By: Eric Siegel, Founder, Predictive Analytics World for Business
In anticipation of her upcoming conference presentation at Predictive Analytics World for Business Las Vegas, June 16-20, 2019, we asked Leslie Barrett, Senior Software Engineer at Bloomberg LP, a few questions about their deployment of predictive analytics. Catch a glimpse of her presentation, Machine Learning Evaluation from Start to Finish, and see what’s in store at the PAW Business conference in Las Vegas.
Q: In your work with predictive analytics, what behavior or outcome do your models predict?
A: Our models have a range of different goals from predicting the classes of documents to the identity of named entities.
Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?
A: Predictive analytics are essential to providing top quality content to our users including enhancing navigation of data and uncovering important insights from documents.
Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: Our entity resolution models perform considerably above published state-of-the-art. We achieve results though a combination of data management, model optimization and rigorous evaluation standards.
Q: What surprising discovery or insight have you unearthed in your data?
A: The importance of communicating technical model quality and translating into customer experience quality.
Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.
A: There are different standards for model quality depending on the development stage.