Leveraging a Graph-Powered, Real-Time Recommendation Engine to Create Rapid Business Value
by Adam Anthony (GraphSQL)
Deployment of open source recommendation systems has been shown to be an effective way to increase sale conversions on a variety of e-commerce sites. However, there remains a large gap between deploying the core algorithm provided by these systems and delivering an application-quality recommendation system, specifically tailored to address complex and dynamically changing business needs. We will discuss the technical aspects of a graph-based implementation of the recommendation engine and how it facilitates the rapid design and deployment of an efficient real-time recommendation system under a single service. We will briefly discuss the architecture of our graph database system to show how it can efficiently serve a large user base even from a single server shared-memory architecture. Attendees will also learn about graph-based data modeling and how viewing data from this perspective can lead to new types of business insights and applications that are not easily implemented using traditional relational and/or NoSQL platforms. We will conclude with a brief demonstration of a real deployed application UI to demonstrate the ease by which recommendation systems can be implemented and deployed using the engine.
About the Speaker
Dr. Adam Anthony received his Ph.D. in computer science from the University of Maryland Baltimore County in 2009. His expertise is in data clustering, pattern recognition and computing similarity in graphs. He has been working at GraphSQL for three years, one of 7 early members. His primary role is in the direction and development of a flexible, graph-based recommendation engine with an emphasis on real-time recommendation with business-centric optimization. The recommendation engine is currently used in production systems, delivering revenue-boosting recommendation systems with minimal developer effort.
Hypothesis Testing: How to Eliminate Ideas as Soon as Possible
by Roman Zykov (Retail Rocket)
Retail Rocket helps web shoppers make better shopping decisions by providing personalized real-time recommendations through multiple channels with over 100MM unique monthly users and 1000+ retail partners. The rapid improvement of the product is important to win on the high-concurrency market of real-time personalization platforms.
The necessity of introducing constant innovations and improvements of algorithms for recommendation systems requires correct tools and a process of rapid testing of hypotheses. It’s not a secret that 9 out of 10 hypotheses actually do not improve the performance at least. We had the task stated as follows: How to detect and eliminate the idea that doesn’t improve as early as possible, to spend a minimum of resources on that process.
In the report we will talk about:
- How we make our process of hypotheses testing faster.
- One programming language for R&D.
- Enmity and friendship of offline and online metrics.
- Why it is difficult to predict the impact of changing diversity of algorithms.
- What is the benefit of AA/BB online tests.
- Bayesian statistics for the evaluation of online tests.
About the Speaker
Roman Zykov is the Chief Data Scientist at the Retail Rocket. In Retail Rocket is responsible for algorithms of personalized and non-personalized recommendations. Previous to Retail Rocket, Roman was the Head of analytics at the biggest e-commerce companies for almost ten years. He received Ms.Sc. in applied mathematics and physics from the MIPhT in 2004.
Recommending the World’s Knowledge: Application of Recommender Systems at Quora
by Lei Yang (Quora)
At Quora, our mission is to share and grow the world’s knowledge. Recommender systems are at the core of this mission: we need to recommend the most important questions to people most likely to write great answers, and recommend the best answers to people interested in reading them. Driven by the above mission statement, we have a variety of interesting and challenging recommendation problems and a large, rich data set that we can work with to build novel solutions for them. In this talk, we will describe several of these recommendation problems and present our approaches solving them.
About the Speaker
Lei is an engineer manager at Quora, leading the growth and feed ranking team. She also oversees Quora’s machine learning engineer guild, consisting of machine learning experts and software engineers who use machine learning to solve many challenging problems across the product, such as home feed ranking, digest email, user and topic recommendations, related questions, answer ranking, and topic inference. Prior to Quora, Lei grew and managed a number of engineering teams at Google, working on Google Now recommendations, Google+ recommendation and personalizations, and Google Ads Quality. She has years of experience in machine learning and is passionate about its application across different fields, such as recommender systems, data mining, user modeling, and spam detection. Lei holds a Ph.D. degree in Computer Engineering from Northwestern University.
Multicorpus Personalized Recommendations on Google Play: Apps/Games/Books/Movies/Music
by Levent Koc & Cyrus Master (Google)
Google Play is a seamless approach to digital entertainment on all of your devices. It gives you one place to find, enjoy and share your favorite entertainment, from apps to movies, music, books and more, on the web or any device. With more than 1 billion active users in 190+ countries around the world, Play is an important distribution platform for developers to build a global audience. More than 50 billion appshave been downloaded from Google Play.
However, generating personalized recommendations for different kind of content is a complex technical and product problem. Each of Play verticals (apps, games, books, movies, music) has different business goals, metrics to optimize, and user behavior. In this talk, we’ll present an overview of how Play recommendations work across these verticals, how we evaluate our results, and the impact of deep neural networks in improving recommendations.
About the Speakers
Levent Koc is the Area Tech Lead for Personalization on Google Play Apps and Games. Before Google Play, he worked on Display Ads infrastructure. He received his MS degree from University of WisconsinMadison under supervision of Chris Re. During his master studies, he worked on combining the power of database optimization with large scale data management and machine learning.
Cyrus Master is the Area Tech Lead for Search & Discovery on Google Play Digital Content, covering Books, Movies and Music. He joined Google in 2010, and was the architect for Play Music, running both the client and infrastructure engineering teams. He received his Ph.D. in Electrical Engineering from Stanford in 2005 in the field of quantum computation complexity theory, and has worked on both mobile and data synchronization services at Good Technology and Motorola.
Related Pins: Item-to-Item Recommendations at Pinterest
by Stephanie Rogers (Pinterest)
This talk presents Pinterest Related Pins, an item-to-item recommendation system that combines collaborative filtering with content-based ranking to drive a quarter of the total engagement on Pinterest. Signals derived from user curation, the activity of users organizing content, are highly effective when used in conjunction with content based ranking. This will be an in-depth dive into the end-to-end system of Related Pins, a real-world implementation of an item-to-item hybrid recommendation system.
About the Speaker
Stephanie Rogers is currently a software engineer on the discovery team at Pinterest, where she has primarily focused on productionizing and localizing the related pins feature–an item-to-item based recommendation system. Before that she worked in the data engineering space where she integrated Spark into Pinterest’s infrastructure, helped build various data products including the internal analytics tool and an insights tool for trending data, and implemented various models including churn prediction. Prior to Pinterest, Stephanie graduated from UC, Berkeley, where she received a masters in computer science with a focus on machine learning.
