Strata Data Conference

From whiteboard to production: A demand forecasting system for an online grocery shop

February 13, 2020

Data-driven software is revolutionizing the world and enable intelligent services we interact with daily. Robert Pesch and Robin Senge outline the development process, statistical modeling, data-driven decision making, and components needed for productionizing a fully automated and highly scalable demand forecasting system for an online grocery shop for a billion-dollar retail group in Europe.

Gaining new insight into online customer behavior using AI

February 13, 2020

Customer satisfaction is a key success factor for any business. Moise Convolbo highlights the process to capture relevant customer behavioral data, cluster the user journey by different patterns, and draw conclusions for data-informed business decisions.

Handling data gaps in time series using imputation

February 13, 2020

Time series forecasts depend on sensors or measurements made in the real, messy world. The sensors flake out, get turned off, disconnect, and otherwise conspire to cause missing signals. Signals that may tell you what tomorrow's temperature will be or what your blood glucose levels are before bed. Alfred Whitehead and Clare Jeon explore methods for handling data gaps and when to consider which.

Hands-on machine learning with Kafka-based streaming pipelines

February 13, 2020

Boris Lublinsky and Dean Wampler examine ML use in streaming data pipelines, how to do periodic model retraining, and low-latency scoring in live streams. Learn about Kafka as the data backplane, the pros and cons of microservices versus systems like Spark and Flink, tips for TensorFlow and SparkML, performance considerations, metadata tracking, and more.

How disruptive tech is reshaping the financial services industry

February 13, 2020

The financial services industry is increasingly using disruptive technologyincluding AI and machine learning, edge computing, blockchain, mobile and mixed reality, virtual assistants, and quantum computing to name a fewto enhance the customer experience and personalize their interactions with customers. Swatee Singh outlines how the same is true at American Express.

How machine learning meets optimization

February 12, 2020

Machine learning and constraint-based optimization are both used to solve critical business problems. They come from distinct research communities and have traditionally been treated separately. But Jari Koister examines how they're similar, how they're different, and how they can be used to solve complex problems with amazing results.

How to deploy large-scale distributed data analytics and machine learning on containers (sponsored by HPE (BlueData))

February 12, 2020

Anant Chintamaneni and Matt Maccaux explore whether the combination of containers with large-scale distributed data analytics and machine learning applications is like combining oil and water or like peanut butter and chocolate.

Improve your data science ROI with a portfolio and risk management lens

February 12, 2020

While data science value is well recognized within tech, experience across industries shows that the ability to realize and measure business impact is not universal. A core issue is that data science programs face unique risks many leaders arent trained to hedge against. Brian Dalessandro addresses these risks and advocates for new ways to think about and manage data science programs.

Improving Spark by taking advantage of disaggregated architecture

February 12, 2020

Shuffle in Spark requires the shuffle data to be persisted on local disks. However, the assumptions of collocated storage do not always hold in todays data centers. Chenzhao Guo and Carson Wang outline the implementation of a new Spark shuffle manager, which writes shuffle data to a remote cluster with different storage backends, making life easier for customers.

Interactive sports analytics

February 12, 2020

Imagine watching sports and being able to immediately find all plays that are similar to what just happened. Better still, imagine being able to draw a play with the Xs and Os on an interface like a coach draws on a chalkboard and instantaneously finding all the similar plays and conduct analytics on those plays. Join Patrick Lucey to see how this is possible.

Learning with limited labeled data

February 12, 2020

Supervised machine learning requires large labeled datasetsa prohibitive limitation in many real world applications. But this could be avoided if machines could earn with a few labeled examples. Shioulin Sam explores and demonstrates an algorithmic solution that relies on collaboration between human and machine to label smartly, and she outlines product possibilities.

Machine learning in data quality management

February 12, 2020

Jennifer Yang discusses a use case that demonstrates how to use machine learning techniques in the data quality management space in the financial industry. You'll discover the results of applying various machine learning techniques in the four most commonly defined data validation categories and learn approaches to operationalize the machine learning data quality management solution.

Managing your Kafka in an explosive growth environment

February 12, 2020

Frequently, Kafka is just a piece of the stack that lives in production that often times no one wants to touchbecause it just works. Alon Gavra outlines how Kafka sits at the core of AppsFlyer's infrastructure that processes billions of events daily.

Migrating millions of users from voice- and email-based customer support to a chatbot

February 12, 2020

At MakeMyTrip customers were using voice or email to contact agents for postsale support. In order to improve the efficiency of agents and improve customer experience, MakeMyTrip developed a chatbot, Myra, using some of the latest advances in deep learning. Madhu Gopinathan and Sanjay Mohan explain the high-level architecture and the business impact Myra created.

Natural language understanding at scale with Spark NLP

February 11, 2020

David Talby, Alex Thomas, Saif Addin Ellafi, and Claudiu Branzan walk you through state-of-the-art natural language processing (NLP) using the highly performant, highly scalable open source Spark NLP library. You'll spend about half your time coding as you work through four sections, each with an end-to-end working codebase that you can change and improve.

Now you see me; now you compute: Building event-driven architectures with Apache Kafka

February 11, 2020

Would you cross the street with traffic information that's a minute old? Certainly not. Modern businesses have the same needs. Michael Noll explores why and how you can use Kafka and its growing ecosystem to build elastic event-driven architectures. Specifically, you look at Kafka as the storage layer, at Kafka Connect for data integration, and at Kafka Streams and KSQL as the compute layer.

Online machine learning in streaming applications

February 11, 2020

Stavros Kontopoulos and Debasish Ghosh explore online machine learning algorithm choices for streaming applications, especially those with resource-constrained use cases like IoT and personalization. They dive into Hoeffding Adaptive Trees, classic sketch data structures, and drift detection algorithms from implementation to production deployment, describing the pros and cons of each of them.

Orchestrating data workflows using a fully serverless architecture

February 11, 2020

Use of data workflows is a fundamental functionality of any data engineering team. Nonetheless, designing an easy-to-use, scalable, and flexible data workflow platform is a complex undertaking. Tomer Levi walks you through how the data engineering team at Fundbox uses AWS serverless technologies to address this problem and how it enables data scientists, BI devs, and engineers move faster.

Parquet modular encryption: Confidentiality and integrity of sensitive column data

February 11, 2020

The Apache Parquet community is working on a column encryption mechanism that protects sensitive data and enables access control for table columns. Many companies are involved, and the mechanism specification has recently been signed off on by the community management committee. Gidon Gershinsky explores the basics of Parquet encryption technology, its usage model, and a number of use cases.

Practical feature engineering

February 11, 2020

Feature engineering is generally the section that gets left out of machine learning books, but it's also the most critical part in practice. Ted Dunning explores techniques, a few well known, but some rarely spoken of outside the institutional knowledge of top teams, including how to handle categorical inputs, natural language, transactions, and more in the context of machine learning.

Protecting the healthcare enterprise from PHI breaches using streaming and NLP

February 11, 2020

Hospitals small and large are adopting cloud technologies, and many are in hybrid environments. These distributed environments pose challenges, none of which are more critical than the protection of protected health information (PHI). Jeff Zemerick explores how open source technologies can be used to identify and remove PHI from streaming text in an enterprise healthcare environment.

Recent trends in data and machine learning technologies

February 11, 2020

Ben Lorica dives into emerging technologies for building data infrastructures and machine learning platforms.

Running AI workloads in containers (sponsored by BMC Software)

February 10, 2020

Developing, deploying and managing AI and anomaly detection models is tough business. See-Kit Lam details how Malwarebytes has leveraged containerization, scheduling, and orchestration to build a behavioral detection platform and a pipeline to bring models from concept to production.

Say what? The ethical challenges of designing for humanlike interaction

February 10, 2020

Language shapes our thinking, our relationships, our sense of self. Conversation connects us in powerful, intimate, and often unconscious ways. Jonathan Foster explains why, as we design for natural language interactions and more humanlike digital experiences, languageas design material, conversation, and design canvasreveals ethical challenges we couldn't encounter with GUI-powered experiences.

Scalable anomaly detection with Spark and SOS

February 10, 2020

Jeroen Janssens dives into stochastic outlier section (SOS), an unsupervised algorithm for detecting anomalies in large, high-dimensional data. SOS has been implemented in Python, R, and, most recently, Spark. He illustrates the idea and intuition behind SOS, demonstrates the implementation of SOS on top of Spark, and applies SOS to a real-world use case.

Search logs + machine learning = autotagged inventory

February 10, 2020

Eventbrite is exploring a new machine learning approach that allows it to harvest data from customer search logs and automatically tag events based upon their content. John Berryman dives into the results and how they have allowed the company to provide users with a better inventory-browsing experience.

Sketching data and other magic tricks

February 10, 2020

Go hands-on with Sophie Watson and William Benton to examine data structures that let you answer interesting queries about massive datasets in fixed amounts of space and constant time. This seems like magic, but they'll explain the key trick that makes it possible and show you how to use these structures for real-world machine learning and data engineering applications.

Solve tomorrows business challenges with a modern data warehouse (sponsored by Matillion)

February 10, 2020

According to Forrester, insight-driven companies are on pace to make $1.8 trillion annually by 2021. Daniel D'Orazio wants to know how fast your team can collect, process, and analyze data to solve presentand futurebusiness challenges. You'll gain actionable tips and lessons learned from cloud data warehouse modernizations at companies like DocuSign that you can take back to your business.