Shiv Sehgal, RSG Media & Daniel Hernandez, IBM | BigDataNYC 2016
summary
RSG Media describes a production pipeline that pulls Excel, APIs, FTP and watch‑folder feeds into a single landing zone and uses Spark and Python for asset matching and machine learning cleansing, then stitches linear and nonlinear versions to produce cross‑platform ratings and ad inventory. IBM DataWorks and Watson Data Works supply embedded Spark, Cloudant and dashDB for operational stores and rapid prototyping of logistic regression random forest and time‑series models; the end‑to‑end pipeline runs under eight hours for scheduling and ROI decisions.
AI-written summary · about
chapters (11)
- 0:00Start
- 0:2001. Daniel Hernandez, IBM, visits #theCUBE!.
- 0:3903. Background of RSG Media.
- 2:1304. DataWorks: Rethinking Governance.
- 3:5905. The RSG Big Data Story.
- 7:2906. Finding Trust in the Data Pipeline.
- 9:4407. IBM Data Works Platform for RSG Media.
- 11:2408. Why IBM?.
- 13:0609. Linear Dollars and Digital Dimes.
- 14:3110. Avoiding the Way of Print Media.
- 16:2811. Watson Data Works: A Big Week for IBM.
