Product Manager? by Datank.ai's Product ManagerProduct School
Main takeaways:
- What is a Product Manager?
- What are some Product Manager archetypes?
- What does a day in the life of a Product Manager look like?
- How do you become a Product Manager?
E Commerce Website Design Proposal PowerPoint Presentation SlidesSlideTeam
If your company needs to submit a E Commerce Website Design Proposal PowerPoint Presentation Slides look no further. Our researchers have analyzed thousands of proposals on this topic for effectiveness and conversion. Just download our template, add your company data and submit to your client for a positive response. https://bit.ly/3dX8NO0
Webinar: Understanding Product Strategy by fmr Flipkart Sr Mgr ProductsProduct School
Main takeaways:
- Product Strategy is an ever-evolving bridge that connects a Vision to a Roadmap
- Lack of a product strategy often results in flatlining metrics and disengaged users
- An effective Product Strategy involves problem statements that stem from a deep understanding of the User's lifecycle, persona, and pain points.
Instacart has revolutionized grocery shopping by bringing groceries to your door in a little as an hour. Behind the scenes, Instacart uses machine learning for everything from routing shoppers to ranking search results. In this talk, Jeremy will cover their recent tech blog post, Deep Learning with Emojis (not Math) ( https://tech.instacart.com/deep-learning-with-emojis-not-math-660ba1ad6cdc ), which details how Instacart is using Keras and Tensorflow to predict the sequence that shoppers will pick items in stores. Jeremy will discuss the data collection, mobile technology and deep learning architectures Instacart is applying to enable on-demand grocery delivery.
DataEngConf 2017 - Machine Learning Models in ProductionSharath Rao
- Integrating machine learning models into customer workflows
- Economies of scope with data products
- Using a shared features store for reusing features across models
What is a Product Manager? by Datank.ai's Product ManagerProduct School
Main takeaways:
- What is a Product Manager?
- What are some Product Manager archetypes?
- What does a day in the life of a Product Manager look like?
- How do you become a Product Manager?
E Commerce Website Design Proposal PowerPoint Presentation SlidesSlideTeam
If your company needs to submit a E Commerce Website Design Proposal PowerPoint Presentation Slides look no further. Our researchers have analyzed thousands of proposals on this topic for effectiveness and conversion. Just download our template, add your company data and submit to your client for a positive response. https://bit.ly/3dX8NO0
Webinar: Understanding Product Strategy by fmr Flipkart Sr Mgr ProductsProduct School
Main takeaways:
- Product Strategy is an ever-evolving bridge that connects a Vision to a Roadmap
- Lack of a product strategy often results in flatlining metrics and disengaged users
- An effective Product Strategy involves problem statements that stem from a deep understanding of the User's lifecycle, persona, and pain points.
In these slides you'll learn how to create a customer journey map, what business objectives it helps achieve, and the differences between B2B and B2C journey mapping.
Insights & Advertising on the Growing Instacart MarketplaceTinuiti
America’s shopping habits were changing in the wake of COVID-19. With 57% of the grocery ecommerce market and order volume up by as much as 500% in 2020, Instacart has emerged as an undisputed opportunity for brands to acquire and retain grocery and CPG shoppers.If you are in store at a participating retailer, then an Instacart Ads program should be part of your media strategy. Join Tinuiti and Instacart as we dig into the top trends dominating 2020 and unpack the latest insights across our digital aisles. We’ll also breakdown Instacart ads, how they work, and the different Instacart ad campaigns you can launch to reach grocery shoppers.
Discovering the right product is a vital part of a product development process. To do that effectively best product teams use a Product Discovery process. It answers the question of what product to build. Done right it helps you build products customers would love.
Test for Success: A Guide to A/B Testing on Emails & Landing PagesOptimizely
Email marketing is a key component to any successful marketing strategy — and it's constantly evolving! That's why testing and optimizing your communications is just as important as the strategy itself.
Sometimes knowing how, what, and when to test can seem overwhelming but don't worry, we've got your back. Join this informative webinar with Jessica Langensand of Marketo and Allison Sparrow of Optimizely to discover:
How to design an effective email A/B test
What to test in your emails and landing pages
Testing ideas you'll want to share with your team!
From the time the buyer registers on the Instacart portal till their grocery list reaches them, a series of steps help streamline the process. We will here walk you through the journey of a buyer on the Instacart platform.
Go through the slide to understand Instacart's work process or visit the link shared to gain more insights about the "Complete Workflow of Instacart"
https://www.fatbit.com/fab/build-grocery-delivery-app-like-instacart/?=ss
Measuring and Improving CX as a PM by fmr Twilio Staff PMProduct School
As a Product Manager, you benefit from mixing anecdotes and data to have an understanding of customer needs.
- You can track the success metrics of your product launch better by defining output metrics vs intermediary signals of progress.
- Sometimes you need to drive stakeholder alignment and internal process changes to improve customer experience
- You can build your own checklist for product launch and for communicating with customers to ensure you have your metrics ready, your communication is well received, and you are driving the desired customer behavior.
How to Build a Product Vision by Spotify Product ManagerProduct School
In this episode, Matt Williams talks about building a product vision and getting stakeholder buy in. He also covers 'managing up' and how to navigate within your organization, whilst fostering an understanding of vision and user empathy with engineers.
Prioritization Method for Every Case by fmr Atlassian Principal PMProduct School
Main Takeaways:
- Prioritization is about understanding each other and making alignment.
- Choose an appropriate prioritization method depending on your project situation and stakeholder group.
- Find a way to scale up or down your prioritization method and balance between quantitative and qualitative approaches.
Epoca presented at Service Design Drinks Milan #3 how to use the customer journey map tool in b2b projects, showcasing a case-study they have been working on in the last years.
From a recent talk to Texas McCombs MBAs about what product management is, what skills product managers need, and how to get a job in product management.
How to Know Your Customers by Amazon Senior Product ManagerProduct School
In this session Will Najar, Amazon Senior PM, will cover everything you need to know about getting in touch with your customers. Learn how to work backwards from your customer's needs, hear the customer voice as you make hard product choices, quantify customer anecdotes with data and to use that knowledge to build the product your customers really want.
With the ever increasing marketing cost due to high competition, it becomes more and more important for e-commerce to create a better user experience to not losing them to your competitors and create a competitive advantage.
Marketplace Product Management by Tal FlanchraychProduct School
Product Management Event Held at the Product Conference in San Francisco.
A great interface does not equal a healthy marketplace.
Tal talked about the difference between interfaces and marketplaces, and the importance in knowing both. She used real-life examples from both interface and marketplace point of view.
Learn how to use A/B testing to figure out the best product and marketing strategies for your business. Adopt a culture of testing everything from website copy to engagement emails to Facebook ads. Learn through a real SaaS product experiment.
Learned Embeddings for Search and Discovery at InstacartSharath Rao
Learned word embeddings such as Word2vec/Glove were initially found to be effective for broad range of tasks in Natural Language Processing (NLP). More recently though, these are being used successfully in areas well beyond text such as graphs and event streams. In this talk Sharath will speak about how we use learned embeddings at Instacart for search ranking, personalization and product recommendations.
Presented at: SF Data Mining Meetup https://www.meetup.com/Data-Mining/events/237164197/
In these slides you'll learn how to create a customer journey map, what business objectives it helps achieve, and the differences between B2B and B2C journey mapping.
Insights & Advertising on the Growing Instacart MarketplaceTinuiti
America’s shopping habits were changing in the wake of COVID-19. With 57% of the grocery ecommerce market and order volume up by as much as 500% in 2020, Instacart has emerged as an undisputed opportunity for brands to acquire and retain grocery and CPG shoppers.If you are in store at a participating retailer, then an Instacart Ads program should be part of your media strategy. Join Tinuiti and Instacart as we dig into the top trends dominating 2020 and unpack the latest insights across our digital aisles. We’ll also breakdown Instacart ads, how they work, and the different Instacart ad campaigns you can launch to reach grocery shoppers.
Discovering the right product is a vital part of a product development process. To do that effectively best product teams use a Product Discovery process. It answers the question of what product to build. Done right it helps you build products customers would love.
Test for Success: A Guide to A/B Testing on Emails & Landing PagesOptimizely
Email marketing is a key component to any successful marketing strategy — and it's constantly evolving! That's why testing and optimizing your communications is just as important as the strategy itself.
Sometimes knowing how, what, and when to test can seem overwhelming but don't worry, we've got your back. Join this informative webinar with Jessica Langensand of Marketo and Allison Sparrow of Optimizely to discover:
How to design an effective email A/B test
What to test in your emails and landing pages
Testing ideas you'll want to share with your team!
From the time the buyer registers on the Instacart portal till their grocery list reaches them, a series of steps help streamline the process. We will here walk you through the journey of a buyer on the Instacart platform.
Go through the slide to understand Instacart's work process or visit the link shared to gain more insights about the "Complete Workflow of Instacart"
https://www.fatbit.com/fab/build-grocery-delivery-app-like-instacart/?=ss
Measuring and Improving CX as a PM by fmr Twilio Staff PMProduct School
As a Product Manager, you benefit from mixing anecdotes and data to have an understanding of customer needs.
- You can track the success metrics of your product launch better by defining output metrics vs intermediary signals of progress.
- Sometimes you need to drive stakeholder alignment and internal process changes to improve customer experience
- You can build your own checklist for product launch and for communicating with customers to ensure you have your metrics ready, your communication is well received, and you are driving the desired customer behavior.
How to Build a Product Vision by Spotify Product ManagerProduct School
In this episode, Matt Williams talks about building a product vision and getting stakeholder buy in. He also covers 'managing up' and how to navigate within your organization, whilst fostering an understanding of vision and user empathy with engineers.
Prioritization Method for Every Case by fmr Atlassian Principal PMProduct School
Main Takeaways:
- Prioritization is about understanding each other and making alignment.
- Choose an appropriate prioritization method depending on your project situation and stakeholder group.
- Find a way to scale up or down your prioritization method and balance between quantitative and qualitative approaches.
Epoca presented at Service Design Drinks Milan #3 how to use the customer journey map tool in b2b projects, showcasing a case-study they have been working on in the last years.
From a recent talk to Texas McCombs MBAs about what product management is, what skills product managers need, and how to get a job in product management.
How to Know Your Customers by Amazon Senior Product ManagerProduct School
In this session Will Najar, Amazon Senior PM, will cover everything you need to know about getting in touch with your customers. Learn how to work backwards from your customer's needs, hear the customer voice as you make hard product choices, quantify customer anecdotes with data and to use that knowledge to build the product your customers really want.
With the ever increasing marketing cost due to high competition, it becomes more and more important for e-commerce to create a better user experience to not losing them to your competitors and create a competitive advantage.
Marketplace Product Management by Tal FlanchraychProduct School
Product Management Event Held at the Product Conference in San Francisco.
A great interface does not equal a healthy marketplace.
Tal talked about the difference between interfaces and marketplaces, and the importance in knowing both. She used real-life examples from both interface and marketplace point of view.
Learn how to use A/B testing to figure out the best product and marketing strategies for your business. Adopt a culture of testing everything from website copy to engagement emails to Facebook ads. Learn through a real SaaS product experiment.
Learned Embeddings for Search and Discovery at InstacartSharath Rao
Learned word embeddings such as Word2vec/Glove were initially found to be effective for broad range of tasks in Natural Language Processing (NLP). More recently though, these are being used successfully in areas well beyond text such as graphs and event streams. In this talk Sharath will speak about how we use learned embeddings at Instacart for search ranking, personalization and product recommendations.
Presented at: SF Data Mining Meetup https://www.meetup.com/Data-Mining/events/237164197/
PSFK Future of Retail 2015 Report - Summary PresentationPSFK
Get your copy of The Future of Retail 2015: www.psfk.com/report/future-of-retail-2015
In the fifth volume of the Future of Retail report the PSFK Labs team explores the dynamic social, technological, and physical forces influencing consumer behavior and driving next-generation shopping experiences. With a refocus on the importance of the physical store, our analysis below includes 10 in-store strategies supported by over a dozen key trends that retailers can use to immediately begin redefining their retail experience.
The report looks at how, in order to stand out from the competition, retailers and brands must make the best use of their customers’ time and attention by designing multichannel experiences that strike a perfect balance between efficiency and enjoyment, relevance and surprise.
Featured within the 110 page report, readers can find:
- 10 strategies to redefine the store
- Over a dozen global trends changing retail
- 20 future store concepts
- Perspectives from leading shopper experts across the globe
If you are interested in seeing a presentation of this report or would like to understand how PSFK can help your team ideate new possibilities for your brand, contact us at sales@psfk.com
Vol. 5 | Published November 2014
All rights reserved. No parts of this publication may be reproduced without the written permission of PSFK Labs.
My talk at DataEngConf, on Instacart's first discovery based recommendation systems that uses machine learning methods on large scale datasets in online grocery.
This is a snapshot of who I am at this moment in time. It is a personification of what I'm about, my interests, & what I aspire to do. If you're interested in chatting, send me an email!
Download a full version of the report at:
www.psfk.com/report/future-of-retail-2016
Built on a robust study of trends and patterns in the market, the 6th edition of PSFK Labs’ Future of Retail report offers a directional playbook for brands and retailers – defining 10 pillars to build a modern and engaging shopper experience strategy and go beyond expectations to create an enhanced shopper experience and therefore, build value, drive sales, and boost loyalty.
Featured within the 80+ page report, readers can find:
- 10 actions every retailer can adapt to redefine the shopper experience
- 20 key trends driving change in the marketplace
- Future service concepts for top brands
- Perspectives from leading retail experts across the globe
If you are interested in seeing a presentation of this report or would like to understand how PSFK can help your team ideate new possibilities for your brand, contact us at sales@psfk.com
Vol. 6 | Published November 2015
All rights reserved. No parts of this publication may be reproduced without the written permission of PSFK Labs.
Solving for X: Why the Future of Business is ExperientialBrian Solis
Products don't define a brand, experiences do. Brian Solis explains why companies must shift from product-centric strategies to cultivating outstanding experiences to remain competitive. By Judith Aquino, TeleTech.
Every startup begins with an idea. This is a talk on how to come up with startup ideas and how to use validation to pick the ones worth working on. It's based on the book "Hello, Startup" (http://www.hello-startup.net/). You can find the video of the talk here: https://www.youtube.com/watch?v=GkmiE8d_5Pw
Lessons From Integrating Machine Learning into Data Products | Wrangle Confer...Cloudera, Inc.
In this talk, we will share practical lessons and patterns for building machine learning (ML) models in production, based on our experience with search ranking and recommendation systems at Instacart. As part of this I will include a detailed discussion on the technical challenges in building a ML features pipeline, one of which is now shared across multiple data products at Instacart.
Webinar: Increase Conversion With Better SearchLucidworks
Hear from IBM Product Line Manager Iris Yuan & Lucidworks VP of Partner Engineering Sarath Jarugula for a deep discussion into how improving ecommerce search can drive conversions and increase revenue.
Winning Supply Chain in Omnichannel - Trends and ImplicationsMichael Hu
I gave a talk at Professor Chopra's class at Kellogg on emerging trends in omnichannel retailing and the need for new supply chain and fulfillment models.
Solutions which focus on easy collaboration, visibility and efficiency, across your entire supply chain.
Maximize your profit, reduce costs and increase competitiveness, definitely, with these solutions.
This booklet explores a few use cases of analytics for the supply chain and how it can be leveraged.
For more info visit: https://www.teamcomputers.com/businessanalytics/Supply%20Chain/Booklet-Supply-chain-Digital.pdf
Find out how retailers can utilize 2014 purchase data to predict 2015 holiday buying.
Highlights include:
-Original research from "Turning 2014 Holiday Trends into 2015 Revenue" by Oracle Marketing Cloud and Edison Research
-Holiday retention strategies from Windsor Circle
-Successful holiday campaign examples from Artbeads
Big data certification training mumbaiTejaspathiLV
ExcelR offers 160 hours classroom training on Business Analytics / Data Scientist / Data Analytics. We are considered as one of the best training institutes on Business Analytics in Mumbai. “Faculty and vast course agenda is our differentiator”. The training is conducted by alumni of premier institutions such as IIT & ISB who has extensive experience in the arena of analytics. They are considered to be one of the best trainers in the industry. The topics covered as part of this Data Scientist Certification program is on par with most of the Master of Science in Analytics (MS in Business Analytics / MS in Data Analytics) programs across the top-notch universities of the globe.
ExcelR is a proud partner of Universiti Malaysia Saravak (UNIMAS), Malaysia’s 1st public University and ranked 8th top university in Malaysia and ranked among top 200th in Asian University Rankings 2017 by QS World University Rankings. Participants will be awarded Data Science international certification from UNIMAS.
ExcelR is the best Data Science training institute in Hyderabad which offers services from training to placement as part of the Data Science training program with over 400+ participants placed in various multinational companies including E&Y, Panasonic, Accenture, VMWare, Infosys, IBM, etc….and the staff is from NIT’s & IIT’s
ExcelR is a proud partner of Universiti Malaysia Saravak (UNIMAS), Malaysia’s 1st public University and ranked 8th top university in Malaysia and ranked among top 200th in Asian University Rankings 2017 by QS World University Rankings. Participants will be awarded Data Science international certification from UNIMAS.
Rishabh Misra, Mengting Wan, Julian McAuley, “Decomposing Fit Semantics for Product Size Recommendation in Metric Spaces”, in Proceedings of 2018 ACM Conference on Recommender Systems (RecSys’18), Vancouver, Canada, Oct. 2018
Predictive Analytics for Customer Targeting: A Telemarketing Banking ExamplePedro Ecija Serrano
A comparison of classification methods to predict buyers in banking telemarketing. Overcoming class imbalance and gaining insight on what customers are likely to buy a particular financial product.
Manthan is one of the best Restaurant Analytics Software Company in US which provides comprehensive AI-powered solution that addresses every need of the contemporary restaurant chain. With Customer Analytics for restaurant marketing, targeting and personalization, Demand Analytics for identifying opportunities and Operational Analytics for day-to-day management.
This 7-second Brain Wave Ritual Attracts Money To You.!nirahealhty
Discover the power of a simple 7-second brain wave ritual that can attract wealth and abundance into your life. By tapping into specific brain frequencies, this technique helps you manifest financial success effortlessly. Ready to transform your financial future? Try this powerful ritual and start attracting money today!
# Internet Security: Safeguarding Your Digital World
In the contemporary digital age, the internet is a cornerstone of our daily lives. It connects us to vast amounts of information, provides platforms for communication, enables commerce, and offers endless entertainment. However, with these conveniences come significant security challenges. Internet security is essential to protect our digital identities, sensitive data, and overall online experience. This comprehensive guide explores the multifaceted world of internet security, providing insights into its importance, common threats, and effective strategies to safeguard your digital world.
## Understanding Internet Security
Internet security encompasses the measures and protocols used to protect information, devices, and networks from unauthorized access, attacks, and damage. It involves a wide range of practices designed to safeguard data confidentiality, integrity, and availability. Effective internet security is crucial for individuals, businesses, and governments alike, as cyber threats continue to evolve in complexity and scale.
### Key Components of Internet Security
1. **Confidentiality**: Ensuring that information is accessible only to those authorized to access it.
2. **Integrity**: Protecting information from being altered or tampered with by unauthorized parties.
3. **Availability**: Ensuring that authorized users have reliable access to information and resources when needed.
## Common Internet Security Threats
Cyber threats are numerous and constantly evolving. Understanding these threats is the first step in protecting against them. Some of the most common internet security threats include:
### Malware
Malware, or malicious software, is designed to harm, exploit, or otherwise compromise a device, network, or service. Common types of malware include:
- **Viruses**: Programs that attach themselves to legitimate software and replicate, spreading to other programs and files.
- **Worms**: Standalone malware that replicates itself to spread to other computers.
- **Trojan Horses**: Malicious software disguised as legitimate software.
- **Ransomware**: Malware that encrypts a user's files and demands a ransom for the decryption key.
- **Spyware**: Software that secretly monitors and collects user information.
### Phishing
Phishing is a social engineering attack that aims to steal sensitive information such as usernames, passwords, and credit card details. Attackers often masquerade as trusted entities in email or other communication channels, tricking victims into providing their information.
### Man-in-the-Middle (MitM) Attacks
MitM attacks occur when an attacker intercepts and potentially alters communication between two parties without their knowledge. This can lead to the unauthorized acquisition of sensitive information.
### Denial-of-Service (DoS) and Distributed Denial-of-Service (DDoS) Attacks
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024APNIC
Ellisha Heppner, Grant Management Lead, presented an update on APNIC Foundation to the PNG DNS Forum held from 6 to 10 May, 2024 in Port Moresby, Papua New Guinea.
1.Wireless Communication System_Wireless communication is a broad term that i...JeyaPerumal1
Wireless communication involves the transmission of information over a distance without the help of wires, cables or any other forms of electrical conductors.
Wireless communication is a broad term that incorporates all procedures and forms of connecting and communicating between two or more devices using a wireless signal through wireless communication technologies and devices.
Features of Wireless Communication
The evolution of wireless technology has brought many advancements with its effective features.
The transmitted distance can be anywhere between a few meters (for example, a television's remote control) and thousands of kilometers (for example, radio communication).
Wireless communication can be used for cellular telephony, wireless access to the internet, wireless home networking, and so on.
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesSanjeev Rampal
Talk presented at Kubernetes Community Day, New York, May 2024.
Technical summary of Multi-Cluster Kubernetes Networking architectures with focus on 4 key topics.
1) Key patterns for Multi-cluster architectures
2) Architectural comparison of several OSS/ CNCF projects to address these patterns
3) Evolution trends for the APIs of these projects
4) Some design recommendations & guidelines for adopting/ deploying these solutions.
16. v
“Frequently bought with” Recommendations
Not necessarily
consumed together
Help customers shop for
complementary products
and try alternatives
Probably
consumed together
18. v
Learning from feedback
Traditionally collaborative filtering used explicit feedback to predict ratings
There may still bias in whether the user chooses to rate
Explicit Feedback Implicit Feedback
19. v
Learning from Explicit Feedback
• Explicit feedback may be more reliable but there is much less of it
• Less reliable if users rate based on aspirations instead of true preferences
vs
20. v
Implicit Feedback - trade-off quality and quantity
Strengthofevidence
Number of Events
21. v
Architecture
Event Data Score and
Select Top N
(Spark/EMR)
User/Product Factors
Event Data
Run-time
ranking for
diversity
Candidate
Selection
ALS
(Spark/EMR)
Generate
User-Product
Matrix
22. v
A Matrix Factorization Formulation for Implicit Feedback
N Products
MUsers
1
-
-
9
-
-
-
3
20
User Product Matrix
R; (M x N)
1
0
0
1
0
0
0
1
1binary
preferences
Preference Matrix R;
(M x N)
“Collaborative Filtering for Implicit Feedback” - Hu et. al
23. v
A Matrix Factorization Formulation for Implicit Feedback
~
Y
XT
Product Factors
(k x N)
User Factors
(M x k)
1
0
0
1
0
0
0
1
1
x
Preference Matrix R;
(M x N)
24. v
Matrix Factorization from Implicit Feedback - The Intuition
#Purchases Preference p Confidence c
0 0 Low
1 1 Low
>>1 1 High
• Confidence increases linearly with purchases r
• c = 1 + alpha * r
• alpha controls the marginal rate of learning from user purchases
• Key questions
• How should the unobserved events be treated
• How should one trade-off observed and the unobserved
25. v
Regularized Weighted Squared Loss
Confidence
User
Factors
Matrix
Product
Factors
Matrix
Preference
Matrix Regularization
Solve using Alternating Least Squares
27. v
Spark ALS Hyper-parameter Tuning
• rank k - diminishing returns after 150
• alpha - controls rate of learning from observed events
• iterations - ALS tends to converge within 5, seldom more than 10
• lambda - regularization parameter
29. v
Scoring user and products
With millions of products and users, scoring every (user, product) pair is prohibitive
Two goals in selecting products to score
• Long tail which have not been discovered
• Products that have an a priori high purchase rate (popular)
~
30. v
Trade-off popularity and discovery in the tail
We start with simple stratified sampling
For each user, score N products
Sample h products from Head
Sample t products from tail
N ~ 10000
h ~ 3000
t ~7000
31. v
Tuning Spark For ALS
Understanding Spark execution model and its implementation of ALS helps
• Training is communication heavy1
, set partitions <= #CPU cores
• Scoring is memory intensive
• Broad guidelines2
• Limit executor memory to 64GB
• 5 cores per executor
• Set executors based on data size
1 - http://apache-spark-user-list.1001560.n3.nabble.com/Error-No-space-left-on-device-tp9887p9896.html
2 - http://blog.cloudera.com/blog/2015/03/how-to-tune-your-apache-spark-jobs-part-1/
33. v
A/B Test Results
• Statistically significant increases
• Items per order
• GMV per order
• Total product sales spread over more
categories
34. v
Ok, we have a recommendation system
Where do we go from here?
35. v
What else do you do with user and product factors?
Score (user, product) pair on demand
Get Top N similar users
Get Top N similar product
As features in other models
36. v
Products similar to “Haigs Spicy Hummus"
More “Spicy Hummus”
Spicy Salsas
Generated using Approximate Nearest Neighbor
(“annoy” from Spotify)
37. v
What next
• Make recommendations more contextual
• Explain recommendations (“Because you did X”)
42. v
Traditional E-commerce
• Manage inventory in warehouses optimized for quick
fulfillment
• Customers only specify the “What”
• Disallow users from ordering out of stock products
• Set expectations
• “3 day shipping” but will ship in 10 business days
43. v
On-demand delivery from local retailers
• Shoppers navigate a complex environment where products
• may have run out
• may be misplaced
• may be damaged
• Customers specify “What”, “When” and “Where from”
• Improvise under uncertainty
44. v
Customers
Advertisers
(brands)
Stores
(Retailers)
lose revenue and
trust of customers
Everybody loses when out of stocks happen
• don’t get exactly what
they want
• must contemplate
and/or communicate
replacements
lose revenue and
trust of customers
• waste time searching for
items that aren’t in store
• context switch to
searching and
communicating
replacements
Shoppers
47. v
A probable solution
Do not show or allow customers to order items
that are currently out of stock
48. v
A probable (but terrible) solution
• Customers really know these stores
• “Missing” items is seen as a sign of an unreliable catalog/service
• May have been out of stock this morning but could be available when the
order is fulfilled
• Sets up negative spirals
“I was there over the
weekend. Please check behind
the cheeses aisle”
“Are you telling
me they don’t carry
strawberries?”
49. v
Solution that works reasonably well
• Shoppers can see Instacart recommended
replacements while shopping in the store
• Customers may also specify or choose from
recommended replacements
• Relatively more flexibility with groceries
• Some services offer to cancel the order if
an item isn’t available
50. v
Instacart Recommended Replacements
Flavor PackingSizeBrand Price
• Several product attributes matter
• Context matters, might benefit from personalization
• Must scale to millions of products
• Not always symmetric
• May be ok to replace X with gluten free X but not the other way around
Diet
Info
51. v
• Shoppers are trained to pick replacements
• But shoppers can benefit from algorithmic suggestions
• Many unfamiliar products in a vast catalog
• Validation for common products
• Finding replacements fast improves operational efficiency
Replacement Recommendations for Shoppers
52. v
• Customers can specify replacements while placing the order
• Can choose to communicate with the shopper in store to verify
Replacement Recommendations for Customers
53. v
What could we do if could predict item availability?
Customer
location
Nearest
store
Farther, but
better availability
Controlling for retailer and quality,
customer is indifferent to physical location
54. v
The Item Availability Prediction
Probability( Item in store | time, context)
What is probability that an item will be at
the store when the shopper shows up to
look for it?
55. v
Item Availability as a Classification Problem
TIMESTAMP, ITEM IDENTIFIED, IN STORE?
• Millions of examples from historical data
• Feature Engineering
• historical availability at multiple resolutions
• Eg: time since last “not found” event
• Item attributes
• Eg: perishables restocked differently than personal care
• Temporal Features
57. v
Serving and Optimization Layer
Fulfillment
Engine
Order
Fulfillment plan:
Store location, Shopper etc.
Items,
eligible store
locations
Availability
scores
Active in production with an acceptable
trade-off between
fulfillment efficiency and refund rate
58. v
Whats next
• Leverage model predictions for other features/data products
• Avoid negative feedback loops!
• Biased training data
• only have access to what is ordered through Instacart
• Tighter integrations with retailer data
• Scaling: continue to score a growing catalog at tight SLAs
61. v
Offline evaluation
• Ideally we want to evaluate user response to recommendations
• But we will only know this from an live A/B test
• Recall based metrics are an offline proxy (albeit not the best)
• Recall: “Fraction of purchased products covered among Top N
recommendations”
• We only use this for hyper parameter tuning
62. v
Ensembles
Use different types of evidence and/or product metadata to easily create ensembles
User x Products Purchased
User x Products Viewed
User x Brands Purchased
Model or Linear
Combination
…
64. v
Online ranking for diversity
“Diversity within sessions, Novelty across sessions”
“Establish trust in a fresh and comprehensive catalog”
“Less is more”
Cached list of
~1000 products
per user
Final list of
<100 products
promote diversity
65. v
Diversity
Top K products - ranked by score
Rank product categories by their median product score
> > >
66. v
Weighted sampling for diversity
Sample category in
proportion to score
Within category, sample in
proportion to product score
68. v
Out of stocks happen due to uncertainty in several places
Order fulfillment in (distant) future
Cannot hold inventory
Real-time inventory tracking across
thousands of locations isn’t perfect (yet)
Customer might reschedule delivery