Tensorflow Solutions for Data

Course details

In this video you'll work with categorical data to predict loan performance. Categorical, structured data often appears in spreadsheets and relational databases, common data sources in business. This technique can be used to effectively predict performance or detect potential fraud.

You will also work with recurrent neural networks, which generate realistic test and placeholder data. This is useful to fill in systems with synthetic test data to simulate load and test the breadth of a working system andpredict one column from the others.

About the Author

Will Ballard serves as Chief Technology Officer at GLG and is responsible for the Engineering and IT organizations.

Prior to joining GLG, Will was the Executive Vice President of Technology and Engineering at Demand Media. Before that, he was Vice President and Chief Technology Officer of Pluck, through its acquisition by Demand Media. At both organizations, Will managed large teams of engineers responsible for software architecture, design, development, and quality assurance.

He was also responsible for the design and operation of large data centers that helped run site services for customers including Gannett, Hearst Magazines, NFL .com, NPR, The Washington Post, and Whole Foods. Will has also held leadership roles in software development at NetSolve (now Cisco), NetSpend, and Works .com (now Bank of America).

Will graduated Magna Cum Laude with a BS in Mathematics from Claremont McKenna College.