Sep 23–26, 2019

Schedule: Temporal data and time-series analytics sessions

Add to your personal schedule
9:00am12:30pm Tuesday, September 24, 2019
Location: 1E 09
Arun Kejariwal (Facebook), Karthik Ramasamy (Streamlio), Anurag Khandelwal (RISELab, UC Berkeley)
In this tutorial, we shall walk the audience through the landscape of streaming systems and overview the inception and growth of the serverless paradigm. Next, we shall present a deep dive of Apache Pulsar which provides native serverless support in the form of Pulsar functions and paint a bird’s eye view of the application domains where Pulsar functions can be leveraged. Read more.
Add to your personal schedule
1:30pm5:00pm Tuesday, September 24, 2019
Location: 1E 08
Sophie Watson (Red Hat), William Benton (Red Hat)
In this hands-on workshop, we’ll introduce several data structures that let you answer interesting queries about massive data sets in fixed amounts of space and constant time. This seems like magic, but we'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. Read more.
Add to your personal schedule
11:20am12:00pm Wednesday, September 25, 2019
Location: 1A 06/07
Ying Yau (AllianceBernstein)
Time series forecasting techniques can be applied in a wide range of scientific disciplines, business scenarios, and policy settings. This session discusses the application of deep learning techniques to time series forecasting and compares them to time series statistical models when forecasting time series with trends, multiple seasonality, regime switch, and exogenous series. Read more.
Add to your personal schedule
2:05pm2:45pm Wednesday, September 25, 2019
Location: 1A 06/07
Keshav Peswani (Expedia Group), Ashish Aggarwal (Expedia Group)
Observability is the key in modern architecture to quickly detect and repair problems in microservices. Modern observability platforms have evolved beyond simple application logs and now include distributed tracing systems like Zipkin, Haystack. Combining them with real time intelligent alerting mechanisms with accurate alerts helps in automated detection of these problems. Read more.
Add to your personal schedule
2:55pm3:35pm Wednesday, September 25, 2019
Location: 1A 06/07
Tony Xing (Microsoft), Bixiong Xu (Microsoft), Congrui Huang (Microsoft), Qun Ying (Microsoft)
Anomaly Detection may sound old fashioned yet super important in many industry applications. How about doing this in a computer vision way? Come to our talk to learn a novel Anomaly Detection algorithm based on Spectral Residual (SR) and Convolutional Neural Network (CNN), and how this novel method was applied in the monitoring system supporting Microsoft AIOps and business incident prevention. Read more.
Add to your personal schedule
4:35pm5:15pm Wednesday, September 25, 2019
Location: 1A 08/10
Robert Pesch (inovex GmbH), Robin Senge (inovex GmbH)
In this talk, we outline the development process, the statistical modeling, the data-driven decision making, and the 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. Read more.
Add to your personal schedule
4:35pm5:15pm Wednesday, September 25, 2019
Location: 1A 12/14
Criteo’s infrastructure provides capacity and connectivity to host Criteo’s platform and applications. The evolution of our infrastructure is driven by the ability to forecast Criteo’s traffic demand. In this talk, we explain how Criteo uses Bayesian Dynamic time series models to accurately forecast its traffic load and optimize hardware resources across data centers. Read more.
Add to your personal schedule
11:20am12:00pm Thursday, September 26, 2019
Location: 1A 21/22
Stavros Kontopoulos (Lightbend), Debasish Ghosh (Lightbend )
In this talk, we discuss online machine learning algorithm choices for streaming applications. We motive the discussion with resource constrained use cases like IoT and personalization. We cover Hoeffding Adaptive Trees, classic sketch data structures, and drift detection algorithms, all the way from implementation to production deployment, describing the pros and cons of using each of them. Read more.
Add to your personal schedule
11:20am12:00pm Thursday, September 26, 2019
Location: 1A 08/10
Anjali Samani (CircleUp)
The application of smoothing and imputation strategies is common practice in predictive modelling and time series analysis. With a technique-agnostic approach, this session will provide qualitative and quantitative frameworks that address questions related to smoothing and imputation of missing values to improve data density. Read more.
Add to your personal schedule
1:15pm1:55pm Thursday, September 26, 2019
Location: 1A 08/10
Alfred Whitehead (Klick), Clare Jeon (KLICK INC)
What will tomorrow’s temperature be? My blood glucose levels tonight before bed? Time series forecasts depend on sensors or measurements made out in the real, messy world. Those sensors flake out, get turned off, disconnect, and otherwise conspire to cause missing data in our signals. We will show a number of methods for handling data gaps and give advice on which to consider and when. Read more.
Add to your personal schedule
2:05pm2:45pm Thursday, September 26, 2019
Location: 1A 08/10
Anais Jackie Dotis (InfluxData)
Did you know that Classical algorithms outperform Machine Learning methods in time series forecasting? I’ll show you how I used the Holt-Winters forecasting algorithm to predict water levels in a creek. Read more.
Add to your personal schedule
2:05pm2:45pm Thursday, September 26, 2019
Location: 1E 14
Akshay Rai (Linkedin)
Failures or issues in a product or service can negatively affect the business. Detecting issues in advance and recovering from them is crucial to keep the business alive. Come, join us, to learn more about LinkedIn's next-generation open-source monitoring platform, an integrated solution for real-time alerting and collaborative analysis. Read more.
Add to your personal schedule
2:05pm2:45pm Thursday, September 26, 2019
Location: 3B - Expo Hall
Heitor Murilo Gomes (Télécom ParisTech), Albert Bifet (Télécom ParisTech)
In this talk, we show how to develop a machine learning pipeline for streaming data using the StreamDM framework (https://github.com/huawei-noah/streamDM). We also introduce how to use StreamDM for supervised and unsupervised learning tasks, show examples of online preprocessing methods, and how to expand the framework adding new learning algorithms or preprocessing methods. Read more.
Add to your personal schedule
4:35pm5:15pm Thursday, September 26, 2019
Location: 1A 08/10
Jeroen Janssens (Data Science Workshops B.V.)
In this talk, we present 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. First, we illustrate the idea and intuition behind SOS. Subsequently, we demonstrate our implementation of SOS on top of Spark. Finally, we apply SOS to a real-world use case. Read more.

    Contact us

    confreg@oreilly.com

    For conference registration information and customer service

    partners@oreilly.com

    For more information on community discounts and trade opportunities with O’Reilly conferences

    strataconf@oreilly.com

    For information on exhibiting or sponsoring a conference

    Contact list

    View a complete list of Strata Data Conference contacts