This document outlines key concepts in recommendation systems. It begins by defining the traditional recommender problem as predicting user ratings for items based on past behavior and relationships. It then discusses lessons learned from the Netflix Prize competition, including the effectiveness of singular value decomposition and the limitations of models designed only for rating prediction. The document outlines approaches beyond rating prediction, including ranking, similarity, social recommendations, and explore/exploit tradeoffs. It discusses optimizing recommendation pages and using higher-order models like tensor factorization. In summary, it provides an overview of traditional and modern approaches in recommendation systems.
Past, Present & Future of Recommender Systems: An Industry PerspectiveJustin Basilico
Slides from our talk at the RecSys 2016 conference in Boston, MA 2016-09-18 on our perspective for what are important areas for future work in recommender systems.
At Netflix we take context of the member seriously.
In this keynote talk we will see how modeling contextual factors such as time or device can help members to find the right content at the right moment
At the end, the goal is to maximize member satisfaction and retention
These slides will go through which contextual factors matters for the video service and why we choose to use them or not.
(Presented at the Deep Learning Re-Work SF Summit on 01/25/2018)
In this talk, we go through the traditional recommendation systems set-up, and show that deep learning approaches in that set-up don't bring a lot of extra value. We then focus on different ways to leverage these techniques, most of which relying on breaking away from that traditional set-up; through providing additional data to your recommendation algorithm, modeling different facets of user/item interactions, and most importantly re-framing the recommendation problem itself. In particular we show a few results obtained by casting the problem as a contextual sequence prediction task, and using it to model time (a very important dimension in most recommendation systems).
Shallow and Deep Latent Models for Recommender SystemAnoop Deoras
In this presentation, we survey latent models, starting with shallow and progressing towards deep, as applied to personalization and recommendations. After providing an overview of the Netflix recommender system, we discuss research at the intersection of deep learning, natural language processing and recommender systems and how they relate to traditional collaborative filtering techniques. We will present case studies in the space of deep latent variable models applied to recommender systems.
Past, Present & Future of Recommender Systems: An Industry PerspectiveJustin Basilico
Slides from our talk at the RecSys 2016 conference in Boston, MA 2016-09-18 on our perspective for what are important areas for future work in recommender systems.
At Netflix we take context of the member seriously.
In this keynote talk we will see how modeling contextual factors such as time or device can help members to find the right content at the right moment
At the end, the goal is to maximize member satisfaction and retention
These slides will go through which contextual factors matters for the video service and why we choose to use them or not.
(Presented at the Deep Learning Re-Work SF Summit on 01/25/2018)
In this talk, we go through the traditional recommendation systems set-up, and show that deep learning approaches in that set-up don't bring a lot of extra value. We then focus on different ways to leverage these techniques, most of which relying on breaking away from that traditional set-up; through providing additional data to your recommendation algorithm, modeling different facets of user/item interactions, and most importantly re-framing the recommendation problem itself. In particular we show a few results obtained by casting the problem as a contextual sequence prediction task, and using it to model time (a very important dimension in most recommendation systems).
Shallow and Deep Latent Models for Recommender SystemAnoop Deoras
In this presentation, we survey latent models, starting with shallow and progressing towards deep, as applied to personalization and recommendations. After providing an overview of the Netflix recommender system, we discuss research at the intersection of deep learning, natural language processing and recommender systems and how they relate to traditional collaborative filtering techniques. We will present case studies in the space of deep latent variable models applied to recommender systems.
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
I had a fun time giving tutorial on the topic of deep learning in recommender systems at Latin America School on Recommender Systems (LARS) in Fortaleza, Brazil.
Déjà Vu: The Importance of Time and Causality in Recommender SystemsJustin Basilico
Talk at RecSys 2017 in Como, Italy on 2017-08-29.
Abstract:
Time plays a key role in recommendation. Handling it properly is especially critical when using recommender systems in real-world applications, which may not be as clear when doing research with historical data. In this talk, we will discuss some of the important challenges of handling time in recommendation algorithms at Netflix. We will focus on challenges related to how our users, items, and systems all change over time. We will then discuss some strategies for tackling these challenges, which revolves around proper treatment of causality in our systems.
Recommendation systems today are widely used across many applications such as in multimedia content platforms, social networks, and ecommerce, to provide suggestions to users that are most likely to fulfill their needs, thereby improving the user experience. Academic research, to date, largely focuses on the performance of recommendation models in terms of ranking quality or accuracy measures, which often don’t directly translate into improvements in the real-world. In this talk, we present some of the most interesting challenges that we face in the personalization efforts at Netflix. The goal of this talk is to sunshine challenging research problems in industrial recommendation systems and start a conversation about exciting areas of future research.
Deeper Things: How Netflix Leverages Deep Learning in Recommendations and Se...Sudeep Das, Ph.D.
In this talk, we will provide an overview of Deep Learning methods applied to personalization and search at Netflix. We will set the stage by describing the unique challenges faced at Netflix in the areas of recommendations and information retrieval. Then we will delve into how we leverage a blend of traditional algorithms and emergent deep learning methods and new types of embeddings, especially hyperbolic space embeddings, to address these challenges.
A Multi-Armed Bandit Framework For Recommendations at NetflixJaya Kawale
In this talk, we present a general multi-armed bandit framework for recommendations on the Netflix homepage. We present two example case studies using MABs at Netflix - a) Artwork Personalization to recommend personalized visuals for each of our members for the different titles and b) Billboard recommendation to recommend the right title to be watched on the Billboard.
Talk with Yves Raimond at the GPU Tech Conference on Marth 28, 2018 in San Jose, CA.
Abstract:
In this talk, we will survey how Deep Learning methods can be applied to personalization and recommendations. We will cover why standard Deep Learning approaches don't perform better than typical collaborative filtering techniques. Then we will survey we will go over recently published research at the intersection of Deep Learning and recommender systems, looking at how they integrate new types of data, explore new models, or change the recommendation problem statement. We will also highlight some of the ways that neural networks are used at Netflix and how we can use GPUs to train recommender systems. Finally, we will highlight promising new directions in this space.
Past, present, and future of Recommender Systems: an industry perspectiveXavier Amatriain
Keynote for the ACM Intelligent User Interface conference in 2016 in Sonoma, CA. I start with the past by talking about the Recommender Problem, and the Netflix Prize. Then I go into the Present and the Future by talking about approaches that go beyond rating prediction and ranking and by finishing with some of the most important lessons learned over the years. Throughout my talk I put special emphasis on the relation between algorithms and the User Interface.
Recommender Systems represent one of the most widespread and impactful applications of predictive machine learning models.
Amazon, YouTube, Netflix, Facebook and many other companies generate an important fraction of their revenues thanks to their ability to model and accurately predict users ratings and preferences.
In this presentation we cover the following points:
→ introduction to recommender systems
→ working with explicit vs implicit feedback
→ content-based vs collaborative filtering approaches
→ user-based and item-item methods
→ machine learning and deep learning models
→ pros & cons of the methods: scalability, accuracy, explainability
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.
Presentation at the Netflix Expo session at RecSys 2020 virtual conference on 2020-09-24. It provides an overview of recommendation and personalization at Netflix and then highlights some of the things we’ve been working on as well as some important open research questions in the field of recommendations.
RecSys 2020 A Human Perspective on Algorithmic Similarity Schendel 9-2020Zachary Schendel
In the Netflix user interface (UI), when a row or UI element is named “Because you Watched...”, “More Like This”, or “Because you added to your list”, the overarching goal is to recommend a movie or TV show that a member might like based on the fact that they took a meaningful action on a source item. We have employed similar recommendations in many UI elements: on the homepage as a row of recommendations, after you click into a title, or as a piece of information about why a member should watch a title.
From an algorithmic perspective, there are many ways to define a “successful” similar recommendation. We sought to broaden that definition of success. To this end, the Consumer Insights team recently completed a suite of research projects to explore the intricacies of member perceptions of similar recommendations. The Netflix Consumer Insights team employs qualitative (e.g., in-depth interviews) and quantitative (e.g., surveys) research methods, interfacing directly with Netflix members to uncover pain points that can inspire new product innovation. The research concluded that, while the typical member believes movies are broadly similar when they share a common genre or theme, similarity is more complex, nuanced, and personal than we might have imagined. The vernacular we use in the UI implies that there should be at least some kind of relationship between the source item and the recommendations that follow. Many of our similar recommendations felt “out of place”, mostly because the relationship between the source item and the recommendation was unclear or absent. When similar recommendations tell a completely misleading, incorrect, or confusing story, member trust can be broken.
We will structure the presentation around three new insights that our research found to have an influence on the perception of similarity in the context of Netflix as well as the research methods used to uncover those insights. First, the reason a member loves a given movie will vary. For example, do you want to watch other baseball movies like Field of Dreams, or would you prefer other romances like Field of Dreams? Second, members are more or less flexible about how similar a recommendation actually needs to be depending on the properties of and their interactions with the canvas containing the recommendation. For example, a Because You Watched row on the homepage implies vaguer similarity while a More Like This gallery behind a click into the source item implies stricter similarity. Finally, even when we held the UI element constant, we found that similar recommendations are only valuable in some contexts. After finishing a movie, a member might prefer a similar recommendation one day and a change of pace the next. Research methods discussed will include Inverse Multi-Dimensional Scaling [1], survey experimentation, and ways to apply qualitative research to improve algorithmic recommendations.
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
I had a fun time giving tutorial on the topic of deep learning in recommender systems at Latin America School on Recommender Systems (LARS) in Fortaleza, Brazil.
Déjà Vu: The Importance of Time and Causality in Recommender SystemsJustin Basilico
Talk at RecSys 2017 in Como, Italy on 2017-08-29.
Abstract:
Time plays a key role in recommendation. Handling it properly is especially critical when using recommender systems in real-world applications, which may not be as clear when doing research with historical data. In this talk, we will discuss some of the important challenges of handling time in recommendation algorithms at Netflix. We will focus on challenges related to how our users, items, and systems all change over time. We will then discuss some strategies for tackling these challenges, which revolves around proper treatment of causality in our systems.
Recommendation systems today are widely used across many applications such as in multimedia content platforms, social networks, and ecommerce, to provide suggestions to users that are most likely to fulfill their needs, thereby improving the user experience. Academic research, to date, largely focuses on the performance of recommendation models in terms of ranking quality or accuracy measures, which often don’t directly translate into improvements in the real-world. In this talk, we present some of the most interesting challenges that we face in the personalization efforts at Netflix. The goal of this talk is to sunshine challenging research problems in industrial recommendation systems and start a conversation about exciting areas of future research.
Deeper Things: How Netflix Leverages Deep Learning in Recommendations and Se...Sudeep Das, Ph.D.
In this talk, we will provide an overview of Deep Learning methods applied to personalization and search at Netflix. We will set the stage by describing the unique challenges faced at Netflix in the areas of recommendations and information retrieval. Then we will delve into how we leverage a blend of traditional algorithms and emergent deep learning methods and new types of embeddings, especially hyperbolic space embeddings, to address these challenges.
A Multi-Armed Bandit Framework For Recommendations at NetflixJaya Kawale
In this talk, we present a general multi-armed bandit framework for recommendations on the Netflix homepage. We present two example case studies using MABs at Netflix - a) Artwork Personalization to recommend personalized visuals for each of our members for the different titles and b) Billboard recommendation to recommend the right title to be watched on the Billboard.
Talk with Yves Raimond at the GPU Tech Conference on Marth 28, 2018 in San Jose, CA.
Abstract:
In this talk, we will survey how Deep Learning methods can be applied to personalization and recommendations. We will cover why standard Deep Learning approaches don't perform better than typical collaborative filtering techniques. Then we will survey we will go over recently published research at the intersection of Deep Learning and recommender systems, looking at how they integrate new types of data, explore new models, or change the recommendation problem statement. We will also highlight some of the ways that neural networks are used at Netflix and how we can use GPUs to train recommender systems. Finally, we will highlight promising new directions in this space.
Past, present, and future of Recommender Systems: an industry perspectiveXavier Amatriain
Keynote for the ACM Intelligent User Interface conference in 2016 in Sonoma, CA. I start with the past by talking about the Recommender Problem, and the Netflix Prize. Then I go into the Present and the Future by talking about approaches that go beyond rating prediction and ranking and by finishing with some of the most important lessons learned over the years. Throughout my talk I put special emphasis on the relation between algorithms and the User Interface.
Recommender Systems represent one of the most widespread and impactful applications of predictive machine learning models.
Amazon, YouTube, Netflix, Facebook and many other companies generate an important fraction of their revenues thanks to their ability to model and accurately predict users ratings and preferences.
In this presentation we cover the following points:
→ introduction to recommender systems
→ working with explicit vs implicit feedback
→ content-based vs collaborative filtering approaches
→ user-based and item-item methods
→ machine learning and deep learning models
→ pros & cons of the methods: scalability, accuracy, explainability
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.
Presentation at the Netflix Expo session at RecSys 2020 virtual conference on 2020-09-24. It provides an overview of recommendation and personalization at Netflix and then highlights some of the things we’ve been working on as well as some important open research questions in the field of recommendations.
RecSys 2020 A Human Perspective on Algorithmic Similarity Schendel 9-2020Zachary Schendel
In the Netflix user interface (UI), when a row or UI element is named “Because you Watched...”, “More Like This”, or “Because you added to your list”, the overarching goal is to recommend a movie or TV show that a member might like based on the fact that they took a meaningful action on a source item. We have employed similar recommendations in many UI elements: on the homepage as a row of recommendations, after you click into a title, or as a piece of information about why a member should watch a title.
From an algorithmic perspective, there are many ways to define a “successful” similar recommendation. We sought to broaden that definition of success. To this end, the Consumer Insights team recently completed a suite of research projects to explore the intricacies of member perceptions of similar recommendations. The Netflix Consumer Insights team employs qualitative (e.g., in-depth interviews) and quantitative (e.g., surveys) research methods, interfacing directly with Netflix members to uncover pain points that can inspire new product innovation. The research concluded that, while the typical member believes movies are broadly similar when they share a common genre or theme, similarity is more complex, nuanced, and personal than we might have imagined. The vernacular we use in the UI implies that there should be at least some kind of relationship between the source item and the recommendations that follow. Many of our similar recommendations felt “out of place”, mostly because the relationship between the source item and the recommendation was unclear or absent. When similar recommendations tell a completely misleading, incorrect, or confusing story, member trust can be broken.
We will structure the presentation around three new insights that our research found to have an influence on the perception of similarity in the context of Netflix as well as the research methods used to uncover those insights. First, the reason a member loves a given movie will vary. For example, do you want to watch other baseball movies like Field of Dreams, or would you prefer other romances like Field of Dreams? Second, members are more or less flexible about how similar a recommendation actually needs to be depending on the properties of and their interactions with the canvas containing the recommendation. For example, a Because You Watched row on the homepage implies vaguer similarity while a More Like This gallery behind a click into the source item implies stricter similarity. Finally, even when we held the UI element constant, we found that similar recommendations are only valuable in some contexts. After finishing a movie, a member might prefer a similar recommendation one day and a change of pace the next. Research methods discussed will include Inverse Multi-Dimensional Scaling [1], survey experimentation, and ways to apply qualitative research to improve algorithmic recommendations.
Building a Recommender systems by Vivek Murugesan - Technical Architect at Cr...Rajasekar Nonburaj
The topic presented at the "Datascience Chennai June Meetup"
"Building a Recommender systems" by Vivek Murugesan - Technical Architect at Crayon Data. Check more at https://www.meetup.com/datasciencechn
Recommendation algorithms and their variations such as ranking are the most common way for machine learning to find its way into a product where it is not the main focus. In this talk we’ll dig into the subtleties of making recommendation algorithms a seamless and integral part of your UX (goal: it should completely fade into the background. The user should not be aware she’s interacting with any kind of machine learning, it should just feel right, perhaps smart or even a tad like cheating); how to solve the cold start problem (and having little training data in general); and how to effectively collect feedback data. I’ll be drawing from my experiences building Metabase, an open source analytics/BI tool, where we extensively use recommendations and ranking to keep users in a state of flow when exploring data; to help with discoverability; and as a way to gently teach analysis and visualization best practices; all on the way towards building an AI data scientist.
Modern Perspectives on Recommender Systems and their Applications in MendeleyKris Jack
Presentation given for one of Pearson's Data Research teams. It motivates the use of recommender systems, describes common approaches to building and evaluating them and gives examples of how they are used in Mendeley. Thanks to Maya Hristakeva for creating some of the slides.
Co-Creation methods for interactive computer systems design are now widely accepted as part of the methodological repertoire in any software devel-opment process. As the community is becoming more aware of the fact that soft-ware is driven by complex, artificially intelligent algorithms, the question arises what “Co-Creation of Algorithms” in the sense of end users explicitly shaping the parameters of algorithms could mean, and how it would work. Algorithms are not tangible like tool features and effects are harder to be explained or under-stood, especially in early design phases without a software prototype. Therefore, we propose a Simulation-based Co-Creation method that allows TEL researchers to collaboratively design algorithms with end users by creating user stories and personas, modelling assumptions and discussing simulated effects. The method extends the build & evaluate loop of co-design iterations, even when the learning technology for the algorithm is not ready. Our proposal is a methodological idea for discussion in the EC-TEL community, yet to be applied in a practice.
Data/AI driven product development: from video streaming to telehealthXavier Amatriain
Healthcare is different from any other application domain, or is it not? While it is true that there are specific aspects, such as high stakes decisions and a complex regulatory framework, that make healthcare somewhat different, it is also the case that many of the lessons learned from building data-driven products in other domains translate remarcably well into healthcare. This is particularly so because healthcare is also a user facing domain, where users can be both patients or healthcare professionals. Given that data has shown to improve user experience while ensuring quality and scalability, few would argue that healthcare cannot benefit from being much more data-driven than it has traditionally been.
In this talk, I described how this experience building impactful data and AI solutions into user facing products for decades can be leveraged to revolutionize telehealth. At Curai, we combine approaches such as state-of-the-art large language models with expert systems in areas such as NLP, vision, and automated diagnosis to augment and scale doctors, and to improve user experience and healthcare outcomes. We will see some of those applications while analyzing the role of data and ML algorithms in making them possible.
AI-driven product innovation: from Recommender Systems to COVID-19Xavier Amatriain
AI/Machine Learning has become an integral part of many household tech products, from Netflix to our phones. In this talk I will draw from my experience driving AI teams at some of those companies to showcase how AI can positively impact products as different as Netflix and Curai, an online telehealth service.
With half of the world’s population lacking access to healthcare services, and 30% of the adult population in the US having inadequate health insurance coverage to get even basic access to services, it should have been clear that a pandemic like COVID-19 would strain the global healthcare system way over its maximum capacity. In this context, many are trying to embrace and encourage the use of telehealth as a way to provide safe and convenient access to care. However, telehealth in itself can not scale to cover all our needs unless we improve scalability and efficiency through AI and automation.
In this talk, we will describe how our work on combining latest AI advances with medical experts and online access has the potential to change the landscape in healthcare access and provide 24/7 quality healthcare. Combining areas such as NLP, vision, and automatic diagnosis we can augment and scale doctors. We will describe our work on combining expert systems with deep learning to build state-of-the-art medical diagnostic models that are also able to model the unknowns. We will also show our work on using language models for medical Q&A . More importantly, we will describe how those approaches have been used to address the urgent and immediate needs of the current pandemic.
AI for COVID-19: An online virtual care approachXavier Amatriain
Slides for the talk I gave at the AI and COVID-19 virtual conference at Stanford. Video here: https://hai.stanford.edu/events/covid-19-and-ai-virtual-conference/video-archive
From one to zero: Going smaller as a growth strategyXavier Amatriain
This talk was designed for Engineering managers. Having been at companies of all sizes, I recommend managers who want to grow to go smaller. At the same time I reflect on what are the important things that remain constant regardless the size and context and which ones don't.
Deep learning has accomplished impressive feats in areas such as voice recognition, image processing, and natural language processing. Deep learning enthusiasts have rushed to predict that this family of algorithms is likely to take over most other applications in the near future. This focus on deep architectures seems to have cast a shadow over more “traditional” machine learning and data science approaches, leaving researchers and practitioners alike wondering whether there is any point in investing in feature engineering or simpler models.
In this talk, I will go over what deep learning can and cannot do for you, both now and in the near future. I will also describe how different approaches will continue to be needed, and why their demand will likely grow despite the rise of deep learning. I will support my claims not only by looking at recent publications, but also by using practical examples drawn from my experience at companies at the forefront of machine learning applications, such as Quora.
Lean DevOps - Lessons Learned from Innovation-driven CompaniesXavier Amatriain
Presentation I gave at the IEEE Devops Symposium in the Computer History Museum, Mountain View. I describe the CASSSH model for Devops as well as lessons learned in innovation-driven companies.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...DanBrown980551
Do you want to learn how to model and simulate an electrical network from scratch in under an hour?
Then welcome to this PowSyBl workshop, hosted by Rte, the French Transmission System Operator (TSO)!
During the webinar, you will discover the PowSyBl ecosystem as well as handle and study an electrical network through an interactive Python notebook.
PowSyBl is an open source project hosted by LF Energy, which offers a comprehensive set of features for electrical grid modelling and simulation. Among other advanced features, PowSyBl provides:
- A fully editable and extendable library for grid component modelling;
- Visualization tools to display your network;
- Grid simulation tools, such as power flows, security analyses (with or without remedial actions) and sensitivity analyses;
The framework is mostly written in Java, with a Python binding so that Python developers can access PowSyBl functionalities as well.
What you will learn during the webinar:
- For beginners: discover PowSyBl's functionalities through a quick general presentation and the notebook, without needing any expert coding skills;
- For advanced developers: master the skills to efficiently apply PowSyBl functionalities to your real-world scenarios.
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Clients don’t know what they don’t know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clients’ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
UiPath Test Automation using UiPath Test Suite series, part 4DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 4. In this session, we will cover Test Manager overview along with SAP heatmap.
The UiPath Test Manager overview with SAP heatmap webinar offers a concise yet comprehensive exploration of the role of a Test Manager within SAP environments, coupled with the utilization of heatmaps for effective testing strategies.
Participants will gain insights into the responsibilities, challenges, and best practices associated with test management in SAP projects. Additionally, the webinar delves into the significance of heatmaps as a visual aid for identifying testing priorities, areas of risk, and resource allocation within SAP landscapes. Through this session, attendees can expect to enhance their understanding of test management principles while learning practical approaches to optimize testing processes in SAP environments using heatmap visualization techniques
What will you get from this session?
1. Insights into SAP testing best practices
2. Heatmap utilization for testing
3. Optimization of testing processes
4. Demo
Topics covered:
Execution from the test manager
Orchestrator execution result
Defect reporting
SAP heatmap example with demo
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
As AI technology is pushing into IT I was wondering myself, as an “infrastructure container kubernetes guy”, how get this fancy AI technology get managed from an infrastructure operational view? Is it possible to apply our lovely cloud native principals as well? What benefit’s both technologies could bring to each other?
Let me take this questions and provide you a short journey through existing deployment models and use cases for AI software. On practical examples, we discuss what cloud/on-premise strategy we may need for applying it to our own infrastructure to get it to work from an enterprise perspective. I want to give an overview about infrastructure requirements and technologies, what could be beneficial or limiting your AI use cases in an enterprise environment. An interactive Demo will give you some insides, what approaches I got already working for real.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. What’s changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
Neuro-symbolic is not enough, we need neuro-*semantic*Frank van Harmelen
Neuro-symbolic (NeSy) AI is on the rise. However, simply machine learning on just any symbolic structure is not sufficient to really harvest the gains of NeSy. These will only be gained when the symbolic structures have an actual semantics. I give an operational definition of semantics as “predictable inference”.
All of this illustrated with link prediction over knowledge graphs, but the argument is general.
Key Trends Shaping the Future of Infrastructure.pdfCheryl Hung
Keynote at DIGIT West Expo, Glasgow on 29 May 2024.
Cheryl Hung, ochery.com
Sr Director, Infrastructure Ecosystem, Arm.
The key trends across hardware, cloud and open-source; exploring how these areas are likely to mature and develop over the short and long-term, and then considering how organisations can position themselves to adapt and thrive.
2. 1. The Traditional Recommender Problem
2. The Netflix Prize
3. Beyond Rating Prediction
4. Lessons Learned
5. A Recsys Architectural Blueprint
6. Building a state-of-the-art recommender system in practice
7. Hands-on tutorial
8. Future research Directions
9. Conclusions
10. Some references
Outline
4. The “Recommender problem”
● Traditional definition: Estimate a utility function that
automatically predicts how much a user will like an
item.
● Based on:
o Past behavior
o Relations to other users
o Item similarity
o Context
o …
5. Recommendation as data mining
The core of the Recommendation
Engine can be assimilated to a
general data mining problem
(Amatriain et al. Data Mining Methods for Recommender
Systems in Recommender Systems Handbook)
6. Data Mining + all those other things
● User Interface
● System requirements (efficiency, scalability, privacy....)
● Serendipity
● Diversity
● Awareness
● Explanations
● …
7. ● Unsought finding
● Don't recommend items the user already knows or
would have found anyway.
● Expand the user's taste into neighboring areas by
improving the obvious
● Serendipity ~ Explore/exploit tradeoff
Serendipity
10. What works
● Depends on the domain and particular problem
● However, in the general case it has been demonstrated
that the best isolated approach is CF.
o Other approaches can be hybridized to improve results in specific
cases (cold-start problem...)
● What matters:
o Data preprocessing: outlier removal, denoising, removal of global
effects (e.g. individual user's average)
o “Smart” dimensionality reduction using MF
o Combining methods through ensembles
12. What we were interested in:
▪ High quality recommendations
Proxy question:
▪ Accuracy in predicted rating
▪ Improve by 10% = $1million!
13. 2007 Progress Prize
▪ Top 2 algorithms
▪ SVD - Prize RMSE: 0.8914
▪ RBM - Prize RMSE: 0.8990
▪ Linear blend Prize RMSE: 0.88
▪ Currently in use as part of Netflix’ rating prediction
component
▪ Limitations
▪ Designed for 100M ratings, not XB ratings
▪ Not adaptable as users add ratings
▪ Performance issues
14. What about the final prize ensembles?
● Offline studies showed they were too computationally
intensive to scale
● Expected improvement not worth engineering effort
● Plus…. Focus had already shifted to other issues that had
more impact than rating prediction.
19. Ranking
● Most recommendations are presented in a sorted list
● Recommendation can be understood as a ranking problem
● Popularity is the obvious baseline
● What about rating predictions?
20. Ranking by ratings
4.7 4.6 4.5 4.5 4.5 4.5 4.5 4.5 4.5 4.5
Niche titles
High average ratings… by those who would watch it
24. Learning to rank
● Machine learning problem: goal is to construct ranking
model from training data
● Training data can be a partial order or binary judgments
(relevant/not relevant).
● Resulting order of the items typically induced from a
numerical score
● Learning to rank is a key element for personalization
● You can treat the problem as a standard supervised
classification problem
25. Learning to rank - Metrics
● Quality of ranking measured using metrics as
o Normalized Discounted Cumulative Gain
o Mean Reciprocal Rank (MRR)
o Fraction of Concordant Pairs (FCP)
o Others…
● But, it is hard to optimize machine-learned models directly
on these measures (e.g. non-differentiable)
● Recent research on models that directly optimize ranking
measures
26. Goal: Present most interesting stories for a user at a given time
Interesting = topical relevance +
social relevance + timeliness
Stories = questions + answers
ML: Personalized learning-to-rank approach
Relevance-ordered vs time-ordered = big gains in engagement
28. ● Displayed in
many different
contexts
○ In response to
user
actions/context
(search, queue
add…)
○ More like… rows
Similars
29. ● Given interest in question A (source) what other
questions will be interesting?
● Not only about similarity, but also “interestingness”
● Features such as:
○ Textual
○ Co-visit
○ Topics
○ …
● Important for logged-out use case
31. Example of graph-based similarity: SimRank
● SimRank (Jeh & Widom, 02): “two objects are
similar if they are referenced by similar objects.”
32. Similarity ensembles
● Similarity can refer to different dimensions
○ Similar in metadata/tags
○ Similar in user play behavior
○ Similar in user rating behavior
○ …
● Combine them using an ensemble
○ Weights are learned using regression over existing response
○ Or… some MAB explore/exploit approach
● The final concept of “similarity” responds to what users vote as
similar
34. Recommendations - Users
● Goal: Recommend new users to follow
● Based on:
○ Other users followed
○ Topics followed
○ User interactions
○ User-related features
○ ...
35. User Trust/Expertise Inference
● Goal: Infer user’s trustworthiness in relation
to a given topic
● We take into account:
○ Answers written on topic
○ Upvotes/downvotes received
○ Endorsements
○ ...
● Trust/expertise propagates through the network
● Must be taken into account by other algorithms
36. Social and Trust-based recommenders
● A social recommender system recommends items that are “popular”
in the social proximity of the user.
● Social proximity = trust (can also be topic-specific)
● Given two individuals - the source (node A) and sink (node C) -
derive how much the source should trust the sink.
● Algorithms
o Advogato (Levien)
o Appleseed (Ziegler and Lausen)
o MoleTrust (Massa and Avesani)
o TidalTrust (Golbeck)
37. Other ways to use Social
● Social connections can be used in combination with
other approaches
● In particular, “friendships” can be fed into collaborative
filtering methods in different ways
○ replace or modify user-user “similarity” by using social network
information
○ use social connection as a part of the ML objective function as
regularizer
○ ...
39. ● One of the key issues when building any kind of
personalization algorithm is how to trade off:
○ Exploitation: Cashing in on what we know about the user right
now
○ Exploration: Using the interaction as an opportunity to learn
more about the user
● We need to have informed and optimal strategies to
drive that tradeoff
○ Solution: pick a reasonable set of candidates and show users
only “enough” to gather information on them
Explore/Exploit
40. ● Given possible strategies/candidates (slot machines) pick the arm that has
the maximum potential of being good (minimize regret)
● Naive strategy: ε-greedy
○ Explore with a small probability ε (e.g. 5%) -> choose an arm at random
○ Exploit with a high probability (1 - ε ) (e.g. 95%) -> choose the best-known arm so far
● Translation to recommender systems
○ Choose an arm = choose an item/choose an algorithm (MAB testing)
● Thompson Sampling
Given a posterior distribution, sample on each iteration and choose the action that
maximizes the expected reward
Multi-armed Bandits
45. User Attention Modeling
From “Modeling User Attention and
Interaction on the Web” 2014 - PhD Thesis by Dmitry Lagun (Emory U.)
46. vs.Accurate Diverse
vs.Discovery Continuation
vs.Depth Coverage
vs.Freshness Stability
vs.Recommendations Tasks
Page Composition
● To put things together we need to combine different elements
o Navigational/Attention Model
o Personalized Relevance Model
o Diversity Model
50. Tensor Factorization
Where:
● We can use a simple squared error loss function:
● Or the absolute error loss
● The loss function over all users becomes
51. Factorization Machines
• Generalization of regularized matrix (and tensor)
factorization approaches combined with linear (or
logistic) regression
• Problem: Each new adaptation of matrix or tensor
factorization requires deriving new learning algorithms
– Hard to adapt to new domains and add data sources
– Hard to advance the learning algorithms across approaches
– Hard to incorporate non-categorical variables
52. • Approach: Treat input as a real-valued feature vector
– Model both linear and pair-wise interaction of k features (i.e. polynomial regression)
– Traditional machine learning will overfit
– Factor pairwise interactions between features
– Reduced dimensionality of interactions promote generalization
– Different matrix factorizations become different feature representations
– Tensors: Additional higher-order interactions
• Combines “generality of machine learning/regression
with quality of factorization models”
Factorization Machines
53. • Each feature gets a weight value and a factor vector
– O(dk) parameters
• Model equation:
O(d2
)
O(kd)
Factorization Machines
54. From Rendle (2012) KDD Tutorial
▪ Two categorical variables (u, i) encoded as real values:
▪ FM becomes identical to MF with biases:
Factorization Machines
55. ▪ Makes it easy to add a time signal
▪ Equivalent equation:
From Rendle (2012) KDD Tutorial
Factorization Machines
56. • L2 regularized
– Regression: Optimize RMSE
– Classification: Optimize logistic log-likelihood
– Ranking: Optimize scores
• Can be trained using:
– SGD
– Adaptive SGD
– ALS
– MCMC
Gradient:
Least squares SGD:
Factorization Machines (Rendle, 2010)
57. • Learning parameters:
– Number of factors
– Iterations
– Initialization scale
– Regularization (SGD, ALS) – Multiple
– Step size (SGD, A-SGD)
– MCMC removes the need to set those
hyperparameters
Factorization Machines (Rendle, 2010)
61. Implicit vs. Explicit
● Many have acknowledged
that implicit feedback is more
useful
● Is implicit feedback really always
more useful?
● If so, why?
62. ● Implicit data is (usually):
○ More dense, and available for all users
○ Better representative of user behavior vs.
user reflection
○ More related to final objective function
○ Better correlated with AB test results
● E.g. Rating vs watching
Implicit vs. Explicit
63. ● However
○ It is not always the case that
direct implicit feedback correlates
well with long-term retention
○ E.g. clickbait
● Solution:
○ Combine different forms of
implicit + explicit to better represent
long-term goal
Implicit vs. Explicit
65. ● Training a simple binary classifier for
good/bad answer
○ Defining positive and negative labels ->
Non-trivial task
○ Is this a positive or a negative?
■ funny uninformative answer with many
upvotes
■ short uninformative answer by a well-known
expert in the field
■ very long informative answer that nobody
reads/upvotes
■ informative answer with grammar/spelling
mistakes
■ ...
67. Training a model
● Model will learn according to:
○ Training data (e.g. implicit and explicit)
○ Target function (e.g. probability of user reading an answer)
○ Metric (e.g. precision vs. recall)
● Example 1 (made up):
○ Optimize probability of a user going to the cinema to
watch a movie and rate it “highly” by using purchase history
and previous ratings. Use NDCG of the ranking as final
metric using only movies rated 4 or higher as positives.
68. Example 2 - Quora’s feed
● Training data = implicit + explicit
● Target function: Value of showing a
story to a
user ~ weighted sum of actions:
v = ∑a
va
1{ya
= 1}
○ predict probabilities for each action, then compute expected
value: v_pred = E[ V | x ] = ∑a
va
p(a | x)
● Metric: any ranking metric
73. ● User can only click on what you decide to show
○ But, what you decide to show is the result of what your model
predicted is good
● Simply treating things you show as negatives is not
likely to work
● Better options
○ Correcting for the probability a user will click on a position ->
Attention models
○ Explore/exploit approaches such as MAB
74. 6. If You Have to Pick one single
approach, Matrix factorization is your
best bet
75. Matrix Factorization
● MF can be interpreted as
○ Unsupervised:
■ Dimensionality Reduction a la PCA
■ Clustering (e.g. NMF)
○ Supervised:
■ Labeled targets ~ regression
● Very useful variations of MF
○ BPR, ALS, SVD++
○ Tensor Factorization, Factorization Machines
● However...
77. Ensembles
● Netflix Prize was won by an ensemble
○ Initially Bellkor was using GDBTs
○ BigChaos introduced ANN-based ensemble
● Most practical applications of ML run an
ensemble
○ Why wouldn’t you?
○ At least as good as the best of your methods
○ Can combine different approaches (e.g. CF and content-based)
○ Can use different models at the ensemble layer: LR, GDBTs, RFs,
ANNs...
78. Ensembles & Feature Engineering
● Ensembles are the way to turn any model
into a feature!
● E.g. Don’t know if the way to go is to use Factorization
Machines, Tensor Factorization, or RNNs?
○ Treat each model as a “feature”
○ Feed them into an ensemble
80. Need for feature engineering
In many cases an understanding of the domain will lead to
optimal results.
81. Feature Engineering Example - Quora Answer Ranking
What is a good Quora answer?
• truthful
• reusable
• provides explanation
• well formatted
• ...
82. Feature Engineering Example - Quora Answer Ranking
How are those dimensions translated
into features?
• Features that relate to the answer
quality itself
• Interaction features
(upvotes/downvotes, clicks,
comments…)
• User features (e.g. expertise in topic)
84. 9. Why you should care about
answering questions
(about your recsys)
85. Model debuggability
● Value of a model = value it brings to the product
● Product owners/stakeholders have expectations on
the product
● It is important to answer questions to why did
something fail
● Model debuggability is so important it can
determine:
○ Particular model to use
○ Features to rely on
○ Implementation of tools
90. Distributing Recommender Systems
● Most of what people do in practice can fit
into a multi-core machine
○ As long as you use:
■ Smart data sampling
■ Offline schemes
■ Efficient parallel code
● (… but not Deep ANNs)
● Do you care about costs? How about latencies or
system complexity/debuggability?
91.
92. 12. The UI is the only communication
channel with what matters the most:
Users
93. UI->Algorithm->UI
● The UI generates the user feedback
that we will input into the algorithms
● The UI is also where the results of
our algorithms will be shown
● A change in the UI might require a
change in algorithms and viceversa
100. Training, testing, metrics
● As mentioned in the lessons, this is essential
● Choose implicit data and metrics that connect to your
business goal
● Sample negatives smartly
● Select validation and test set carefully (e.g. avoid time
traveling)
108. AB Test
● So, you have your first implementation
○ Have tuned hyperparameters to optimize offline
metric
○ How do you know this is working?
● Run AB Test!
○ Make sure offline metric (somewhat) correlates to
online effect
109. AB Test
● Ideally, you would run several AB tests with different
offline metrics and data sampling strategies
111. Ensemble
● Now, it’s time to turn the model into a signal
● Brainstorm about some simple potential features that
you could combine with implicit MF
○ E.g. user tenure, average rating for the item, price
of the item…
● Add to MF through an ensemble
112. Ensemble
● What model to use at the ensemble layer?
○ Always favor most simple -> L2-regularized Logistic
Regression
○ Eventually introduce models that can benefit from non-linear
effects and many features -> Gradient Boosted Decision
Trees
○ Explore Learning-to-rank models -> LambdaRank
116. Exercise
● Train an ALS implicit matrix factorization
recommender system
● Do basic feature engineering to add other features
● Add the mix to an XGBoost-based ensemble
● This is very close to what you could be using in
real-life (minus scalability/performance issues)
118. 1. Indirect feedback
2. Value-awareness
3. Full-page optimization
4. Personalizing the how
Others
● Intent/session awareness
● Interactive recommendations
● Context awareness
● Deep learning for recommendations
● Conversational interfaces/bots for
recommendations
● …
Many interesting future directions
119. Challenges
User can only click on what you show
But, what you show is the result of what your
model predicted is good
No counterfactuals
Implicit data has no real “negatives”
Potential solutions
Attention models
Context is also indirect/implicit feedback
Explore/exploit approaches and learning across
time
...
click
upvote
downvote
expand
share
Indirect Feedback
120. ● Recsys optimize for probability of action
● Not all clicks/actions have the same “reward”
○ Different margin in ecommerce
○ Different “quality” of content
○ Long-term retention vs. short-term clicks (clickbait)
○ …
● In Quora, the value of showing a story to a user is approximated by weighted sum of actions:
● v = ∑a
va
1{ya
= 1}
● Extreme application of value-aware recommendations: suggest items to create that have the
highest value
Netflix: Which shows to produce or license
Quora: Answers and questions that are not in the service
Value-aware recommendations
121. ● Recommendations are rarely displayed in isolation
○ Rankings are combined with many other elements to make a
page
● Want to optimize the whole page
● Jointly solving for set of items and their placement
● While incorporating
○ Diversity, freshness, exploration
○ Depth and coverage of the item set
○ Non-recommendation elements (navigation, editorial, etc.)
● Needs work hand-in-hand with the UX
Full-page optimization
122. ● Algorithm level: Ideal balance of diversity, novelty, popularity, freshness, etc. may depend
on the person
● Display level: How you present items or explain recommendations can also be personalized
○ Select the best information and presentation for a user to quickly decide whether or
not they want an item
● Interaction level: Balancing the needs of lean-back users and power users
Personalizing how we recommend (not just what)
125. ● Recommendation is about much more than just
predicting a rating
● All forms of recommendation require of a tight
connection with the UI
○ Capture the right kind of feedback
■ Explicit/implicit feedback
■ Correct for presentation bias
■ ...
○ Present the recommendations correctly
■ Explanations
■ Diversity
■ Exploration/Exploitation
■ ….
Conclusions
126. ● For the algorithm:
○ Use implicit feedback if possible
○ Build a Matrix Factorization recommender system
○ Think of using ensembles and turning your problem into a
feature engineering problem
○ Always think of the metric you are optimizing to and the data
you are using
● Whatever you do in the lab, you should trust your AB tests
Conclusions
128. ● 4 hour video of my lecture at MLSS at CMU (Youtube)
● “Recommender systems in industry: A netflix case study” (X. Amatriain, J. Basilico) in
Recommender System Handbook
● “Past, Present, and Future of Recommender Systems: An Industry Perspective” (X. Amatriain,
J. Basilico. Recsys 2016)
● “Mining large streams of user data for personalized recommendations” (X. Amatriain) - ACM
SigKDD Explorations Newsletter
● “Big & personal: data and models behind netflix recommendations” (X. Amatriain) - ACM
Workshop on Big Data
● Visit my slideshare page: https://www.slideshare.net/xamat
Other resources