The Rendezvous architecture proposed by Ted Dunning and Ellen Friedman in their book on Machine Learning Logistics was a wonderful solution I found for a specific architectural problem I was working on. I was looking for a tried and tested design pattern or architectural pattern that helps me run Challenger and Champion models together in a maintainable and supportable way. The rendezvous architecture was significantly more useful in the big data world because you are dealing with heavy data and large pipelines. The ability to run Challenger and Champion models together on all data is a very genuine need in machine learning, where the model performance can drift over time and where you want to keep improving on the performance of your models to something better always. So, before I delve deeper into this architecture, I would like to clarify some of the jargon I have used above.

In this post, you learn how to create a MLOps project to automate the deployment of an Amazon SageMaker endpoint with multiple production variants for A/B testing. You also deploy a general purpose API and testing infrastructure that includes a multi-armed bandit experiment framework. This testing infrastructure will automatically optimize traffic to the best-performing model over time based on user feedback. Amazon SageMaker MLOps projects are a new capability recently released with Amazon SageMaker Pipelines, the first purpose-built, easy-to-use, continuous integration and continuous delivery (CI/CD) service for ML. The MLOps project template provisions the initial setup required for a complete end-to-end MLOps system, including model building, training, and deployment, and can be customized to support your own organizations requirements.

As the fuel that powers their progressing digital transformation endeavors, organizations wherever are searching for approaches to determine as much insight as could reasonably be expected from their data. The accompanying increased demand for advanced predictive and prescriptive analytics has, thus, prompted a call for more data scientists capable with the most recent artificial intelligence (AI) and machine learning (ML) tools. However, such highly-skilled data scientists are costly and hard to find. Truth be told, they're such a valuable asset, that the phenomenon of the "citizen data scientist" has of late emerged to help close the skills gap. A corresponding role, as opposed to an immediate substitution, citizen data scientists need explicit advanced data science expertise.

Check out the "Model Development, Governance, Operations" sessions at the Strata Data Conference in New York, September 23-26, 2019. Best price ends June 28. Our surveys over the past couple of years have shown growing interest in machine learning (ML) among organizations from diverse industries. A few factors are contributing to this strong interest in implementing ML in products and services. First, the machine learning community has conducted groundbreaking research in many areas of interest to companies, and much of this research has been conducted out in the open via preprints and conference presentations.

Human: What do we want? Human: When do we want it? Computer: When do we want what? Artificial intelligence, especially machine learning, will overhaul big industries, including manufacturing, finance, and healthcare, potentially adding up to $126 billion to the US economy by 2025. June 2017 McKinsey report emphasizes that digital-native firms such as Google and Baidu are betting vast amounts of money on AI – between $20 billion and $30 billion in 2016, including significant M&A activity.

In December, I attended the Amsterdam RiskMinds Conference, which highlighted current priorities of Chief Risk Officers [CROs] and risk professionals. Having reflected over Christmas sherry and Mariah Carey New Year PR disasters, I consider 7 key CRO and risk priorities. The modern Chief Risk Officer was beautifully characterized by Bank of America Merrill Lynch's Geoffrey Greener, a CRO who has travelled from the "dark side" of hedge fund proprietary trading to the comparative "light" of risk management. He services his "much simpler" organization, by being his customer's Chief Risk Officer or "Chief Worrier". An EMEA CRO, pointing to her Financial Conduct Authority personal liability, reiterated the point: "I worry about that 3am call, with a London Whale thing."