Our world is drowning in data, and inherently many organizations struggle to employ their data assets to drive strategic and tactical decisions. This has created what is commonly known as “data rich, information poor” world.
This state gave birth to the field of Data Science – which is the art and science of leveraging data in creative ways to give organizations competitive advantages.
On March 30, we will be hosting several of the smartest data science minds from Quicken Loans like Mo El Kaderi, Yogesh Dalal, Mike Tan, etc and other companies.
COME LEARN, NETWORK AND SHARE IDEAS WITH THE BEST IN DATA SCIENCE AND SEE BENZINGA'S NEW DETROIT OFFICE!
If you are a new to data science this event will be very helpful as you can ask questions of top leaders, all of whom spent years in the field.
5:00PM - 5:30PM: Networking/Food
5:30PM - 6:00PM: Presentations by Yogesh Dalal & Mike Tan, Quicken Loans
6:00PM - 6:30PM: Discussion Session and Q&A
6:30PM - 7:15PM: Open Networking
Yogesh Dalal will describe the architecture of a scoring engine for hosting models & providing large scale automated data-driven decision support.
Mr. Dalalis a member of the Big Data Analytics team at Quicken Loans. He focuses on the design and development of a scalable Data-Driven Scoring platform.
Yogesh has contributed to many Big Data solutions that address critical business challenges. He is passionate about building innovative solutions that provides timely and optimal business decisions.
Mike Tan will talk about the use-case: Loan Phase Transition Analysis, which will introduce the general approach for predicting loan phase movement. He will cover the motivation, the methodology and an application: predicting a loan’s risk of becoming delinquent.
Mr. Tan is a member of the Advanced Analytics team at Quicken Loans. Mike received his Ph.D. in Statistics from Colorado State University. His focuses on predictive modeling for Quicken Loans Servicing where he builds models to predict mortgage delinquency.
As a Ph.D. student, Mike developed a modulated renewal process approach to model recurrent event data. This has been applied to neural spike train data for understanding how groups of brain neurons process information and interact with each other.