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
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
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/
A talk on how we use simulation-based optimization at Instacart to manage several tradeoffs and achieve supply/demand equilibrium when trying to solve how many shoppers we need to staff for.
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.
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
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
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/
A talk on how we use simulation-based optimization at Instacart to manage several tradeoffs and achieve supply/demand equilibrium when trying to solve how many shoppers we need to staff for.
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.
Artwork Personalization at Netflix Fernando Amat RecSys2018 Fernando Amat
For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front of our members at the right time. But the job of recommendation does not end there. The homepage should be able to convey to the member enough evidence of why a title may be good for her, especially for shows that the member has never heard of. One way to address this challenge is to personalize the way we portray the titles on our service. An important aspect of how to portray titles is through the artwork or imagery we display to visually represent each title. The artwork may highlight an actor that you recognize, capture an exciting moment like a car chase, or contain a dramatic scene that conveys the essence of a movie or show. It is important to select good artwork because it may be the first time a member becomes aware of a title (and sometimes the only time), so it must speak to them in a meaningful way. In this talk, we will present an approach for personalizing the artwork we use on the Netflix homepage. The system selects an image for each member and video to give better visual evidence for why the title might be appealing to that particular member.
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.
Talk from QCon SF on 2018-11-05
For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front each of our members at the right time. With a catalog spanning thousands of titles and a diverse member base spanning over a hundred million accounts, recommending the titles that are just right for each member is crucial. But the job of recommendation does not end there. Why should you care about any particular title we recommend? What can we say about a new and unfamiliar title that will pique your interest? How do we convince you that a title is worth watching? Answering these questions is critical in helping our members discover great content, especially for unfamiliar titles. One way to do this is to consider the artwork or imagery we use to visually portray each title. If the artwork representing a title captures something compelling to you, then it acts as a gateway into that title and gives you some visual “evidence” for why the title might be good for you. Selecting good artwork is important because it may be the first time a member becomes aware of a title (and sometimes the only time), so it must speak to them in a meaningful way. In this talk, we will present an approach for personalizing the artwork we show for each title on the Netflix homepage. We will look at how to frame this as a machine learning problem using contextual multi-armed bandits in a recommendation system setting. We will also describe the algorithmic and system challenges involved in getting this type of approach for artwork personalization to succeed at Netflix scale. Finally, we will discuss some of the future opportunities that we see to expand and improve upon this approach.
Personalized Page Generation for Browsing RecommendationsJustin Basilico
Talk from First Workshop on Recommendation Systems for TV and Online Video at RecSys 2014 in Foster City, CA on 2014-10-10 about how we personalize the layout of the Netflix homepage to make it easier for people to browse the recommendations to quickly find something to watch and enjoy.
How to Improve Your Amazon Operations to Grow Purchase Orders & ProfitabilityTinuiti
Amazon is constantly changing. Today, vendors have more insight & tools than ever before to improve their operational performance and Amazon competency. Unfortunately, interpreting and implementing these changes are challenging.
But for Amazon vendors who want to scale sales, it’s essential to use Vendor Central data to create a holistic product catalog analysis, the dynamic factors affecting sales & profitability, and how that aligns with Amazon’s ongoing PO process.
Some Topics We’ll Discuss:
-Leveraging Amazon’s Retail Analytics (Basic + Premium)
-Demystifying Your Amazon Vendor Central Data
-Warehouse Functions & Their Impact on Inventory Availability
-Understanding Amazon’s Demand Forecasting Model
-Combining Operational Data into Your AMS Strategy
our Privacy Policy.
Don’t Miss Out—Former Manager, Vendor Management at Amazon and now CPC Strategy’s Manager of Amazon Vendor Operations, Eric Kauss, is joined by our Head of Markeptlace Strategy, Pat Petriello, for a webinar that delves into maintaining a operationally efficient & profitable business on Amazon.
Personalizing "The Netflix Experience" with Deep LearningAnoop Deoras
These are the slides from my talk presented at AI Next Con conference in Seattle in Jan 2019. Here I talk in a bit more detail about the intuition behind collaborative filtering and go a bit deeper into the details of non linear deep learned models.
Controlled Experimentation aka A/B Testing for PMs by Tinder Sr PMProduct School
Main Takeaways:
-A/B testing: a simple idea that can be simple to apply
-Useful for more than incremental optimization - A/B tests can yield deep insight
-Just test it - A/B tests have the highest ROI of any data activity
How to Leverage your Amazon Holiday Sales for a Profitable 2015 FeedVisor
The selling potential for Amazon sellers is massive over the Holiday Season. But what happens once Christmas ends? How do you carry over your Christmas success?
Did you know that you can use your Christmas sales to advance your sales figures in the New Year?
Join Feedvisor’s Director of Marketing, Shmuli Goldberg, and SellerLabs’ Co-Founder, Brandon Checketts, for expert advice on the strategies you can implement today to ensure your 2014 Holiday momentum carries forward into 2015. They’ll be discussing advanced tactics to increase sales and improve your bottom line.
Webinar Highlights:
- Amazon revenue forecasts for 2015 and what this means for you
- The Amazon Buy Box and its impact on sales
- How to use the Feedback and Pricing metrics to your advantage
- Tactics you can implement today to make more profit
Artwork Personalization at Netflix Fernando Amat RecSys2018 Fernando Amat
For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front of our members at the right time. But the job of recommendation does not end there. The homepage should be able to convey to the member enough evidence of why a title may be good for her, especially for shows that the member has never heard of. One way to address this challenge is to personalize the way we portray the titles on our service. An important aspect of how to portray titles is through the artwork or imagery we display to visually represent each title. The artwork may highlight an actor that you recognize, capture an exciting moment like a car chase, or contain a dramatic scene that conveys the essence of a movie or show. It is important to select good artwork because it may be the first time a member becomes aware of a title (and sometimes the only time), so it must speak to them in a meaningful way. In this talk, we will present an approach for personalizing the artwork we use on the Netflix homepage. The system selects an image for each member and video to give better visual evidence for why the title might be appealing to that particular member.
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.
Talk from QCon SF on 2018-11-05
For many years, the main goal of the Netflix personalized recommendation system has been to get the right titles in front each of our members at the right time. With a catalog spanning thousands of titles and a diverse member base spanning over a hundred million accounts, recommending the titles that are just right for each member is crucial. But the job of recommendation does not end there. Why should you care about any particular title we recommend? What can we say about a new and unfamiliar title that will pique your interest? How do we convince you that a title is worth watching? Answering these questions is critical in helping our members discover great content, especially for unfamiliar titles. One way to do this is to consider the artwork or imagery we use to visually portray each title. If the artwork representing a title captures something compelling to you, then it acts as a gateway into that title and gives you some visual “evidence” for why the title might be good for you. Selecting good artwork is important because it may be the first time a member becomes aware of a title (and sometimes the only time), so it must speak to them in a meaningful way. In this talk, we will present an approach for personalizing the artwork we show for each title on the Netflix homepage. We will look at how to frame this as a machine learning problem using contextual multi-armed bandits in a recommendation system setting. We will also describe the algorithmic and system challenges involved in getting this type of approach for artwork personalization to succeed at Netflix scale. Finally, we will discuss some of the future opportunities that we see to expand and improve upon this approach.
Personalized Page Generation for Browsing RecommendationsJustin Basilico
Talk from First Workshop on Recommendation Systems for TV and Online Video at RecSys 2014 in Foster City, CA on 2014-10-10 about how we personalize the layout of the Netflix homepage to make it easier for people to browse the recommendations to quickly find something to watch and enjoy.
How to Improve Your Amazon Operations to Grow Purchase Orders & ProfitabilityTinuiti
Amazon is constantly changing. Today, vendors have more insight & tools than ever before to improve their operational performance and Amazon competency. Unfortunately, interpreting and implementing these changes are challenging.
But for Amazon vendors who want to scale sales, it’s essential to use Vendor Central data to create a holistic product catalog analysis, the dynamic factors affecting sales & profitability, and how that aligns with Amazon’s ongoing PO process.
Some Topics We’ll Discuss:
-Leveraging Amazon’s Retail Analytics (Basic + Premium)
-Demystifying Your Amazon Vendor Central Data
-Warehouse Functions & Their Impact on Inventory Availability
-Understanding Amazon’s Demand Forecasting Model
-Combining Operational Data into Your AMS Strategy
our Privacy Policy.
Don’t Miss Out—Former Manager, Vendor Management at Amazon and now CPC Strategy’s Manager of Amazon Vendor Operations, Eric Kauss, is joined by our Head of Markeptlace Strategy, Pat Petriello, for a webinar that delves into maintaining a operationally efficient & profitable business on Amazon.
Personalizing "The Netflix Experience" with Deep LearningAnoop Deoras
These are the slides from my talk presented at AI Next Con conference in Seattle in Jan 2019. Here I talk in a bit more detail about the intuition behind collaborative filtering and go a bit deeper into the details of non linear deep learned models.
Controlled Experimentation aka A/B Testing for PMs by Tinder Sr PMProduct School
Main Takeaways:
-A/B testing: a simple idea that can be simple to apply
-Useful for more than incremental optimization - A/B tests can yield deep insight
-Just test it - A/B tests have the highest ROI of any data activity
How to Leverage your Amazon Holiday Sales for a Profitable 2015 FeedVisor
The selling potential for Amazon sellers is massive over the Holiday Season. But what happens once Christmas ends? How do you carry over your Christmas success?
Did you know that you can use your Christmas sales to advance your sales figures in the New Year?
Join Feedvisor’s Director of Marketing, Shmuli Goldberg, and SellerLabs’ Co-Founder, Brandon Checketts, for expert advice on the strategies you can implement today to ensure your 2014 Holiday momentum carries forward into 2015. They’ll be discussing advanced tactics to increase sales and improve your bottom line.
Webinar Highlights:
- Amazon revenue forecasts for 2015 and what this means for you
- The Amazon Buy Box and its impact on sales
- How to use the Feedback and Pricing metrics to your advantage
- Tactics you can implement today to make more profit
11 eCommerce CRO Tips to Scale up Your Business Graphsndigitalindia
The competition in eCommerce market is huge and so the conversion. We have compiled a list of 11 techniques to sustain and accrue if implemented correctly.
A SMART PRODUCT REVIEW STRATEGY FOR LAUNCHING NEW PRODUCTS AS A 3p SELLERTinuiti
learn top strategies for launching a product in the Amazon marketplace at an accelerated rate with our partner eComEngine, LLC. We'll be reviewing the Amazon Born to Run program, different options to manage inventory and tactics to get reviews.
Your customers are on a journey when they search for your products online, and your store's landing pages should be the destination they can't miss. But do you know which types of landing pages work best?
Join Raphael Paulin-Daigle, CEO of SplitBase, in this session where he'll reveal five types you should definitely test out. Get to see how to align your landing pages perfectly with your customer's buying journey and ad campaigns for maximum impact.
When it comes to Conversion Rate Optimization (CRO) for eCommerce, personalization is key. Raphael will also share top tips for audience research, empowering you to tailor your landing pages like a pro. Plus, he'll unveil a fail-proof process to test your landing pages and watch your conversions skyrocket.
Recovering Lost Leads & Customers Along Your Sales Funnel Using Simple Websit...Divvit
The ultimate guide to plugging leaks along your sales funnel, from our webinar with CartStack's Colton Bradshaw. Learn how to optimize each step of the sales funnel to reduce bounce rate, browse abandonment rate, and cart abandonment rate with smart recovery emails and UX optimization.
Read the article here: https://www.divvit.com/blog-posts/recovering-lost-leads-how-improve-ecommerce-sales-funnel
Watch the webinar here: https://youtu.be/WdpPAOpxU0k
With several major retail clients, the growing popularity of consumer “showrooming” piqued our interest at Crimson Hexagon. We were curious: how can we leverage online consumer opinion to address this major industry-wide challenge?
Through deep analysis of social data, we seek to discover opportunities for retailers to fight back against “showrooming” and keep customers in-store. We discuss our research findings, and explain the implications for retailers.
eComm HubSpot User Group: Customer Cultivation ResellerRatings
Unific is known for unlocking and simplifying Ecommerce growth with data integration, analytics, personalization, and retention tools running on top of HubSpot. Their Customer Cultivation framework helps marketers use data to discover what to do next in order to consistently delight their customers with HubSpot.
With RFM / Buying Behavior Analysis, learn how Unific helps Ecommerce growth marketers use HubSpot to:
-- Identify and act on weaknesses in the customer journey with HubSpot Workflows
-- Increase abandoned cart recovery rate and save margin by using data to decide who needs a coupon to complete their checkout and who doesn’t
-- Use Dynamic Segments with HubSpot Workflows to send the right message to the right person at the right time
-- Use HubSpot Workflows to delight and collect UGC (user-generated content)
-- Increase revenue from best customers and prevent churn from drifting customers with Dynamic Coupons
-- Use Unific’s deep shopping cart integration with HubSpot’s Service Hub to provide an exceptional experience during pre-purchase and post-purchase interactions
-- Use HubSpot's powerful Custom Workflow Actions and use Unific and other apps in the HubSpot app marketplace to provide a delightful experience in every part of the customer journey
5 Types of Customers & What Motivates Them Tal Lior
What are the 5 types of customers that exist online? What does it take to turn them into buyers?
Learn how to identify, convert, and track them in this power guide.
Merchandising around out of stock to save the saleNEW MEDIA GURU
Merchandising around out of stock to save the sale
>>>>>>
An online shopper’s discovery that a searched-for product is out of stock is a lost opportunity for the merchant. Frustration can drive shoppers to another site, leaving a trail of disappointment with the brand in their wake – but it doesn’t have to be that way. It’s all about narrowing the gap between the expectations your site sets up for shoppers around current inventory status and what your site is able to deliver. This session will highlight how merchants can handle out-of-stocks online to retain shoppers’ future business, and even direct them to other in-stock products in a way they’ll be receptive to.
Digikala is the biggest e-commerce startup in Iran. It was founded in July, 2006 by twin brothers Hamid and Saeed Mohammadi. Digikala online grocery shopping was a pioneer project in Iran e-commerce which designing its development plan, setting out the key resources to tuning a business model need to know the world best practices
Control Your Online Reputation - MSP Social Media BreakfastAaron Weiche
My presentation covering online review, customer testimonials and case studies. Learn the power of online reputation, customer feedback, Net Promoter Score, rich snippets and more.
Similar to ML @ Instacart: Improving the quality of On-demand Grocery (20)
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptxBrad Spiegel Macon GA
Brad Spiegel Macon GA’s journey exemplifies the profound impact that one individual can have on their community. Through his unwavering dedication to digital inclusion, he’s not only bridging the gap in Macon but also setting an example for others to follow.
# 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
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.
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.
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.
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!
17. “Don’t show
me items that
can’t be
fulfilled”
“Call/chat during
picking regarding
replacements”
“Warn me about
stock level and
let me specify the
replacement”
“Trust the
shopper to
replace”
“Do not
replace item”
More permissive
Convenience Focus
More Proactive
Precision Focus
18. ● Item Found Rate
○ % of ordered items that are fulfilled
● Replacement Satisfaction Rate
○ % of replacements implicitly/explicitly approved by customer
21. In-store activity assumed as ground truth of item being in the store
Model Probability(Found) as a supervised binary classification problem
22. Aggregate Found Rate Statistics at higher levels (Critical for Tail Items)
● Product
● Retailer + Product
● Retailer + Product + Region
XGBoost Model with ~100 features
Example Item Level Features (Effective for Popular Items)
● Time since last not-found/found
● Found Rate in last 6m, 3m, 1 week, 1 day, 6 hours
23. Availability scores low across US
Even in stores where it hasn’t been bought (due to
product level features)
A store in Mission District:
Availability score: bottom 2 percentile
Past found rate: extremely low
From the Vice News report: “The milk
substitute has become so popular in places
like Brooklyn that shortages have broken out,
and a grey market for the most sought-after
brand of the stuff — Oatly — has popped up
online. Sometimes liters of Oatly can sell for
as much as $18 each.”
24. What comes next?
You’ve been freed
Do you know
how hard it is to lead?
-
Source: https://smcl.org/blogs/post/wait-for-it/
26. ● Retailer Location Selection
● Replacement Suggestions
during fulfillment/picking
● Picking Item List Ranking
● Search and Merchandising Ranking
● Low Stock Inform and Mitigate
● Post-Checkout Experience
● Chat with shopper during
fulfillment/picking
Customer Experience Shopper Experience
27. ● Eroding trust in Catalog
● Customer Churn
Show all relevant
items including
low stock
Remove all low
stock items
● Eroding trust in Fulfillment
● Lower shopper productivity
● Customer Churn
How can we create the optimal search experience?
28. Good improvement in Found Rate
Unacceptable drop in Search Conversion Rate
Hidden Items
Query: “Milk chocolate”
We were often removing items customers really wanted!
29. Demoted Items
No drop in Search Conversion Rate
Low improvement in Found Rate
Customers were ordering demoted items anyway!
Query: “Milk chocolate”
30.
31. ● Use data collected from demotion experiment
● Learn a simple model/heuristic to predict whether a
demoted item would be ordered given search
Key Insight:
Highly relevant
Query: “Milk chocolate”
32. Top 2 features describing search context
● # of results
● # of demoted results from top 5
# of items demoted in top 5
results
Don’t operate here
Ensure that the search results are relevant, mostly in stock and retains good selection of products
33.
34. “Don’t show
me items that
can’t be
fulfilled”
“Call/chat during
picking regarding
replacements”
“Warn me about
stock level and
let me specify the
replacement”
“Trust the
shopper to
replace”
“Do not
replace item”
More permissive
Convenience Focus
More Proactive
Precision Focus
37. ● Retailer Location Selection
● Replacement Suggestions
during fulfillment
● Picking Item List Ranking
● Search and Merchandising Ranking
● Low Stock Inform and Mitigate
● Post-Checkout Experience
● Chat with shopper during
fulfillment/picking
40% relative reduction
in low quality deliveries
Customer Experience Shopper Experience
38. ● Pick problems where ML can make unique contributions
○ Hiring/training product minded ML Engineers is challenging
● Pick problems that are fundamental to the business with broad applications
○ Instacart examples: Item Availability, Replacement recommendation, Product Targeting
● New use cases of existing models are often higher ROI than improving the model*
● Design and PM are key partners in getting the most value out of ML efforts