Podcast658 Videos


Assessing Data Quality at Shopify with Wendy Foster – #592

Today we’re back with another installment of our Data-Centric AI series, joined by Wendy Foster, a director of engineering & data science at Shopify. In our conversation with Wendy, we explore the differences between data-centric and model-centric approaches and how they manifest at Shopify, including on her team, which is responsible for utilizing merchant and […]

Transformers for Tabular Data at Capital One with Bayan Bruss – #591

Today we’re joined by Bayan Bruss, a Sr. director of applied ML research at Capital One. In our conversation with Bayan, we dig into his work in applying various deep learning techniques to tabular data, including taking advancements made in other areas like graph CNNs and other traditional graph mining algorithms and applying them to […]

Machine Learning in Production: What to do after you’ve trained the models?

Search is the first line of defense when it comes to a customer looking for what to buy on an e-commerce website. If a customer can’t find what they are looking for you are likely to lose the customer or worse never acquire them. In addition to being critical to the E-Commerce experience, providing personalized […]

Productionizing Machine Learning Models at Scale with Kubernetes

Productionizing machine learning models in an organization is a difficult challenge for several reasons. From a technical perspective, it requires tooling to handle tasks such as model deployment, monitoring, and retraining. Talent-wise, these tasks require practitioners to possess technical skills in software engineering and DevOps. Coupled with a rapidly changing landscape and shortage of established […]

Team Teardown: Organizing and Supporting ML at Airbnb

We usually hear conference presentations from a singular perspective–that of one of an organization’s data scientists, data engineers, platform engineers, or ML/AI leaders. In this “Team Teardown” panel we turn this model on its head and speak with several members of an organization’s team to explore the complex relationships between platform consumers (i.e. data scientists) […]

Chaos and Pain in Machine Learning, and the ‘DevOps for ML Manifesto'

Most AI/ML projects start shipping models into production, where they can deliver business value, using the no-process process. That is, people just do their best by creating an ad-hoc process with familiar tools. This works for tiny teams at first, but as the team grows you’ll discover significant chaos and pain trying to operationalize AI. […]

Top Trends in Enterprise Machine Learning for 2021

In the past 12 months, there have been myriad developments in the field of AI/ML. Not only have we seen shifts in tooling, security, and governance needs for organizations, but we’ve also witnessed massive changes in the field due to the economic impacts of COVID-19. Every year, Algorithmia surveys business leaders and practitioners across the […]

Live from TWIMLcon! Use-Case Driven ML Platforms

Fran leads a team of 100 data scientists building use-case driven data science platforms at Uber. Her teams’ platforms build on top of the low-level capabilities offered by Uber’s Michelangelo to allow data scientists to rapidly deliver higher-level applications as varied as forecasting, anomaly detection, NLP/conversational AI, experimentation, segmentation, and more. Fran will join Sam […]

Machine Learning is Going Real-Time

This talk covers the state of real-time machine learning in production and the staggering differences in its adoption across Internet companies in the US and China. There are two levels of real-time machine learning. Level 1: Your ML system makes predictions in real-time (online predictions). Level 2: Your system can incorporate new data and update […]

Why is Production ML so Hard?

Industrial-grade ML requires transformation in almost every part of an organization, and as a result, production ML hurdles are often organization-wide hurdles. Teams face challenges ranging from political issues and data product/market fit to limitations with software tools and technology platforms. This talk proposes solutions aimed at tackling these challenges including approaches to project and […]

Operationalizing Responsible AI

This panel explores how organizations can go beyond a general desire to be ethical in their use of ML/AI to building transparency, accountability, fairness, anti-bias, etc. into their ML pipelines and practices in a systematic and sustainable way. YouTube Source for this AI Video

Building the Business case for ML Platforms

ML projects are expensive. For business leaders considering where the next incremental investment in ML goes, there is a natural tension between investing in front line ML projects and the platforms, tools and teams that can accelerate these projects and help ensure their success. In this session we discuss how to explain the value of […]

Exploring Tradeoffs in Experiment Management as part of AI Platforms

As teams scale their AI platforms, they must decide which capabilities to build versus buy. Whether balancing standards and flexibility or differentiation and scale, there is a playbook teams should run to make these decisions effectively. Join SigOpt Co-Founder & CEO Scott Clark’s session at TWIMLcon to learn how AI leaders weigh these tradeoffs. During […]

Keynote Interview: Solmaz Shahalizadeh

Solmaz is the Vice President of Data Science & Engineering at Shopify. During her time at the company, she implemented the company’s first ML products, built their financial data warehouse, led multiple cross-functional teams, and played a critical role in their IPO. In this keynote interview, Sam and Solmaz will discuss how she’s helped the […]

SurveyMonkey's ML Platform Journey

In this talk, we will share how SurveyMonkey was able to extend it’s ML platform in a hybrid cloud. We will also share how we took stock of our strengths and existing investments and built a platform that made sense for us, and our learnings along the way. YouTube Source for this AI Video

Live from TWIMLcon! Operationalizing ML at Scale

What should we takeaway from how web giants and autonomous vehicles are redefining scale and impact for ML platforms? Hussein Mehanna, Head of AI/ML at Cruise, a subsidiary of GM, is in a unique position to answer this question. Prior to joining Cruise, Hussein founded the AI Platforms team at Facebook and then went on […]

End-to-End ML with Cloudera Machine Learning

In this workshop we will explore how Machine Learning on the Cloudera Data Platform enables fast and effective end-to-end machine learning workflows – from the data preparation and pipelines that power the models, to managing the move to production for the models, and finally to how data science teams can enable those machine learning models […]

Embeddings @ Twitter

ML modeling teams at Twitter face a variety of uniquely hard yet fundamentally related machine learning problems. For example, tasks as different as ad serving, abuse detection, and user timeline construction all rely on powerful representations of user and content entities. In addition, because of Twitter’s real-time nature, entity data distributions are constantly in flux, […]

ML Product Experiments at Scale

Today, nearly all data experimentation at Yelp—from products to AI and machine learning—occurs on the custom-built Bunsen platform, with over 700 experiments in total being run at any one time. Bunsen supports the deployment of experiments to large but segmented parts of Yelp’s customer population, and it enables the company’s data scientists to roll back […]

Keynote Interview: Ya Xu

Ya Xu leads the LinkedIn data science practice, consisting of hundreds of researchers distributed across the USA (Sunnyvale, Mountain View, San Francisco, New York), India and Dublin. The team touches every aspect of the organization, helping to inform decisions about new product features, business investments, surfacing economic insights for policy makers, and much more. In […]