In daily fantasy sports, players enter into "contests" where they compete against each other by building teams of athletes that score fantasy points based on what actually occurs in a real-life sports match. For any given sports match, there are a multitude of contests available to players, with substantial variation across 3 main dimensions: entry fee, number of spots, and the prize pool distribution. As player preferences are also quite heterogeneous, contest personalization is an important tool to match players with contests. This paper presents a scalable contest recommendation system, powered by a Wide and Deep Interaction Ranker (WiDIR) at its core. We productionized this system at our company, one of the large fantasy sports platforms with millions of daily contests and millions of players, where online experiments show a marked improvement over other candidate models in terms of recall and other critical business metrics.

A common architecture for distributed applications is to have a frontend component that is exposed to users that interacts with one or more backend components. In this article, we focus on such a distributed architecture, and describe how to test multiple versions of the backend component. In the figure below, the frontend component might be an online store. It relies on a backend model-driven recommendation component to make product suggestions. We are interested in A/B/n testing multiple versions of the backend recommendation component.

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Artificial Intelligence (AI) promises to transform almost every business on the planet. That's why most business leaders are asking themselves what they need to do to successfully deploy AI into production. Many get stuck deciphering which applications are realistic for the business; which will hold up over time as the business changes; and which will put the least strain on their teams.

In 2019, eBay started an initiative to upgrade the monitoring platform to handle increased monitoring signals. We decided to make these upgrades in order to cope with the vast number of queries our system encounters, which in turn revealed several engineering challenges to be overcome. In addition to ingestion, storage and query layer, we decided to upgrade the anomaly detection module because the anomaly detection results that were provided by the previous monitor platform to site SEC/SRE received complaints due to noise and inaccuracy. We revisited all of the use cases that have been used by the SEC/SRE. Business metrics These metrics, including listing number/minute, checkout number/minute and others are critical signals for eBay business.

We've been long working on improving the user experience in UGC products with machine learning. Here are our ten key lessons of implementing recommendation systems in business to build a really good product. The global task of the recommendation system is to select a shortlist of content from a large catalog that is most suitable for a particular user. The content itself can be different -- from products in the online store and articles to banking services. FunCorp product team works with the most interesting kind of content -- we recommend memes.

As a Head of the Data Science team, I am continually challenged with planning for a Machine Learning project and estimating the amount of time and effort necessary to complete it. In order to make an informed decision about each machine learning project, I prepared a template that can assist me with thinking about important elements before planning. To simplify the explanation of the most important points, each machine learning project is divided into three main parts, prototyping, deployment, and monitoring. Each part describes the items that you should consider in planning. The goal of prototyping is to decide if the application is workable and worth deploying.

How often do you test ML models in a Jupyter notebook, get good results, but still cannot convince your boss that the model should be used right away? Or maybe you manage to convince her and put the model in production, but you do not see any impact on business metrics? Luckily for you, there are better ways to test ML models in the real world and to convince everyone (including you) that they add value to the business. In this article you will learn what these evaluation methods are, how to implement them, and when should you use each. We, data scientists and ML engineers, develop and test ML models in our local development environment, for example, a Jupyter notebook.

Doing projects is the one sure way to get your foot in the door of machine learning and data science. Everyone whose serious about getting into the field is aware of this. Consequently, we've now got several people building projects, putting them in their Github portfolio, and sharing them across their various networks, but many of them aren't resonating. A new standard has been set. The fact you can build a model that predicts something and deploy it using some cloud server is impressive, but most people can do that now.

AI practitioners are all too familiar with statistics that over 80% of AI projects fail. A lot has been said about what organizations and data science teams can do to increase this low success rate. Nonetheless, even organizations with established machine learning (ML) practices and high-end AI teams struggle. Some AI initiatives become transformational for the business, while others show little return on investment or never even come to fruition. Of course, this isn't unique to AI projects, but since data science is a fairly new discipline, there's another factor impeding success: not everything can be solved with AI.

This is the list of the 10 most exciting machine learning start-ups you should be following in 2022. Artificial Intelligence has been a hot area of innovation in recent years and ML is one of the major sections of the whole AI arena. ML refers to the development of intelligent algorithms and statistical modeling that allow for further programming improvement without having to code them explicitly. Machine learning can make a predictive analysis app more precise over time, for instance. ML is not without its problems.