Sold Out

 

 

PLAN YOUR ESCAPE

DATA SCIENCE

DATA SCIENCE

VISUALIZE DATA IN YOUR BROWSER WITH WAVE

VISUALIZE DATA IN YOUR BROWSER WITH WAVE

by Salesforce

HANDS ON WITH WATSON ANALYTICS

by IBM

Description of the Class:

Salesforce.com uses a multi-tenant structure to host enterprise applications and data in the cloud in a secure and user friendly manner. In this workshop you will learn how to access that data and visualize it within your browser using Wave, a search-based and mobile friendly analytics engine built into the Salesforce Platform. The session will begin with the basics of how to build applications on the Salesforce Platform, including custom data models and business logic. Attendees will be instructed on how they can utilize Trailhead, an interactive learning framework, to start working with Wave using a free Developer Edition license.

 

Who Should Attend:

Interest in the creation and administration of cloud based enterprise applications and the easy visualization of related data.

 

Technology Requirements:

Please bring a laptop with a modern browser.

USING TRACKING DATA FOR SPORTS ANALYTICS

by STATS LLC

MACHINE LEARNING AT SCALE USING PYTHON AND SPARK

SPORTS ANALYTICS USING R

by SPS

OPEN FORUM

Presentations

Description of the Class:

How to use simple tools like Python, Scikit-Learn for building Machine Learning algorithms. Learn workflows that a data scientist or Machine Learning engineer can follow while building machine learning models. Learn preprocessing steps like feature engineering, hyper parameter tuning. Now we will take all these skills and learn how to scale using the most popular data processing framework called Apache Spark and it’s machine learning toolkit Mllib.

 

Prerequisites:

  • Participants should bring their own computers
  • Experience with Python is minimum requirement. Basic knowledge of Linear Algebra, Statistics and Machine Learning is required as well. Participants should have some knowledge of Big Data systems like Apache Hadoop and Apache Spark, but no experience is required.

 

Technology Requirements:

None, his session will be held in a computer lab.

 

VISUAL ANALYTICS WITH TABLEAU

Description of the Class:

Join a Tableau expert for a hands-on training session to help you see and understand your data. Learn best practices for data visualization and how to create interactive visualizations and dashboards in Tableau. This workshop is designed for all audiences and skill levels.

 

Prerequisites:

This workshop is designed for all audiences and skill levels.

 

Technology Requirements:

Bring a laptop computer (Mac, Linux, or Windows) with Tableau Desktop installed. A 30-day trial code will be supplied

http://www.tableau.com/products/desktop/download

HANDS ON WITH WATSON ANALYTICS

Description of the Class:

The Watson Analytics Workshop is designed for professors and students as a way to introduce you to the revolutionary approach to analytics that is smart data discovery. Industry is demanding it and here is an opportunity to learn from Watson Analytics experts how you can benefit from learning about guided exploration, automated predictive analysis, and effortless dashboard creation.

 

Technology Requirements:

Please bring your own laptop (please be sure it is charged) and create a Watson Analytics account prior to the workshop at:

 https://watson.analytics.ibmcloud.com/

TO LEARN MORE: Spend an hour with Watson Analytics:

http://bigdatauniversity.com/courses/watson-analytics-fundamentals/

CLOUD-BASED ANALYTICS WITH CORTANA ANALYTICS SUITE

Description of the Class:

As the world of Big Data and Analytics have evolved, Microsoft has led the way with cloud delivery of a simple to use, integrated analytics platform. Cortana Analytics Suite was designed to integrate the technologies required to allow you to transform your data into action.

 

Cortana Analytics Suite allows you to:

  • Take action ahead of your competitors by going beyond looking in the rear-view mirror (traditional reporting and self-service BI tools) to predict what’s next with analytics that enables action.
  • Get closer to your customers. Infer their needs through their interaction with natural user interfaces (perceptual intelligence).
  • Build with partner solutions for your industry to get going quickly and tailor to your specific needs.
  • Get value from your data in a secure and scalable way regardless of its size and complexity.
  • Get things done with Cortana in more helpful, proactive and natural ways.

 

Some industry scenarios where Cortana Analytics can help include:

  • Manufacturing – Predictive Maintenance
  • Financial Services – increase customer satisfaction and scale online
  • Retail – Attract new customers and keep them coming back
  • Healthcare – Enable positive patient outcomes

 

This workshop will provide an overview of the technologies included in the Cortana Analytics Suite. It will also include a hands-on lab where you will build out a solution using the tools. The hands-on approach will allow you to spend time working with the tools and learn how data flows through a big-data analytics solution. We’ll include loading data, creating a predictive model, as well as create reports and a dashboard to show how to visualize this data.

 

Technology Requirements:

Please bring a charged laptop computer with Remote Desktop Connection capabilities. Mac users can download software here: https://itunes.apple.com/us/app/microsoft-remote-desktop/id715768417?mt=12

GETTING STARTED WITH WATSON IoT IS AS EASY AS PI

Description of the Class:

Learn the platform for all of your Internet of Things development and application needs. Learn about IBM's Watson IoT platform on IBM Bluemix that will help you rapidly connect your devices, and also infuse capabilities around device management, information management, real-time analytics, risk management and cognitive computing. Create and deploy your IoT application on the cloud using Node-Red with ease. You will also learn to use a variety of “recipes”provided by our device partners and individual users to connect your devices to the cloud. You can take the knowledge and contribute yourself to the developerWorks recipes community. For more information, check out: https://internetofthings.ibmcloud.com/#/

 

Prerequisites:

This workshop is designed for all audiences and skill levels, but a laptop is recommended for this session.

 

Technology Requirements:

Please bring your own laptop, charged, and with network connectivity capabilities.

HADOOP PLATFORM SECURITY

Description of Class:

This session will provide a full understanding of the following:

  • Hadoop Platform Security
  • Best practices in Hadoop development and administration for secured cluster
  • Using Hadoop and Predictive analytics for identifying security threats in enterprise.

 

What you will learn in this session:

Hadoop Platform Security concepts will be introduced, which are as follows:

  • Perimeter
    • Authentication
    • Network isolation
  • Data
    • Encryption
    • Data Masking
  • Access
    • ACL
    • Permissions
    • Authorization
  • Visibility
    • Audit
    • Lineage

Secure Hadoop Application Development and Integration

Best Practices for Hadoop Application Development/Integration in secure environment will be introduced and implemented in hands on session as follows:

  • Delegation Chaining
  • Impersonation
  • Secure Client Access through Java, python code for:
    • HDFS
    • HBASE
    • SPARK/MAPREDUCE
    • HIVESERVER2

Secure Hadoop Cluster Administration

Best Practices for secure Hadoop Cluster Administration will be discussed and demonstrated in hands on session which are as follows:

  • IAM integration with Hadoop Cluster
  • Certificate, Keytab, keys and escalated privilege management
  • FAQs in Secure Hadoop cluster Management

Security threat detection based use case will be introduced and overview of activities to implement sample implementation will be provided

 

Technology Requirements:

We will cover each of these topics and go over each of them topic by topic. Requirements include

  • Good Internet access to AWS EC2 environment
  • SSH tools installed to login to EC2 nodes. Example: putty, secureCRT, MobaXTERM etc
  • Chrome or Firefox installed
  • JDK 1.7+ installed. (Preferred JDK1.7.0_67)
  • Python 2.7+ installed
  • Maven 3.3 installed OR IDE such as Netbeans, Eclipse or Intellij Idea
  • Mac, PC or Linux
  • 4GB+ RAM
  • VMWare, VirtualBox
  • Cloudera will provide exact link for CDH QuickStart Demo VM for participants if they prefer to use QuickStart VM (available on Cloudera Downloads page). This will require at-least 8GB RAM on host machine.
  • Although the presenter will have shared AWS EC2 environment for participants, attendees may use their own preferred CDH cluster that meets the following requirements:
    • CDH5.5+
    • 60 GB HDFS capacity
    • Cloudera Manager enabled cluster

Please reach out to Vijaykumar Singh with any questions about technological requirements at: singhvjd@cloudera.com

INTRODUCTION TO THE DATA SCIENTIST WORKBENCH

Description of the Class:

Open Source movement has fundamentally changed the way we find and consume software. It offered us things for free that only yesterday used to cost a fortune. Most important, it freed us from the tyranny of procurement. However, open source comes with its own set of challenges, especially for Data Scientists and Data Engineers. Python, R, Scala, Julia and dozens of other languages all with tens of thousands of often incompatible libraries. Scores of notebook and IDE technologies, Hadoop, Spark, Kafka and the rest of the big data ecosystem. Putting this all together is a huge challenge. This workshop suggests a way to enjoy the benefits of the open source tools for the data scientists but without the pain of assembling it all together yourself. For more information, visit: https://datascientistworkbench.com/

 

Prerequisites:

This workshop is designed for all audiences and skill levels, but a laptop is recommended for this session.

 

Technology Requirements:

Please bring your own laptop, charged, and with network connectivity.

VISUAL ANALYTICS: MAKING SENSE WITH QLIK SENSE

Description of the Class:

How long does it take you to get insights into your data? Days? Weeks? Are you caught in “Spreadsheet Hell” where every report is a cumbersome, macro-laden, Microsoft Access nightmare? Do you find yourself giving up and making decisions based on gut feelings because you simply cannot get analyses in a timely manner? Well, perhaps it’s time to step into the world of self-service analytics where you can quickly integrate data, analyze data, and share insights without having to work through elongated delivery cycles.

 

Whether you want to better utilize data to improve your own analyses or to better manage your organization, or if you are responsible for a team which provides analytics to your company, Qlik Sense may be the product that enables you and your company to make timelier, data-driven decisions. Kenway Consulting’s Introduction to Qlik Sense Workshop is a hands-on session that will show you how to:

  • Use Qlik Sense and navigate pre-existing reports, and get an understanding of how Qlik Sense works
  • Integrate data from multiple data sources and manipulate the data model to provide enhanced analytics
  • Build your own reports, visualizations, and dashboards rapidly without the assistance from IT resources
  • Incorporate findings into presentations that you can use to quickly share deeper insights

 

By walking you through a case study of a large bicycle retailer, we will guide you through the various stages of Business Intelligence maturity—shifting from raw data to descriptive visualizations to diagnostic analyses that allow users to answer the big questions as to why events occurred. Following the workshop, you will be able to come into work on Monday and immediately start using Qlik Sense for your data analysis needs.

 

To learn more about Qlik Sense, you can visit Qlik’s website:

 

Who should attend:

Anyone who is interested in making better sense of their data in order to better manage their organization—process efficiency, resource performance, supply chain analytics, and more—through Qlik Sense’s ability to consolidate multiple data sources into an easy to use dashboard application. Likewise, anyone tasked with providing analytics to their company should attend in order to see how Qlik Sense can be utilized as both a front-end tool for data delivery, as well as a means to perform data analysis and create proof of concepts to determine project feasibility.

 

Prerequisites:

There are no prerequisites to this workshop. Anyone who wants to improve their and their team’s insight into their organization through better data analysis or to get their company out of “Spreadsheet Hell” is encouraged to attend and witness the value of Qlik Sense.

 

Technology Requirements:

None. This session will be held in a computer lab.

HADOOP IN ACTION

Description of the Class:

High ETL complexity and costs, data latency and redundancy, and batch window limits are just some IT challenges caused by legacy enterprise data warehouses (EDW). Using Hadoop and open source big data tools to create an Enterprise Data Hub can reduce traditional EDW costs and improve performance. With Hadoop as an Enterprise Data Hub you can store and process all of your data in one place to create a single version of truth and run multiple transformation jobs that deliver information to multiple systems.

 

In this session, the MetaScale big data team will guide participants through an exploration of the Modern Enterprise Data Hub, including:

  • Structured, unstructured and semi-structured data
  • Batch analytics with RDBMS data
  • Real-time analytics with streaming social media data
  • Data integration
  • Reporting and visualization
  • This approach enables faster data workloads, provides a more robust set of tools to analyze data and makes it possible to consolidate hardware and software within the Hadoop infrastructure.

 

Join MetaScale for a detailed discussion on Hadoop and the Modern Enterprise Data Hub, how we build it, what open source big data tools and technologies are used and how business users can leverage it for greater insights. We will highlight the features and benefits of the enterprise data hub approach with an in-depth analytics demo.

 

Who should attend:

This is a must attend session for anyone interested in developing a greater understanding of how open source big data technologies such as Hadoop enable advanced analytics. Data Management, Business Intelligence and Analytics Managers who are struggling to develop a big data strategy or achieve ROI from their implementations will benefit from the discussion and demo.

 

Prerequisites:

Anyone on the path to becoming an IT or Business leader and interested in gaining practical knowledge of Hadoop and big data analytics will find value in this discussion. Learn more at:

NoSQL QUERIES USING SEMANTICS AND XQUERY/SPARQL

Description of the Class:

We will walk through a hands on workshop that will cover creating Semantics within a MarkLogic database.  By the end of this workshop you should be able to:

  • Describe Semantic data, triples and triple store
  • Create a MarkLogic database to use the triple store
  • Create Sematic indexes
  • Load RDF data into the MarkLogic triple store using MarkLogic Content Pump
  • Test the triple store database via a REST api
  • Query triples using XQuery and SPARQL

 

Who Should Attend:

Those interested in learning how to ingest data into a MarkLogic database and then get a brief understanding of Querying a Big Data data store using XQuery and SPARQL

 

Prerequisites:

Some programming experience and an understanding of basic databases.

 

Technology Requirements:

All workshop attendees must:

  • Bring their own computer

ETHICAL HACKING FOR TEENS

Description of the Class:

Learn basic Ethical Hacking skills including how the “bad guys and gals” create viruses, use wrappers, crack passwords, and exploit vulnerabilities in network devices (computers, laptops, tablets and smartphones) and information networks.  This course will help participants understand how to protect themselves and others against malicious users on the Internet while exploring the world of information technology.

 

Example topics and labs:

 

  • Taking the mystery out of computers, network devices, and the Internet
  • How malicious hackers exploit weaknesses in technology
  • Creating a virus and infecting a target using a wrapper
  • Hacking everything but harming nobody
  • How the bad folks use key loggers

 

Hands-on experience with common security attacks (e.g. man-in-the-middle)

 

Sponsored by Northwestern University’s School of Professional Studies, this course combines interactive discussion and hands-on lab work in a fun, casual environment.

 

Who Should Attend:

Students between the ages of 14 and 19 interested in technology (or a career in  technology) will gain valuable insight into how the Internet works and how to hack  common weaknesses, which is key to understanding how mischievous hackers think and  work.  This course requires no previous experience, and all computers will be provided!

QUICK-RESPONSE BIG DATA QUERIES

Description of the Class:

Big Data has an increasing problem of access and real-time (or close to real-time) analysis.  The conversation around Big Data has traditionally been geared around storing and analyzing large amount of data at off-peak times or in systems where latency of querying is not an issue.  However, there is an increasing need to attach big data systems to applications.  This course will discuss strategies for organizing data for this purpose.

 

We will discuss common querying frameworks like Hive, Sqoop and Pig. and where these frameworks start to break down in a real-time querying situation.  We will also talk about distributed search technologies like ElasticSearch and Solr and how these can be used for fast indexing.  Finally, we will discuss architecture strategies to use these products together to create customer-facing solutions that respond quickly.

 

Who Should Attend:

This workshop will benefit anyone who is working with big data systems that need fast querying.

 

Prerequisites:

Basic programming knowledge is recommended for the hands-on exercises. The conversation will benefit anyone who is interested.

 

Technological Requirements:

Please bring a charged laptop with the following installed:

SPORTS ANALYTICS

USING TRACKING DATA FOR SPORTS ANALYTICS

Description of the Class:

The “Moneyball” revolution coincided with a shift in the way professional sporting organizations handle and utilize data in terms of decision-making processes. Due to the demand for better sports analytics, organizations are utilizing fine-grain tracking data to enhance their ability to analyze performances. Two prime examples are the STATS SportVU system which has been deployed in the NBA, as well as Prozone tracking data which is used in most European soccer Leagues.

 

In this workshop, I’ll first show a portfolio of recent research that utilizes tracking data for a host of applications. Specifically, I’ll show examples using SportVU data in basketball, Prozone data in soccer and Hawk-Eye data in tennis.

 

In the second part of the workshop, I will give step-by-step examples on how to:

  • cluster multi-agent tracking data
  • build simple shot prediction models by crafting domain specific features and learn a simple classifier

 

Who Should Attend:

Anyone interested in sports, unstructured fine-grained data, and/or applied machine-learning will find this interesting.

 

Prerequisites:

It is not necessary to have a computer science or programming background as there will be lots of examples and visualizations. In some sections, brief descriptions of recent published algorithms will be given, so an understanding of machine-learning/data-mining would be useful. Additionally, in the second part of the workshop, examples will be given in Python so some knowledge of it will be helpful. (Unfortunately, no data or code will be shared in the workshop – the second part of the workshop is just a demonstration of recent published techniques.)

 

Technology Requirements:

Please bring your laptop, but there are no requirements for this session.

SPORTS ANALYTICS USING R

Description of the Class:

This is a hands-on workshop in sports analytics. Students will get a chance to work with open-source software analyze data relating to professional sports, including Major League Baseball, the National Basketball Association, and the National Football League. The workshop demonstrates various performance measurement and modeling methods used to guide sports decision-making. The workshop is divided into three parts:

 

Part I. Which players should we draft? We will examine performance data and measures from both the National Football League (NFL) as well as the NFL Combine. Here we review physiological and physical performance measures, showing how they relate to performance of players across various positions in the sport of football. Methods include exploratory data analysis, descriptive statistics, and classical models.

 

Part II. What play should we call? The focus here is play-by-play data from Major League Baseball. We introduce game states, transition probabilities, and Markov chain models as they apply to baseball.

 

Part III. What is a player worth? Using data from the National Basketball Association, we show how to generate ratings and rankings of players. We also show how to assess a player’s worth in terms of points made or number of team wins relative to other players. We end by showing how player performance measures may be translated into dollars during salary negotiations.

 

Technological Requirements:

Bring a laptop computer (Mac, Linux, or Windows) with a modern browser installed (Chrome or Firefox). Install versions of R and RStudio that are compatible with your computer. R is available at:

 

RStudio is available at:

 

You may also want to install a capable text editor such as Sublime Text 2:

OPEN FORUM PRESENTATIONS AND THINK TANK

See more details about specific ideas and papers that will be presented on our Publications Page ->

 

Workshop Description:

This year, the Publication Steering Committee has invited original paper authors and industry leaders to present innovative and ground-breaking ideas in this open-discussion forum. This showcase of Data Science technologies includes:

  • Machine Learning algorithms with Big Data
  • Predictive Analytics Applications
  • Real-time analytics with Data Science Technologies
  • NoSQL technologies – mongoDB, CassandrA
  • Large Scale Data Science implementations
  • Big Data Architecture and Governance
  • Data Science application for Social Cause
  • Application of Big Data and Data Science to world of Politics
  • Internet of Things applications
  • Data Science applications in Government
  • Best practices in handling sensitive Big Data
  • Use cases of Columnar Databases
  • Applications of Data Science in Healthcare
  • Big Data Ecosystem with Hadoop
  • Integration of Data Science technologies with traditional technologies

 

Who Should Attend:

Those who are looking to learn about the future of Data Science but feel that the hands-on workshops might be a little overwhelming. If you are looking to learn and want to listen in on some great discussions to see how Data Science will influence your future, this is the session for you.

 

Prerequisites:

None. Come one, come all and dive into some great lectures and discussions.

Join us May 7th, 2016 for the Escape Data Science and Sports Analytics Conference in Chicago, IL where we will "Learn by Doing."

 

Brought to you by Northwestern University and Robert Morris University.

Contact Info

Northwestern University

Dr. Faisal Akkawi

f-akkawi@northwestern.edu

 

339 East Chicago Avenue Chicago, Illinois 60611

Share Escape

Facebook

Twitter

LinkedIn

Google+

Email