Past Webinars

Applying Satellite Data for Public Good

Event Info

icon_calendar.jpgJune 29, 2021
icon_clock.jpg6pm EDT
icon_stopwatch.jpgDuration: 1 hour
Philadelphia_webinar_March_2021.jpg

Robert Cheetham
President and CEO of Azavea

Falling launch costs have combined with the microelectronics, optics, and fast hardware iterations from smartphones to create a revolution in Earth observation satellites. A few bus-sized satellites are being replaced by constellations of dozens or hundreds. Further, optical and multispectral data are being supplemented with radar and hyperspectral instruments. The results include avalanches of data, dozens of well-funded startups, and a widening array of potential applications. While the satellite industry was built on the back of national defense and intelligence budgets, today's companies are looking beyond that to commercial and humanitarian use cases. This talk will outline some of the latest open source tools and standards for working with Earth observation imagery, describe several contemporary use cases, and suggest some important technical challenges ahead.

View Recording here!

A Recipe for Analytics Success (What I Learned the Hard Way so You Don't Have to)

Event Info

icon_calendar.jpgSeptember 29, 2020
icon_clock.jpg6pm EDT
icon_stopwatch.jpgDuration: 1 hour
Philadelphia_webinar_March_2021.jpg

Dr. Erick Wikum
Independent Analytics Consultant,Wikalytics, LLC.

Dr. Erick Wikum is an independent analytics consultant for his own firm, Wikalytics, LLC. Over a nearly 30 year career in the practice of operations research and analytics, Erick has served as an internal and external consultant for numerous organizations in a variety of industries including transportation and logistics, retail and agribusiness. Erick is an active INFORMS member, recently serving as president and Subdivisions Council representative of the Analytics Society. Erick is an associate editor of the INFORMS Journal on Applied Analytics and is slated to serve as general chair of the 2022 INFORMS Business Analytics Conference. Erick earned M.S. and Ph.D. degrees in operations research from Georgia Tech and a B.S. in mathematics and operations research from the U.S. Air Force Academy.

The hype surrounding data analytics would have you believe that combining one part data with one part mathematics, stirring liberally and salting to taste will produce a dish sure to please, but the truth is far more complicated.  You see, when it comes to achieving success with analytics, it is not just what you do, but how you do it.  In this talk, Erick Wikum will share 10 hard-earned lessons for how you, as an individual contributor, can deliver real value with analytics.

View Webinar Recording

Event Info

icon_calendar.jpgSeptember 29, 2020
icon_clock.jpg6pm EDT
icon_stopwatch.jpgDuration: 1 hour

Speakers

Presented by Carolyn Mooney and Ryan O'Neil, Co-founders of Nextmv

The on-demand economy is exploding. With it, consumers demand immediate access to everything from meals to electronics. We will discuss the challenges such as highly dynamic business models create, and new optimization and simulation technologies for addressing them.

View Webinar Recording

Use of Machine Learning and AI at Comcast to Drive Business Objectives & The Use of Machine Learning to Predict Customer Out-of-Home Network Service Issue

Event Info

icon_calendar.jpgOctober 27, 2020
icon_clock.jpg6pm EDT
icon_stopwatch.jpgDuration: 1 hour

Speakers

Ranjit Jangam
Executive Director of Data Science, Comcast

Machine learning and data science plays significant role at cable & telecommunication industries. There is vast amount of data with 3600 view to develop models to drive revenue & growth, manage risk, improve customer experience, provide personalized experiences to consumers, developing innovative & reliable product experiences. Due to excessive competition in the industry, emphasis on data science driven machine learning algorithms including parametric or non-parametric, big data and AI tools has been severe and never been most important. Objective of this session is to review complete end to end cycle of developing machine learning models at scale including feature engineering, model development, model deployment, data & model governance and review real-world business applications of predictive models in the cable industry.

Rama Mahajanam
Director of Machine Learning, Comcast

With the COVID-19 pandemic starting mid-March, 2020, the rapid development of an “outside network check” provided an opportunity for the ML/AI modeling team to gather better features and labels. With a keen desire to keep technicians and customers isolated, the team explored new ML/AI models. These new models are trained to use cloud-based RF measurements. These measurements include remote telemetry from DOCSIS, and other equipment logged by collection systems. Another set of measurements were taken at the tap and ground block, finally offering a way to segment the network and train the machines differently. We will review a few highlights of this fascinating exercise, which is currently underway.