Hi [[ session.user.profile.firstName ]]

How to build a geolocated recommender using Spark ML, Cassandra and Akka

Natalino introduces a collection of machine learning techniques to extract insights from location-based social networks such as Facebook, demonstrating how to combine a dataset of venues’ check-ins with the user social graph using Spark and how to use Cassandra as a storage layer for both events and models before sketching how to operationalize such predictive models and embed them as microservices. In terms of data architecture this processing follows closely the SMACK stack.

The proposed data-pipeline is effective at detecting patterns in the sequences of visited venues and recommend relevant venues to visit next, based on the user, and friends location's history as well as the venue popularity graph. Natalino Busa explains how these predictive analytics tasks can be accomplished by using Spark SQL, Spark ML, and just a few lines of Scala and Python code.
Recorded Jul 14 2016 46 mins
Your place is confirmed,
we'll send you email reminders
Presented by
Natalino Busa, Head of Applied Data Science at Teradata
Presentation preview: How to build a geolocated recommender using Spark ML, Cassandra and Akka

Network with like-minded attendees

  • [[ session.user.profile.displayName ]]
    Add a photo
    • [[ session.user.profile.displayName ]]
    • [[ session.user.profile.jobTitle ]]
    • [[ session.user.profile.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(session.user.profile) ]]
  • [[ card.displayName ]]
    • [[ card.displayName ]]
    • [[ card.jobTitle ]]
    • [[ card.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(card) ]]
  • Channel
  • Channel profile
  • How to Implement Machine Learning Patterns into Data Visualizations Aug 24 2017 5:00 pm UTC 60 mins
    Dr. Umesh Hodeghatta Rao, CTO, Nu-Sigma Analytics Labs
    Data visualization must be intuitive in order for non-IT business leaders to see data patterns. Representing data in a graphical or pictorial format is easy, but constructing the data in the best and most logical way can be tricky.

    In this session, Umesh will talk about how to represent data simply to make quicker and better business decisions. He will walk through several data visualization techniques through business cases and examples. By the end of the session, you will not only know different data visualization techniques, but also have an understanding of circumstances under which each technique should be used and the best way to represent particular data sets for different business cases.
  • Unsupervised learning to uncover advanced cyber attacks Aug 22 2017 10:00 am UTC 45 mins
    Rafael San Miguel Carrasco, Senior Specialist, British Telecom EMEA
    This case study is framed in a multinational company with 300k+ employees, present in 100+ countries, that is adding one extra layer of security based on big data analytics capabilities, in order to provide net-new value to their ongoing SOC-related investments.

    Having billions of events being generated on a weekly basis, real-time monitoring must be complemented with deep analysis to hunt targeted and advanced attacks.

    By leveraging a cloud-based Spark cluster, ElasticSearch, R, Scala and PowerBI, a security analytics platform based on anomaly detection is being progressively implemented.

    Anomalies are spotted by applying well-known analytics techniques, from data transformation and mining to clustering, graph analysis, topic modeling, classification and dimensionality reduction.
  • Visualizing Smart Cities: How Data Visualization can help shape our communities Jun 23 2017 12:00 pm UTC 60 mins
    Andy Kriebel, Head Coach at The Data School, Tableau Zen Master & Eva Murray, Tableau Evangelist at EXASOL, Tableau Trainer
    Whenever there is data, there is the chance to visualize it and gain valuable insights that can drive change and improvements. Governments have realized the potential that data holds for transforming our towns, cities, living spaces and communities to better address the needs of our modern society.

    Governments may want to change public transport services to suit commuters who move away from city centers due to increasing living costs, or develop programs that deliver more support services to areas showing high incidences of mental illnesses, or simply monitor bike traffic to assess the necessity of additional cycle lanes and bike share programs in our capitals. Data and data visualization can help us identify the needs of our communities and can support us in addressing them effectively.

    In this webinar Andy and Eva will present examples of Government using data visualization to improve services for communities and will share how you can get involved through analyzing open data and becoming part of the wider 'dataviz' community.
  • IoT Business Models Need a Reality Check Jun 23 2017 11:00 am UTC 45 mins
    Michael Kuegeler, Principal Solution Architect Magic Software
    We will examine challenges regarding business model design in the emerging context of the Internet of Things (IoT).
    An unrefined IoT business model implies a significant risk in terms of investment and implementation.

    The key question is, "How can IoT application models be subjected to a reality check taking into account challenges pertaining technology, organization and target markets?"
  • How to get data moving: Impact of big data on transportation Jun 23 2017 10:00 am UTC 45 mins
    Arwen Smit, Head of Marketing, dovu
    Moving from A-B is slowly being revolutionised through data. Car-sharing and ride-hailing are just the beginning. Thousands of connected devices are currently monitoring data points, and although stand-alone analysis can be useful, true innovation occurs when these data sets are combined to transform into something new.

    In the near future, IoT data explosion and the API revolution will collide to change city planning, urban movement and the role of the car in the 21st century.

    First off, we set out to understand what big data means in the context of transportation, answering questions such as what is it, where is it coming from, and what can you do with it.
    - Next, we'll zoom out and apply these learning to transport innovation in a wider context, considering how it will influence concepts such as urban movement, social mobility, and quality of life.
    - Finally, we'll discuss the relationship between open data and innovation.
  • Interpreting IoT Data: Context is Everything Jun 23 2017 8:00 am UTC 45 mins
    Dr. Boris Adryan, Head of IoT & Data Analytics, Zühlke Engineering GmbH
    For decades “things” have been connected to the Internet. Embedded in carefully planned end-to-end solutions, the what and why of the data arising from these devices has often been hard-coded. In other words, in the M2M world, it is usually clear from the outset what is going to happen with the data. In a future IoT, this won’t necessarily be the case. In a world full of connected devices, the meaning and the potential of the device data is only going to become clear in the context where it is needed in.

    But how can software tell that your connected thermometer is useful for a medical application, or that a car in the drive way is likely an indicator of your partner’s presence? This is where device catalogues, information models and ontologies come in handy.

    While the talk is not specifically tailored towards a smart city focus, it should become clear how these technologies can be useful in such environment.
  • Tableau in the Cloud: A Netflix Original Jun 22 2017 1:00 pm UTC 75 mins
    Albert Wong - Reporting Platform Manager, Netflix
    See how Netflix built its analytics in the cloud with Tableau and Amazon Web Services

    Building out a data platform doesn't have to be like building a House of Cards, and our friends at Netflix know this better than anyone else. With 86 million members and counting, and more than 700 billion events per day, Netflix has had to expand their data capabilities by developing a scalable and flexible analytics platform built on Tableau and AWS.

    Attend this webinar to hear from Albert Wong, analytics expert at Netflix, to see how they simplified their data stack by building a data lake/data warehouse strategy which allows Netflix to collect and store massive amounts of data, supporting thousands of Tableau users with managed data.

    You'll learn about:

    How to set up effective analytics on top of enormous data sets
    How Netflix serves large groups of people with governed data
    The details of Netflix's data lake/data warehouse strategy
    How Netflix manages Hadoop with Tableau
  • Fog Computing in Mobile Network Jun 22 2017 8:00 am UTC 45 mins
    Adnyesh Dalpati, Director Solutions Architect at Alef Mobitech
    Fog computing has the potential to resolve the issues with network latency since the media rich content can be delivered through such nodes directly.

    Fog Computing inside the mobile network providers opens up a window of revenue opportunities for MNO's and creates a innovative space in content & application delivery platform.

    Join this webinar to learn how to tackle the different challenges with fog computing and its role in the IoT cycle.
  • Toward Internet of Everything: Architectures, Standards, & Interoperability Jun 21 2017 3:00 pm UTC 60 mins
    Ram D. Sriram, Chief of the Software and Systems Division, IT Lab at National Institute of Standards and Technology
    In this talk, Ram will provide a unified framework for Internet of Things, Cyber-Physical Systems, and Smart Networked Systems and Societies, and then discuss the role of ontologies for interoperability.

    The Internet, which has spanned several networks in a wide variety of domains, is having a significant impact on every aspect of our lives. These networks are currently being extended to have significant sensing capabilities, with the evolution of the Internet of Things (IoT). With additional control, we are entering the era of Cyber-physical Systems (CPS). In the near future, the networks will go beyond physically linked computers to include multimodal-information from biological, cognitive, semantic, and social networks.

    This paradigm shift will involve symbiotic networks of people (social networks), smart devices, and smartphones or mobile personal computing and communication devices that will form smart net-centric systems and societies (SNSS) or Internet of Everything. These devices – and the network -- will be constantly sensing, monitoring, interpreting, and controlling the environment.

    A key technical challenge for realizing SNSS/IoE is that the network consists of things (both devices & humans) which are heterogeneous, yet need to be interoperable. In other words, devices and people need to interoperate in a seamless manner. This requires the development of standard terminologies (or ontologies) which capture the meaning and relations of objects and events. Creating and testing such terminologies will aid in effective recognition and reaction in a network-centric situation awareness environment.

    Before joining the Software and Systems Division (his current position), Ram was the leader of the Design and Process group in the Manufacturing Systems Integration Division, Manufacturing Engineering Lab, where he conducted research on standards for interoperability of computer-aided design systems.
  • Computational Behaviour Modelling for the Internet of Things Jun 21 2017 12:00 pm UTC 45 mins
    Dr. Fahim Kawsar, Director of IoT Research at Nokia Bell Labs
    We are observing a monumental effort from the industry and academia to make everything connected. Naturally, to understand the needs of these connected things, we need a better understanding of humans and where, when, and how they interact. This behavioural understanding would help us to create digital services and capabilities that fundamentally change the way we experience our lives.

    In this talk, I will explore the system and algorithmic challenges in modelling human behaviour. I will discuss how mobile and wearable devices together with the wireless network can be used as a multi-sensory computational platform to learn and infer human behaviour and to design user-centred connected services across Enterprise, Urban City and Lifestyle.

    Dr Fahim Kawsar leads the Internet of Things research at Bell Labs and holds a Design United Professorship at TU Delft. His current research explores novel algorithms and system design techniques to build transformative multi-sensory systems for disruptive mobile, wearable and IoT services. He borrows tenets from Social Psychology, learns from Behavioural Economics and applies Computer Science methods to drive his research. He is a frequent keynote, panel and tutorial speaker, hold 15+ patents, organised and chaired numerous conferences, (co-)authored 100+ publications and had projects commissioned. He is a former Microsoft Research Fellow and has worked before at Nokia Research, and Lancaster University. His work and publications can be viewed at http://www.fahim-kawsar.net.
  • SAP Cloud Analytics - get control on BigData Jun 21 2017 10:00 am UTC 60 mins
    Iver van de Zand
    BigData requires processing performance but even more it requires agility of your cloud analytics. Iver will demonstrate how today's SAP BusinessObjects Cloud has leading capabilities when used in a highly complex and dynamic environment accessing extreme data volumes.
  • Big Data and real time analytics in the IoT: From measurement to knowledge Jun 21 2017 9:00 am UTC 45 mins
    Raquel López Alarcón, Sofia2 Platform Architect
    Do you want to get actual knowledge from your data, to understand it and to predict what will happen next? We will see what it takes from the device to the dashboard.

    In this webinar, we will discuss:
    - Use cases of IoT Analytics in different areas.
    - Architectural components & strategy required for a complete IoT solution.
    - Application Example.
  • Big Data analytics for IoT: Making sense of data from sensors Jun 21 2017 8:00 am UTC 45 mins
    Muralidhar Somisetty, Co-founder and CTO, Innohabit
    Big data analytics is undoubtedly one of the most exciting areas in computing today, and remains an area of fast evolution. Thanks to the data deluge from millions of sensors from IoT networks, it is humanly impossible to analyse and make sense of the data from sensors without analytics tools and processes.

    In this webinar, we will go over basics of big-data analytics, how analytics is different from traditional data warehouses or business intelligence systems, different tiers of data analytics etc., We will also see different use-cases of IoT from Smart Home to Transporation to Smart City context and how analytics can be applied for various use-cases for actionable insights.

    Webinar also briefly touches upon machine learning tools / techniques that are available as-a-service on cloud today.
  • Apache Zeppelin in the Enterprise: Build, Secure & Reuse Data Pipelines w Spark Jun 16 2017 2:00 pm UTC 45 mins
    Eric Charles, Founder at Datalayer
    Apache Zeppelin is a great entry point for Data Scientist to explore and model Data.

    In an enterprise environment, this exploration tool can be used to assemble pipeline of notes and deploy them in a production system.

    In this webinar, you will learn how to:

    + Create functional notes corresponding to each step of the analysis.
    + Call a note from another note.
    + Pipe multiple notes together.
    + Create a deployable unit and run this unit on a remote cluster
  • Jupyter is more than notebooks, JupyterLab and beyond! (Webinar) Jun 1 2017 5:00 pm UTC 60 mins
    Ali Marami
    Join us to learn about JupyterLab, the new open source computational environment for Jupyter. Increase the performance of your data science projects by working in an integrated environment for your notebooks, editor, terminal and console. We will also discuss R-Brain cloud platform and its new R Python Cloud IDE which is built on JupyterLab.
  • Ask the Innovation Expert: Ask me Anything with David Siegel Jun 1 2017 3:00 pm UTC 60 mins
    David Siegel, Blockchin, Decentralization and Business-agility Expert
    David is a 22-time serial entrepreneur with 20 years in Silicon Valley and 13 years in New York City starting companies. He has written five books about the web and business. He's an expert in corporate culture, collaboration, innovation, design, typography, data, blockchain, crypto-investing, venture/angel investing, management, business, decentralization, macro economics, and dark chocolate. You can read some of his key essays here:

    www.theculturedeck.com
    www.globalbetaventures.com
    www.openstanford.com
    www.decentralstation.com
    www.2030.io

    David is currently starting 20|30, an open platform for blockchain innovation. This is an ask-me-anything format with people typing in questions and david answering. He'll talk about current events in the world of blockchain and innovation, tell stories of working at Pixar, his new token offering, his new legal project, and you never know what will happen, so join the fun on June 1st!

    Ask David your most challenging business question - he's happy to offer suggestions.
  • Venture Investing and Entrepreneurship with David Siegel Live 60 mins
    David Siegel, Angel Investor and Serial Entrepreneur
    David has been an angel investor for 20 years and has worked with Steve Jobs, Ed Catmul, and others in Silicon Valley. He played a significant role in the development of the Worldwide Web, has written five books, and coaches startups. Last year he was a candidate to be the next dean of Stanford business school. This year, he’s starting his 22nd company.

    In this 60-minute webinar, you'll learn what really causes startups to fail, why you shouldn't build an MVP, explore how you can use Kanban to improve team coordination, why understanding your market is more important than understanding your product, raising money from crazy investors, why you shouldn't go to business school, and building an agile culture. Here are some of his writings:

    www.theculturedeck.com

    www.openstanford.com

    www.globalbetaventures.com

    This webinar is for both early-stage investors and entrepreneurs at all levels.
  • IT Relevance in the Self-Service Analytics Era Recorded: May 23 2017 61 mins
    Kevin McFaul and Roberta Wakerell (IBM Cognos Analytics)
    There’s no denying the impact of self-service. IT professionals must cope with the explosive demand for analytics while ensuring a trusted data foundation for their organization. Business users want freedom to blend data, and create their own dashboards and stories with complete confidence. Join IBM in this session and see how IT can lead the creation of an analytics environment where everyone is empowered and equipped to use data more effectively.

    Join this webinar to learn how to:


    · Support the analytic requirements of all types of users from casual users to power users
    · Deliver visual data discovery and managed reporting in one unified environment
    · Operationalize insights and share them instantly across your team, department or entire organization
    · Ensure the delivery of insights that are based on trusted data
    · Provide a range of deployment options on cloud or on premises while maintaining data security
  • Makeover Monday: improving the way we visualize data, one chart at a time Recorded: May 15 2017 63 mins
    Andy Kriebel, Head Coach at The Data School, Tableau Zen Master & Eva Murray Tableau Evangelist at EXASOL, Tableau Trainer
    Join Andy Kriebel and Eva Murray to hear about #MakeoverMonday, the popular social data project linking hundreds of members from the global data visualization community in an effort to create better charts and more useful data stories.

    In this webinar Andy and Eva will share how Makeover Monday not only results in thousands of better data visualizations, but also helps people find their 'voice' in the community and land their dream jobs all while becoming better analysts and story tellers.

    They will also discuss the challenge for week 20, present their own makeovers, and the design and thought process that went into them.
  • Fighting Fraud with Graph Databases Recorded: May 10 2017 55 mins
    Kaush Kotak, Project Manager Cambridge Intelligence; Gehirg Kunz, Project Manager, Datastax
    The need to combat fraud can make or break a company. Threats are at an all-time high, but thankfully so are the availability of tools to help us combat them. Modern fraud detection has significant engineering challenges. From managing the ingestion and scale, to the analysis of those patterns in real-time.

    ✓ How companies are fighting fraud using systems with graph technologies at their core.

    ✓ Tools, workflows, and techniques that drive critical tasks like fraud detection and regulatory compliance.

    ✓ A live demo of Cambridge Intelligence’s KeyLines technology, showing a visual approach to transforming data from DSE Graph into valuable intelligence that helps to detect, predict and prevent fraud.
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: How to build a geolocated recommender using Spark ML, Cassandra and Akka
  • Live at: Jul 14 2016 3:00 pm
  • Presented by: Natalino Busa, Head of Applied Data Science at Teradata
  • From:
Your email has been sent.
or close