What are the ingredients for an a-ha moment in financial services where a trade is discovered, a risk exposed or a behavior illuminated? It is not luck, or fate, or even hard work. It is the intersection of tools, technology and domain knowledge. This webinar covers how sophisticated market participants are engineering these a-ha moments by tackling massive, proprietary data with next-generation computing tools and good old fashion common sense to “see” what others cannot.
The conversation and demonstration will be hosted by MapD founder and CEO, Todd Mostak and EVP of Orbital Insights, A.J. DeRosa and will cover the rise of the proprietary dataset, the use of GPU-powered analytics and how the combination of speed, scale and domain expertise is changing the financial services industry.
RecordedFeb 14 201750 mins
Your place is confirmed, we'll send you email reminders
Mike Flaxman, Spatial Data Science Lead, OmniSci & Adam Edelam, Federal Solutions, OmniSci
Today’s geospatial professionals are increasingly called upon to deliver content in the form of interactive web apps. This can be challenging with traditional architectures, both because of the inflexibility of conventional template-based approaches, and due to major performance issues when delivering large geotemporal data across the web. OmniSci is a GPU database with built-in high performance geographic rendering (capable of handling literally billions of features). OmniSci’s Immerse web application allows end users to build or customize a wide range of dashboards themselves. This workshop will present some typical GEOINT applications delivered as interactive dashboards, and will drill down into the construction of one of them in detail. Attendees will learn all three levels of a modern web stack. We will start by reviewing the capabilities of OmniSci Immerse. Next, we will dig into the capabilities of OmniSQL, which uses postGIS-like syntax to expose powerful geoprocessing tools. Lastly, we will walk through Jupyter Notebook integration, and show how Python and the pymapd library can be used to construct powerful workflows.
1. What is GPU analytics and why should I care? How can I get it?
2. How to create powerful geotemporal dashboards in Immerse
3. Using omniSQL to handle geotemporal data at scale
4. Leverage Jupyter notebook integration to optimize data pipelines supporting interactive use cases
Dr. Mike Flaxman, Spatial Data Science Practice Lead, OmniSci & Brian Kummer, Director West, OmniSci
Conventional vegetation management by power utilities has been based on 3-year revisit scheduling and largely ground-based monitoring. These efforts have not been minor - utilities spend rather many millions of dollars per year. But recent events in California have made it clear that they are completely insufficient. OmniSci offers power utility companies an alternative solution based on continuous monitoring data and fire science. Our GPU-accelerated analytics platform integrates disparate datasets, including near-real time satellite, LIDAR and weather and micro-demographics data, in order to assess risk dynamically. Thanks to the power of cloud ETL and GPU-accelerated geoprocessing, we are able to put analysis-ready data interactively in front of key utility managers.
During this session, we will discuss how GPU-accelerated analytics can help visualize vegetation risk and help utility companies take action on wildfire prevention. From vegetation management, to balancing the electrical grid, to smart meter analysis, fleet management, and beyond, GPU-accelerated analytics is a breakthrough technology that allows utility and vegetation management companies to visualize their massive IoT and telematics datasets. This unprecedented level of data visualization improves vegetation management plans - including invasive vegetation management - and wildfire prevention methods to help utility companies reduce costs, catastrophes, and to keep the lights on. We will show this capability through a demonstration of California fire history and risk to infrastructure dataset on the OmniSci GPU-accelerated analytics platform .
Herfini Haryono, VP Vertical Industry, OmniSci & Jared Ritter, Sr. Director Analytics & Automation, Charter Communications
As one of the earliest adopters and collectors of big data, Telcos are now leading the world in addressing the challenges that come from having lots of data, but oftentimes too few insights. Some of those challenges include:
- Multiple Sources of Data
- Lengthy ETL Processes
- Limited Data Science Teams
- Growing Data Science Teams
- Multiple Service Offerings
In this talk, Charter Communications and OmniSci will show how they are addressing these challenges for the telecom industry. We’ll demonstrate using GPUs and OmniSci’s accelerated analytics platform for fast queries and joins of multiple sources of data, interactive visualizations of spatiotemporal data, and integration with the latest AI/ML tools for running complete data science pipelines without the need for a large team of data scientists.
Dr. Mike Flaxman, Spatial Data Science Lead, OmniSci
5G Is on its way to consumer markets in the coming years. 5G network infrastructure is expected to completely revolutionize network connectivity. With proper 5G network planning and optimization, telecommunications companies will be able to deliver better customer experiences, solve complex problems, and move their business forward. 5G and big data go hand-in-hand. Experts predict 5G data usage could increase by 10-14 times current figures. This astronomical influx of 5G data creates an incredible opportunity for telco companies to explore real-time 5G insights and leverage 5G data analytics for 5G network optimization that gives your customers fast and consistent network connectivity at all times.
Abhishek Damera, Data Scientist, Product Management & Dr. Mike Flaxman, Spatial Data Science Practice Lead, OmniSci
Undercounting within the US National Census has always been a significant issue for specific populations, such as those with complex family structures. With the rise of Covid-19 and a shortened counting period, this year’s census is probably the most challenging to date. How can data science and new datasets help?
We found that modern machine learning techniques can provide the basis for much-improved census undercount prediction. We also found that the addition of GPS data and point of interest data increased model accuracy and provided further insight into behavioral factors beyond demographics which significantly affect undercount.
Kim Pevey, Software Engineer, Quansight & Tony Fast, Developer Advocate, Quansight
Holoviz is a framework for visualization and application development that encourages annotating data to generate rich interactive visualizations and dashboards. Holoviz provides interfaces to multiple plotting backends in python including Bokeh and Matplotlib. This talk, will demonstrate brand new functionality showing how Omnisci, through the ibis framework, can now plot data using hvplot or holoviews. We’ll demonstrate these novel integrations with Omnisci in a series of computational notebooks that visualize different projections of Omnisci data, and deploy them as applications.
Kim Pevey, Software Engineer, Quansight & Tony Fast, Developer Advocate, Quansight
This work discusses the open source technologies used to bring Omnisci to the greater scientific python ecosystem. These efforts allow Omnisci data to be analyzed in Jupyterlab, query data from omnisci databases, interoperate with pandas dataframes, and visualize information. We’ll walk through several computational notebooks that cover the capabilities of Omnisci interacting with different data analysis and visualization tools in Python. Throughout these exercises we’ll highlight the open source packages and technologies that amplify OmniSci’s abilities with tools like ibis, pandas, altair, and holoviews.
Abhishek Damera, Data Scientist & Dr. Mike Flaxman, Spatial Data Science Practice Lead, OmniSci
Human mobility patterns have been studied for millennia and are of obvious interest to transportation infrastructure and retail planners among others. It is only in the last few years that consumer GPS and cell phones have allowed observations of large samples over wide areas and long periods of time. Yet the mechanisms used by these services vary widely and should be expect by default to contain demographic sampling biases. We have conflated these GPS-derived spatial event stream data sources with traditional census block group data in order to quantify and calibrate them. We have used these adjustments to produce the first known map of US populations at an hourly basis before and during the COVID-19 epidemic. In order to protect individual privacy, we have deployed an explicit aggregation system using variable-sized hexagonal bins. Nonetheless, our maps represent much higher resolution data than conventionally available, ranging from 50m in dense urban areas to 1km in non density rural areas. Because sampling along roads is much higher than elsewhere, we are able to provide traffic estimates at high spatial precision nationally. In addition to overall population density, we have used overnight device dwell times in residential areas to infer the hourly demographic characteristics of areas based on device trajectories.
OmniSci is designed for big data but for custom computations the data needs to be retrieved to a client machine. This puts a ceiling on data sizes based on both network speed and local hardware resources. What if we could send the algorithm to the data instead?
This talk presents the Remote Backend Compiler (RBC), a package that affords OmniSci database capabilities to execute functions written in Python inside SQL queries. Our approach uses Numba, a high performance Python compiler, to generate fast low level machine code of user defined functions. We will learn more about how the RBC connects open source technologies, like NumPy and Numba, to the OmniSci database. Lastly, we conclude with a demonstration using an applied example of the Black-Scholes financial model. This will highlight how to leverage the newly added User-Defined Functions and User-Defined Table Functions capabilities with OmniSci.
Altair is a lovely tool that lets you build up complex interactive charts in Python. Ibis is also a lovely tool that lets you use a Pandas-like API to compose SQL expressions in OmniSci and other backends. By tying them together you can use the familiar syntax of Pandas, combined with the expressive power of Vega and Vega Lite, to visualize large amounts of data stored in OmniSci. This talk will walk through a number of examples of using this pipeline and then go through how it works.
In this overview talk, we'll showcase how Data Science workflows are a key part of the OmniSci platform, since the launch last year. We will showcase new integrations of OmniSci within the open PyData ecosystem, new foundational capabilities within the open source OmniSci engine useful for data science, and discuss joint work with our collaborators at Intel and Quansight, as well as some exciting future plans
In this session you will learn how to operationalize the insights gained through data exploration. We will walk the audience through a logistics use-case where modern AI techniques applied to the right data can accelerate optimization plans by many orders of magnitude and unlock new sources of revenue.
Eliot Eshelman, VP HPC Initiatives, Microway & Michael McCracken, Federal Sales Engineer, OmniSci
Today's agencies face a huge challenge: they have an avalanche of data from billions of sources but struggle to deliver information dominance at the speed of thought.
During this webinar, the team from OmniSci and Microway will show how GPU-accelerated analytics solve today's data analytic challenges for government and enable agencies to:
- Combine visual analytics and geo-visualization
- Attack problems previously considered too large, too complex or too time consuming
- Eliminate downsampling, pre-aggregation, and partial visibility
- Convert millions and billions of records of data into better, more actionable information
- Fuse data from multiple data providers
- Reduce costs and the power necessary to complete the mission
To show these capabilities for all government & agency customers, we will analyze flight traffic patterns during the COVID-19 pandemic as an example unclassified dataset.
With the OmniSci GPU-accelerated analytics platform and Microway’s WhisperStation, we will trace insight from the trajectory of flight patterns during stay-at-home orders, reopening of airports and commercial airline flights, and commercial airline flight destinations and size of planes using data from multiple data providers fused under a single pane of glass. These same capabilities can translate to your mission and unique data.
:During this session we’ll explore the spread of the COVID-19 global pandemic by analyzing and visualizing billions of rows of records with near-zero latency. Adam Edelman, Federal Solutions Engineer at OmniSci, will explain OmniSci’s GPU-accelerated analytics platform before providing a demonstration of its powerful capabilities.
Learn how massive data sets of anonymized data can be leveraged for contact tracing, understanding population movement, and identifying trends around specific points of interest.
Learn how to build cohorts to optimize analytic queries and rapidly spot new pandemic hotspots.
Learn how OmniSci bookends data science workflows by integrating with popular data science tools.
Jon Stresing, Account Manager DoD, NVIDA & David Goodwin, Director DoD, OmniSci
The presence of extraordinary amounts of data, to train on, to learn from, and to explore, represents a golden age of computing. But beneath this incredible opportunity lies a massive challenge. Traditional CPU compute cannot keep pace with the growth in data, and as a result, even the most sophisticated organizations are unable to unlock its value. There is a new approach to computing and analytics that solves this yawning gap, involving the application of GPU compute from NVIDIA and analytical software from OmniSci Join OmniSci and NVIDIA to learn about GPUs, GPUs AI/ML, and how you can use NVIDIA and OmniSci for big data analytics and data science initiatives.
Cecile Tezenas du Montcel, Advanced Compute & Solutions Business Development Manager, HP
n a world of emerging technologies such as 5G and IOT, the data volume is exploding; 80% generated at the edge in conjunction with phenomenal GPU processing power enhancement. Shifting intelligence to the point data is created opens a new world of possibilities: saving cost, enabling real time access & increasing security. HP Z workstations are the perfect way to access data sets and run models locally in combination with OmniSci solutions.
Eric Kontargyris, Principal Solutions Consultant, OmniSci
With the emergence of 5G, Digital Service Providers (DSPs) need to transform their business assurance solutions to support the dynamism and complexity that 5G offers. Business Assurance must adopt artificial intelligence, machine learning and Open API’s for the 5G verticals’ digital ecosystems to support the DSP’s business goals of improved revenue and customer experience beyond the traditional value chain. This demo will demonstrate how to use AI to assure 5G services, including 5G slicing, perform as planned with API-based use cases including customer experience, churn-management and fraud-management.
How to engineer serendipity in financial servicesTodd Mostak, Founder & CEO of MapD and A.J. DeRosa, EVP & Head of Global Sales at Orbital Insight[[ webcastStartDate * 1000 | amDateFormat: 'MMM D YYYY h:mm a' ]]50 mins