Browse communities
Browse communities
Presenting a webinar?

Scalable Cross-Platform R-Based Predictive Analytics

Mario Inchiosa, US Chief Scientist at Revolution Analytics
In this webinar we will take a quick tour through an end-to-end predictive analytics session. We will start by exploring our data with summaries and histograms.

Using the knowledge gleaned from data exploration, we will create transformations to clean our data and prepare it for model building. Next, we will establish a prediction baseline by performing linear regression.

Then we will apply a state-of-the-art black box algorithm, Ensembles of Decision Trees, to push prediction to the limit. Finally, we will use this high quality ensemble model to score new data, completing the prediction workflow.

We will discover how to perform these steps scalably using an R-based tool across a wide range of platforms: Windows and Linux laptops and workstations, multicore servers, Hadoop and MPI clusters, and massively parallel databases.
Dec 12 2013
46 mins
Scalable Cross-Platform R-Based Predictive Analytics
More from this community:

Business Intelligence and Analytics

  • Live and recorded (1620)
  • Upcoming (46)
  • Date
  • Rating
  • Views
  • During this webinar, Elena Martínez, Retail Specialist at Openbravo, and Victor Gaspar, Project Manager at GMV (Openbravo Certified Partner), will explain how retailers can help enable their stores to be smarter and which technologies are helping them today to make this happen.

    What Will You Learn?
    - The concept of smarter stores and how it is related with the convergence of technologies like mobility and the Internet of Things.
    - The importance of physical smarter stores in today's omnichannel reality.

    Who Should Attend?
    - Business Areas Directors
    - CIOs
    - IT Administrators
    - Consultants
  • On April 15th, Birst announced a technology partnership with Tableau Software. This product integration brings Tableau’s powerful visual analytics to Birst’s agile and scalable Cloud BI data platform through an ODBC connector. Watch this 90 second demo to see how Birst and Tableau work together to ensure numbers never looked so good.
  • Join us on Thursday, April 16, 2015 at 11:00 AM PST/2:00 PM EST for this follow-up webinar to the Introduction to Apache Ignite(TM) (incubating) webinar, in which GridGain co-founder and EVP of Engineering and Ignite PMC Chair, Dmitriy Setrakyan will take a deep dive into several coding examples.
  • Ingesting raw data into Hadoop is easy, but extracting business value leveraging exploration tools is not. Hadoop is a file system without a data model, data quality, or data governance, making it difficult to find, understand and govern data.

    In this webinar, Tony Baer, Principal Analyst of Ovum Research, will address the gaps and offer best practices in the end-to-end process of discovering, wrangling, and governing data in a data lake. Tony Baer will be followed by Oliver Claude who will explain how Waterline Data Inventory automates the discovery of technical, business, and compliance metadata, and provides a solution to find, understand, and govern data.

    Attend this webinar if you are:
    --A big data architect who wants to inventory all data assets at the field level automatically while providing secure self-service to business users
    --A data engineer or data scientist who wants to accelerate data prep by finding and understanding the best suited and most trusted data
    --A Chief Data Officer or data steward who wants to be able to audit data lineage, protect sensitive data, and identify compliance issues
  • Here’s the good news. While the number of data sources organizations face is rapidly increasing, the cost to store data has never been cheaper. This trend – as well as big data technologies like Hadoop – has led to more valuable insights for organizations.

    But it’s also led to IT departments overburdened with requests from the business users they support. So where do we go from here?

    View this webinar that discusses data federation, a type of data virtualization that:

    • Provides a centralized governance and security layer.
    • Speeds the creation of virtual data views.
    • Makes it easier for business users to access the data they need.

    We’ll also demonstrate technologies like big data virtualization, federated data-as-a-service and data masking.
  • SAS® In-Memory Analytics is built for speed. It enables you to access unstructured and structured data and tackle complex analytical computations blazingly fast. But it doesn’t end there.

    SAS In-Memory Analytics also delivers incremental value from big data so that you can find more lucrative opportunities, detect risks and improve targeted marketing.

    View this webinar to learn why SAS In-Memory Analytics can help you:

    • Tackle problems never before considered due to computing constraints.
    • Draw timely insights from Hadoop.
    • Perform self-service data discovery.
    • Run iterative and interactive analytics scenarios.
  • Your business is extremely competitive – a loyal customer can be lost with the click of a mouse, the wrong product mix erodes sales, and supply chain inefficiencies eat into profit margins. Have you begun transforming your business using Big Data to engage individually with customers, optimize your merchandising and logistics, and re-gain competitive advantage? If not, then it’s time to start your Big Data journey!

    In this webinar you will learn:
    •Big Data use-cases and market trends in Retail and CPG
    •Informatica’s Big Data solution for Retail and CPG
    •Real-world customer examples and case studies

    The wealth of data available to Retail and CPG companies often goes untapped, even though it can provide tremendous business value when managed as an asset. Using Informatica to access, transform, cleanse, and master Big Data can turn data captured from POS systems, social media, sales & marketing campaigns, Electronic Data Interchange (EDI) feeds, supplier catalogs, clickstreams, mobile devices, and more into Great Data. Delivering great data to business, consumers, and suppliers lets you put the right products in front of the right customers at the right time.

    In this webinar, you will learn how to use Informatica for Big Data use-cases specific to the Retail and CPG industry such as omni-channel marketing campaign and supply chain optimization. Real-world examples and customer case studies will illustrate how other companies are achieving amazing results by fully leveraging their Big Data.
  • Speakers:
    Stewart Rogers: Director of Marketing Technology; VB Insight
    Ujjwal Dhoot: CMO; FSAstore.com
    Talia Wolf: Founder & CEO; Conversioner
    Nichole Elizabeth DeMeré: Community Growth for Inbound.org at HubSpot Labs

    Abstract:

    In an increasingly competitive marketplace, conversion rate optimization (CRO) tools, techniques, and tactics can be the difference between becoming a market leader or an ‘also ran.’

    The practice of gaining as much as possible from existing traffic, visits, reads, and views is becoming a serious business, and a raft of tools are carving out their place in the field.

    We’ll analyze the top solutions, revealing what techniques CRO practitioners use them for, how they are priced, how satisfied users are with them, how they score for each major feature, and what types of business use each product.

    Check out VB Insight to access Stewart's Conversion Rate Optimization report, and to access the latest research on Marketing Technology:

    http://insight.venturebeat.com/report/conversion-optimization-how-win-performance-marketing
  • Join this webinar to learn how Informatica and X15 Software have teamed up to:

    -Provide an end-to-end machine and log data management solution on Hadoop
    -Dramatically simplify and accelerate machine data collection, indexing, storage, analysis and visualization
    -Scale to handle massive volumes of streaming data
    -Gain insights into user activities, product utilization, security threats and many other operational metrics
    -Help you leverage your existing investment in analytic resources and BI technologies
  • Kurze Darstellung des IBM SPSS Portfolios. Detailliertere Vorstellung von IBM SPSS Modeler und dem Cross Industry Standard für Data Mining.
  • Channel
  • Channel profile
  • My Favourite Pie (chart): Simple Rules for Clear and Attractive Visuals Jul 22 2015 9:00 am UTC 45 mins
    Markus Ehrenmueller, Business Intelligence Architect, Runtastic
    Do you want to deliver information in an effective and efficient way? Even when the attractiveness of a report is important, beauty is in the eye of the beholder. Join this session where Markus will show you some simple rules for helping end-users to understand the story their data is trying to tell.

    You will see how you can implement those rules with different tools from Microsoft’s BI stack – resulting in clear and concise information delivered through beautiful dashboards. You will also learn how to identify sub-optimal dashboards and what you can do to improve them.
  • Experiments in Deep Learning May 28 2015 6:00 pm UTC 60 mins
    Patrick Hall, Senior Associate Research Statistician Developer, SAS
    The human brain makes it look easy. What our eyes see, we decode immediately and effortlessly. But is it that simple? In truth, how we process images is staggeringly complex. Inspired in part by our remarkable neurons, deep learning is a fast-growing area in machine learning research that shows promising breakthroughs in speech, text and image recognition. It’s based on endowing a neural network with many hidden layers, enabling a computer to learn tasks, organize information and find patterns on its own.

    Recently, SAS took on a classical problem in machine learning research, the MNIST database, a data set containing thousands of handwritten digit images. Learn how we did – and what it reveals about the future of deep learning.
  • Ask, Measure, Learn May 28 2015 4:00 pm UTC 45 mins
    Lutz Finger, Director of Data Science and Data Engineering, LinkedIn; Author, "Ask, Measure, Learn"
    We do not want Big Data! We want the right data to answer the right questions!

    Data is changing our world. Predictions using massive data not only have improved many products. At the same time, they have, in some industries, disrupted business models and created new ones.

    What does an organization need to do to generate a new competitive advantage out of data? The answer might be surprising. “Change the state of mind.”

    Companies often do not need big data. They essentially want small and actionable advice. Some predictions will need big data to surface relevant information, but not all. The key to success for many companies, however, is to enable “data­driven” decision making. Lutz will discuss the steps he has used in starting and developing his own company (later sold to WPP), as well as how he leads LinkedIn’s data science team.

    A) Change the state of mind!
    Enable everyone in the company to ask “data driven” questions. Lutz will show how this is the hardest part of the on­going exercise, but why most businesses actually can achieve this with their current strategic abilities. Using examples we will learn what is the best way to formulate the “Ask”.

    B) What data?
    Data can be a source of disruption & innovation. Business models change because new data sources and enhanced computational power allows new services or improve old services. But which data to use? Domain knowledge is often more important than having “Big Data". Lutz will introduce a framework on how to think about data.

    C) How to build a Data Team?
    How can organizations build up data capabilities within your team. Contrary to the common discussion that a data scientist are not ‘hard to find’. Lutz will explain how every company can create a data science organization by just mixing the right skillets.
  • Machine Learning - where to next? May 28 2015 1:00 pm UTC 45 mins
    Peter Morgan, CEO, Zepto Ventures
    We have all probably heard of machine learning by now. Some may even know that it is embedded in hundreds of everyday consumer and business products and services from search to image and speech recognition. In this talk Peter will give a brief overview of what machine learning is, where it came from and where it might take us in the near, medium and far term - two, five and ten years, respectively. He will cover the positive changes it will bring, plus the risks and issues that may result from the widespread adoption of this technology.
  • Human-Centered Design and Data Science May 27 2015 3:00 pm UTC 45 mins
    Dean Malmgren, Partner and Data Scientist, Datascope Analytics
    When you hear someone say, “that is a nice infographic” or “check out this sweet dashboard,” many people infer that they are “well-designed.” Creating accessible (or for the cynical, “pretty”) content is only part of what makes good design powerful. The human-centered design process is geared toward solving specific problems. This process has been formalized in many ways (e.g., IDEO’s Human Centered Design, Marc Hassenzahl’s User Experience Design, or Braden Kowitz’s Story-Centered Design), but the basic idea is that you have to explore the breadth of the possible before you can isolate truly innovative ideas.

    In this talk, I'll share some lessons we've learned from the human-centered design process and how those lessons can be used by other data science practitioners.
  • An Introduction to Machine Learning May 27 2015 11:00 am UTC 45 mins
    Dr. Nilesh Karnik, Chief Data Scientist, Aureus Analytics
    The term machine learning is frequently heard these days in connection with data science. In this talk, I’ll explain what machine learning is and how it is related to some other terms we hear in the context of data science such as predictive modelling or data mining. I’ll also cover key concepts related to machine learning such as supervised and unsupervised learning, and cover some of the commonly used machine learning approaches like regression, decision trees, clustering and artificial neural networks. Finally, with the help of an example, I’ll go over the process of using machine learning to solve a real life problem.
  • Hadoop and the Enterprise Data Warehouse, Simplified Apr 23 2015 6:00 pm UTC 60 mins
    Tamara Dull, Dir. Emerging Technologies, SAS Best Practices; Tony Pagliarulo, Partner & Practice Lead, NewVantage Patners
    When Apache Hadoop hit the market eight years ago, it rattled the cages of traditional BI and data warehousing professionals. Many speculated whether Hadoop would replace existing infrastructures, complement them, or become just the latest technology fad.

    We now know Hadoop is not a fad and driving topic of discussion today is around how best to utilize Hadoop - even if you don't have big data.

    If you're a technically savvy business professional who is still trying to understand how big data - and Hadoop in specific - impacts the enterprise data game, this webinar is for you. We'll highlight six common ways Hadoop is being used to support and extend the enterprise data warehouse ecosystem, with or without "big" data.
  • Integrating Hadoop into Business Intelligence Apr 23 2015 3:00 pm UTC 60 mins
    Philip Russom, Senior Manager, TDWI Research
    TDWI recognizes that Hadoop usage is a minority practice today, but assumes that mainstream usage of Hadoop within business intelligence (BI) and data warehousing (DW) applications will become common across many industries within a few years. This Webinar provides an overview of Hadoop products and best practices in the context of BI/DW applications so that user organizations can prepare to integrate Hadoop into their BI/DW technology stacks and software portfolios successfully.

    In this webinar, you’ll learn:

    What Hadoop technologies are and can do for BI/DW
    Common types of analytic applications that Hadoop technologies enable
    Adjustments that Hadoop-based analytics with big data requires of practices in data integration, metadata management, query optimization, data warehouse architecture, and so on
  • Big Data Solutions: Simplifying Data with Hadoop Apr 23 2015 10:00 am UTC 45 mins
    Chandra Salem, Senior Enterprise Data Architect
    Data is now the driving force behind business success. Embrace it and the rewards can be an ever-increasing competitive advantage, significant revenue growth and bottom-line boosting profit margins.

    What is your big data challenge?

    · Is your existing infrastructure too small to go big?

    · Are you facing ever sky-rocketing capital expenditure just to support your infrastructure?

    · Is there an expertise gap in your business that you are struggling to fill?

    · Are you finding that your external options are limited by vendor lock-in?

    · Are you struggling to move on to the next phase and embrace innovative technologies, such as Hadoop, to capture the insights you need?

    Hear from Rackspace, Data Store experts to understand how to take your business to the next level in the data age.
  • Hadoop and Self-Service Analytics: Embracing Big Data Apr 22 2015 4:00 pm UTC 45 mins
    Dustin Smith, Tableau
    The maturity of Hadoop as a technology framework suitable for organizations, large and small, to economically store and process vast amounts of data is no longer a prediction, but rather a reality every IT leader understands. But that doesn’t mean Hadoop is done disrupting the data and analytics landscape.

    Self-service analytics solutions capable of leveraging the massive processing and data discovery potential of distributed Hadoop clusters are ushering in a new era of data freedom for business users who are hungry to put data at the heart of their decision making process. With programming and query languages no longer a prerequisite skill for exploring Hadoop environments, organizations everywhere are waking up to the reality that even non-technical users can quickly and easily find insights in even the biggest of Hadoop data sets.

    Attend this webinar to hear how IT groups are adjusting to this new breed of bold and curious data user and learn:
    - How IT is shifting from data protector to data mentor
    - Why business users are so data hungry and so un-afraid of Big Data
    - What true self-service analytics can look like when paired with Hadoop
  • Explore Big Data Analytics with Amazon Redshift Apr 22 2015 3:00 pm UTC 45 mins
    Rahul Pathak, Senior Product Manager, Amazon Redshift Ted Wasserman, Product Management & Development, Tableau Software
    Amazon Redshift enables customers to innovate quickly using its fully managed and immensely scalable data warehousing solution. Tableau’s ability to connect directly to Redshift and leverage its massive computing power means even the most non-technical business user can quickly discover business insights with easy to use drag and drop visual analytics against mammoth data sets. Join Amazon Web Services (AWS), Mixpo and Tableau Software, an AWS Technology Partner, to learn how customers are leveraging both Tableau and AWS to tackle big data exploration projects and recognize business benefits in record time.
  • Open source analytics in Enterprise-level environment: Opportunities& challenges Apr 22 2015 12:00 pm UTC 45 mins
    Maciej Zawadziński, CEO, Piwik PRO
    Using real life examples drawn from his work with enterprise clients, Maciej Zawadziński, CEO of Piwik PRO, will outline possible uses of open source analytics platforms in Enterprise-level environments, also indicating potential opportunities and challenges. A must-attend for anyone serious about enterprise sector and curious about business applications of open source software!
  • Stream Processing 360 in the Hadoop Ecosystem: Use Cases and Best Practices Apr 22 2015 11:00 am UTC 45 mins
    Michael Hausenblas, Chief Data Engineer, MapR Technologies
    Processing data from social media streams and sensors devices alike, in real-time, is becoming increasingly prevalent and there are plenty open source solutions to choose from.

    In this Webinar we will help practitioners decide what to use for which use case by comparing three popular ASF open source stream processing frameworks: Apache Storm, Apache Samza and Apache Spark Streaming.Last but not least, we will discuss best practices and review real-world customer use cases from the stream processing domain.
  • Leveraging Hadoop - with or without on-premise infrastructure Apr 22 2015 10:00 am UTC 45 mins
    Lee Carter, VP EMEA, Bright Computing
    In this presentation, Lee Carter, VP EMEA at Bright Computing, will talk about Hadoop in the cloud, and how to leverage Hadoop without necessarily having to invest in on-premise infrastructure. Lee will explore the challenges faced when setting up, operating, using and managing Hadoop clusters. He will discuss user demand for Hadoop to be easier, and look at how the shortage of skilled Hadoop resources is impacting the industry. Lee will investigate the idea that better management tools can solve these challenges.
  • HDFS TDE: Native Encryption in Hadoop Apr 22 2015 9:00 am UTC 45 mins
    Alberto Romero, Senior Hadoop Technical Architect, Hortonworks
    HDFS Transparent Data Encryption has been added to HDFS 2.6, and it finally provides with a solution to data encryption on a higher level than the OS one whilst remaining native and transparent to Hadoop. It aims cover the gap that existed for privacy and security regulations that many industries require, without having to introduce a third-party solution into the mix. This way, having encryption at HDFS level gives an optimal context for policy definition that is relevant to the industry, while remaining transparent to the applications running on Hadoop.

    Join this webinar to learn:

    -where HDFS Transparent Encryption sits within the Hadoop security framework
    - an introduction to the technical details including how to create Encryption Keys and Encryption Zones
    - Interaction with the Apache Key Management System (KMS) and the encryption/decryption data flow
    - Future work in the space of Hadoop security in general, and encryption in particular
  • Big Data Virtualization with SAS Federation Server Recorded: Apr 15 2015 24 mins
    Matthew Magne, Product Marketing Manager, Data Management, SAS and Johnny Starling, Senior Technical Architect, SAS
    Here’s the good news. While the number of data sources organizations face is rapidly increasing, the cost to store data has never been cheaper. This trend – as well as big data technologies like Hadoop – has led to more valuable insights for organizations.

    But it’s also led to IT departments overburdened with requests from the business users they support. So where do we go from here?

    View this webinar that discusses data federation, a type of data virtualization that:

    • Provides a centralized governance and security layer.
    • Speeds the creation of virtual data views.
    • Makes it easier for business users to access the data they need.

    We’ll also demonstrate technologies like big data virtualization, federated data-as-a-service and data masking.
  • Demystifying In-Memory Analytics Recorded: Apr 15 2015 38 mins
    Scott Chastain, Systems Engineer Manager, SAS and Tapan Patel, Product Marketing Manager, SAS
    SAS® In-Memory Analytics is built for speed. It enables you to access unstructured and structured data and tackle complex analytical computations blazingly fast. But it doesn’t end there.

    SAS In-Memory Analytics also delivers incremental value from big data so that you can find more lucrative opportunities, detect risks and improve targeted marketing.

    View this webinar to learn why SAS In-Memory Analytics can help you:

    • Tackle problems never before considered due to computing constraints.
    • Draw timely insights from Hadoop.
    • Perform self-service data discovery.
    • Run iterative and interactive analytics scenarios.
  • Visualize Data for Actionable Insight into Your B2B Processes Recorded: Apr 12 2015 2 mins
    OpenText DEMO
    An overview of how businesses can gain visibility into B2B transactions to speed decision-making, respond to changing customer and market demands, and optimize business processes.
  • Discover how to simplify your LMS Experience -LearnFlex SimplifyDPS Recorded: Apr 12 2015 47 mins
    Joel Kristensen, Solutions Consultant, OpenText
    LearnFlex Learning Management Solution (LMS) enables your organization to create and share knowledge in a simple, automated, and integrated way. LearnFlex makes the process of automating, tracking, managing, and reporting on all aspects of your enterprise-level learning initiatives easier—all while demonstrating a clear return on investment.
  • Analytics Architectures for the Era of Abundance Recorded: Apr 10 2015 28 mins
    Gary Spakes, Senior Systems Engineer Manager, SAS
    Opportunities and risks abound for IT organizations. At each digital step, the diverse data that organizations need to manage and analyze continues to grow.

    Is IT ready for the “Era of Abundance”? Or is it constantly stuck in the vicious cycle of the “Era of Scarcity”?

    Hosted by Gary Spakes of SAS, this on-demand webinar will prescribe an optimal set of information architecture options involving Hadoop for data management, data discovery and analytics.

    You’ll learn how to:

    • Embrace analytics by looking beyond technology and existing organizational mindsets.
    • Modernize your analytics architecture to integrate with what you have.
    • Meet current and future needs around different types of users, workloads and scalability.
    • Make the most intelligent decisions when building a big data architecture.
Managing and analyzing data to inform business decisions
Data is the foundation of any organization and therefore, it is paramount that it is managed and maintained as a valuable resource.

Subscribe to this channel to learn best practices and emerging trends in a variety of topics including data governance, analysis, quality management, warehousing, business intelligence, ERP, CRM, big data and more.

Embed in website or blog

Successfully added emails: 0
Remove all
  • Title: Scalable Cross-Platform R-Based Predictive Analytics
  • Live at: Dec 12 2013 7:00 pm
  • Presented by: Mario Inchiosa, US Chief Scientist at Revolution Analytics
  • From:
Your email has been sent.
or close
You must be logged in to email this