Beyond the Data Warehouse
Learn how organizations like yours have achieved everything they hoped for by adding Snowflake to their data lake architecture. They’re also using Snowflake to augment their machine learning and AI, with benefits such as forecasting, personalization, and anomaly detection. Snowflake customers and our own product managers will discuss common use cases, best practices, and how to best leverage the Snowflake platform for a wider set of situations.
BEYOND THE DATA WAREHOUSE Sessions
ASICS: Predicting an Athlete’s Performance … in the Rain
Is ASICS Runkeeper traffic moving because of a recent release, or is it just a change in the weather? Using shared weather data and over a billion historical runs and other workouts stored in Snowflake, representatives from ASICS attempt to resolve this question. This session describes how ASICS used the Snowflake Python connector and key data science packages in Jupyter to build predictive models and animated geographic data visualizations. This session also explores the impact that weather has on a runner’s race performance and how it can alter or disrupt the habits of individual runners.
Manager of Analytics, Asics
CCI: Lessons Learned Building a New Data Science Platform
Brought to you by SnapLogic
Castleton Commodities International (CCI) is a leader in global commodities trading and investing. Chris Throop, head of CCI’s global data science initiative explains how his team developed a next-generation data science platform from the ground up to improve the company’s data processes and outcomes.
Learn how CCI crafted its data strategy, why it chose to make Snowflake and SnapLogic core elements of the data science platform, and how it successfully deployed that platform.
Managing Director, Global Head of Data Science, Castleton Commodities International
Chesapeake Energy Uses Databricks and Snowflake to Automate Data Pipelines
Brought to you by Databricks
Chesapeake Energy is augmenting real-time IOT streams with machine learning techniques to explore historical IOT data and other reference datasets to enhance operational and exploratory business needs. The result is increased efficiency and reduced operational maintenance in the field. Attend this session and learn how:
- Data engineering and data science workflows became more integrated and time to operationalize data science projects was reduced
- Workflow pattern between Snowflake and S3 were established for data engineering and data science use cases
- MLflow was incorporated to provide a repeatable approach for machine learning
Principal Data Architect, Chesapeake Energy
Devon: From Many Pools to Just One Modern Data Lake
You’ve implemented Snowflake, or you’re about to. What’s next? How about consolidating all of your hard-to-handle, underperforming solutions into a single repository? For years, Devon Energy had an underused data lake, a cumbersome data warehouse, unstable enterprise data sets, and an unmonitored open database. Find out how the natural gas exploration company consolidated this into a modern cloud data lake with Snowflake, Databricks, and Attunity. Devon’s consolidated data analytics platform now provides governed access to all users, and it has streamlined operational support and tooling. In addition it has more closely aligned IT teams with their business counterparts.
Enterprise Data Architect, Devon
How Expedia Uses Snowflake To Supercharge Its Data Lakes
Expedia has multiple data lake silos due to its numerous brand acquisitions. In previous years, Expedia spent a significant amount of energy and resources to standardize these data lakes. The company’s data lake journey has evolved from using Hive to Presto to Spark. Join this session to learn how Expedia uses Snowflake to manage its data lakes and supercharge its data lake queries. And, don’t forget to ask how little effort Expedia spent to migrate its data lake queries to Snowflake.
Database Developer, Expedia
Product Manager, Snowflake
Harmoney: Averting Credit Issues With Predictive Modeling
Harmoney operates as a marketplace lending platform, providing personal loans to consumers in New Zealand and Australia. The company needed to rapidly produce and deploy a predictive model to avert a previously unseen credit issue that had serious implications for the business, which operates in an automated online environment. The combination of Snowflake and DataRobot enables V1 Harmoney to rapidly produce and deploy models, which are executed in near real time. This session explores the business problem, how Harmoney applied a machine learning model to help minimize the recurrence of the problem, the practical issues associated with deploying this model, performance monitoring, and ongoing refinements.
Chief Data Scientist, Harmoney
iDirect: How To Democratize Modern Data Analytics for All Your Users
Brought to you by Talend
iDirect, one of the world’s largest manufacturers for satellite network and communications hardware, wanted to enable big data analytics in the cloud. By deploying a joint solution from Datalytyx, Talend, and Snowflake, iDirect business users, including sales and marketing, now have direct access to relevant data analytics and data science capabilities. Any business user can manipulate data and spot business opportunities without a background in statistics or technology, and without incurring additional IT costs or needing dedicated resources.
CTO of Datalytyx
Malwarebytes: Data Science With a Snowflake Data Lake
Malwarebytes is accelerating its data science efforts with Snowflake as its primary data lake. Snowflake’s unlimited scale, on-demand execution clusters, and support of a rich set of data formats have allowed Malwarebytes to centralize all data from transactions to billions of telemetry logs. This session demonstrates how data science, algorithms, and domain expertise are packaged into usable machine learning. You’ll learn how Malwarebytes ingests real-time application telemetry into Snowflake, using Kafka for training data science models in R and Python, and applies the classification models to real-time streaming data for identifying detections and false positives.
Director, Data Science and Engineering, Malwarebytes
Outreach: Faster and More Accurate Query Results With Snowflake
Outreach’s sales engagement platform leverages machine learning (ML) and A/B testing to coordinate email, voice, and social interactions. The need for trustworthy decision-making through A/B testing in sales was clear. However, lack of quality infrastructure frequently resulted in invalid tests and the inability to correctly guide users through the testing process. This session covers how Snowflake served as the quality foundation for implementing a trustworthy A/B testing solution. Snowflake’s native support for semi-structured data eliminated the need to conduct schema planning while delivering a single source of truth for error and user event data. You’ll also learn how Snowflake’s easy integration with Databricks enables Outreach to efficiently run about 1 million statistical tests per day.
VP of Data Science, Outreach
ShopRunner: Bringing Data + Machine Learning Together for Repeatable Success
Brought to you by Databricks
ShopRunner helps online shoppers get what they love, faster by connecting retailers to high-value customers with free shipping, highly personalized product feeds, granular inventory information, increasing both conversion rates and average spend. See how ShopRunner uses Databricks and Snowflake to tackle data science problems across personalization, recommendations, targeting, and analysis of text and images.
Sr. Data Engineer, ShopRunner
Strava: Using Data as the key to uncovering growth channels
Strava is the global network for athletes. Strava’s mission is to connect athletes to what motivates them and help them find their personal best. We do this by being the record of the world’s athletic activities and creating the technology that makes every effort count. This session will explore how athletes discover Strava today, and how Strava uses customer data to improve product discoverability. During the session, you will learn how Strava uses Snowflake to connect data from disparate sources with internal data to uncover its growth channels and analyze the customer acquisition journey. Topics covered include attribution modeling, incrementality measurement of paid acquisition and web experimentation.
Marketing Data Scientist, Strava
Trimble : Predictive Modeling for Better, Faster Insights
Trimble develops Global Navigation Satellite System receivers, laser rangefinders, unmanned aerial vehicles, inertial navigation systems, and software processing tools. Learn how Trimble uses Snowflake’s robust data connectors and scalable compute to efficiently store and transfer data between tools during the analytics lifecycle of model-building. The end result? Trimble’s data scientists now spend more time developing predictive models and less time waiting for data to become available. They can quickly build R&D data sets and discover insights that inform and support decision-making for predictive maintenance, video analysis, and employee-churn analysis.
Manager, Data Science, Trimble
Turner's Journey: From Hadoop to Snowflake via the CLEAR Framework
As Turner’s teams became more data-driven, the media company ran into a
(good) problem: their legacy system couldn’t handle the volume. It
became clear they not only needed a data warehouse that could meet their
needs, but they needed a better way to migrate to reduce business costs
and interference. In this session, Turner Senior Tech Director Vikram
Marathe will share how and why his team selected Snowflake, and Clarity
Insights Snowflake CoE Leader Ali Sajanlal will break down the CLEAR
migration framework which helped Turner migrate from Hadoop. You’ll see
how best-in-class organizations take advantage of Snowflake’s data
sharing and learn firsthand how to execute a seamless migration.
Sr. Technical Director, Warner Media
Yieldmo: Building the Modern Data Lake With Snowflake
Learn how Yieldmo successfully migrated its enterprise data stack from Hadoop to Snowflake. This session details the limitations of Yieldmo’s legacy system and how Yieldmo partnered with Snowflake to accelerate its data practice. Yieldmo uses Snowflake compute to ingest, load, and transform disparate semi-structured source formats, and co-locate data. Today, its Snowflake data lake efficiently supports various mission-critical business functions such as billing, attribution, reporting, and targeting as well as distributed machine learning pipelines.
VP Data, Yieldmo
Big Data Architect, Yieldmo
Building a Digital Platform at Uniper
Uniper, an international energy company located in Düsseldorf, Germany is using Snowflake as a central data lake in its Data Analytics Platform on Microsoft Azure. In this session Uniper will share their insights about motivation, their data strategy and transformation road-map into a data driven organization. Sample use case will be shared with the audience to show how Snowflake is used for data analytics across Uniper’s organization.
VP Data Integration, Uniper
Automated Machine Learning with DataRobot and Snowflake
Brought to you by DataRobot
Predictive modeling using machine learning techniques is transforming every aspect of modern business. Traditional approaches to machine learning is a time-consuming, resource-intensive and highly error-prone process. Automated machine learning platforms can make the process of building highly accurate predictive models fast and efficient. In this session, we will show how DataRobot can collaborate with data scientists to quickly build hundreds of highly accurate predictive models in a transparent and flexible manner, generate deep insights and deliver immediate value to business with easy deployment options. We will also illustrate how Snowflake users can bring in data from their data warehouse to DataRobot, delivering the performance, simplicity, concurrency, and affordability not possible with other data analytics platforms.
Head of Field Engineering, DataRobot
Deep Dive on Multi-Cloud External Stages in Snowflake
External stages enable customers to load data directly from cloud-based storage services. Come learn about recent enhancements to the set of supported cloud storage services, security and permissioning improvements, and how your organization can leverage the new external stages while enforcing rules on data exfiltration to secure your data.
Sr. Product Manager, Snowflake
Enabling AI Initiatives Through Operationalization and Self-Serve Analytics
Brought to you by Dataiku
Many organizations with the hope of becoming more data-driven ask the question: self-service analytics, or data science operationalization – which will get me where I need to be? And the answer is: you need both together. The fact is, it’s the interplay and balance between operationalization (o16n) and self-service analytics (SSA) initiatives that makes a successful data-powered company that executes on all projects to its fullest potential. While at first glance the two appear to be completely different (maybe even contradictory), it’s precisely because they differ in value, scale, and more that they round out a complete data strategy. This talk takes focuses on how to implement a complete strategy for both, pitfalls to avoid along the way, and use cases of large enterprises who have successfully implemented the two.
Lead Data Scientist, Dataiku
End-to-End Machine Learning with Snowflake and XGBoost
At least 80% of the work in machine learning is basic data management and processing: things at which databases excel. Snowflake’s engineering team will walk you through an end-to-end machine learning example using various factors in a Chicago taxi data to predict taxi fare. We’ll cover data ingestion, data cleaning, and preprocessing using Snowflake; integration with XGBoost for training; and deployment of the resulting model back to Snowflake as a simple SQL query. Except for the training step, which happens on an external machine, everything relies on Snowflake’s strong data processing power.
Software Engineer, Snowflake
How to Unify Your Data Lake With Snowflake
Attend this session to learn how to use Snowflake’s new features to integrate your existing data lake platform and strategy with your data warehouse.
Sr. Product Manager, Snowflake
Overview of AI, ML, and Data Science in the Snowflake Ecosystem
The Snowflake partner ecosystem powers a number of robust AI, ML and Data Science solutions. While each of these solutions provides distinct value for various types of users, all of them rely on data to drive insight. This session will highlight the benefits of leveraging Snowflake’s Cloud Data Warehouse as a flexible and scalable data platform to provide data for all these solutions, including real-life use cases.
Senior Sales Engineer, Snowflake
Predicting the Future With AWS Forecast and Snowflake
No crystal balls are necessary when you have Snowflake and AWS to predict your future. See how easy it is to integrate Snowflake with the AWS machine learning and AI stack. This session includes a code walkthrough and demo of Snowflake integrated with AWS Forecast.
Sales Engineer, Snowflake
Snowflake as an Engineering Feature Repository
Organizations are increasingly realizing they need to consolidate the outputs of their data and feature engineering into a central repository for reuse. This session covers the techniques and best practices for data reuse in Snowflake, and how the key capabilities of Snowflake provide an optimal feature repository.
Field CTO, Snowflake
Using TensorFlow with Snowflake Secure Data Sharing
Snowflake extends the power of cloud data warehousing. In this session, see how Snowflake uses live and secure data sharing with native programmatic connectors to integrate and process data in custom models. This session includes a demo of Snowflake used with a TensorFlow image recognition model.
Sales Engineer, Snowflake
Bring Your Own Schema: Performance Evaluation with Generated Data
You need a new data warehouse and have done your homework, you’ve compared features and benchmarks, and you’ve settled on a short list. But one important question is left. How will the new system perform with your actual data? This is impossible to answer unless you put your valuable data through a proof of concept.
If that’s not an option, come to this session and learn how to easily generate data that is structured like your data, looks like your data, and most importantly, scales like your data–so you can run your actual queries and see firsthand how the new system performs. Run your own benchmarks without the hassle of putting your data into the new system by tapping into the power of Snowflake’s data generation capabilities.
Field CTO, Snowflake
Run Analytics on a Data Lake Using Snowflake
Most companies have made significant investments in building out data lakes as their central data repository. And most customers use a data warehouse to query and analyze business-critical data and run reports on that data. But what about other non-business critical data? What about ad-hoc queries that need to be executed on archived data or infrequently used data? How can you achieve fast performance on these queries? In this hands-on lab you will use Snowflake features to run analytics on data in your data lakes.
Software Engineer, Snowflake
Product Manager, Snowflake
Supercharging Data Science and Machine Learning with Snowflake
Brought to you by Cervello
Tired of big data turning into big overhead? Join us in this session to learn how to harness the power of Snowflake to manage your enterprise data and enable your data science capabilities. You will learn how to easily build, train, and score models using data managed in Snowflake.
Data Scientist, Cervello