Loading…
Saturday, October 20 • 2:30pm - 3:00pm
Deploying Data Science Engines to Production: Comparing Options + Code Examples

Sign up or log in to save this to your schedule and see who's attending!

Feedback form is now closed.
Reducing the gap between R&D and production is still a challenge for data science/ machine learning engineering groups in many companies. Typically, data scientists develop the data-driven models in a research-oriented programming environment (such as R and python). Next, the data/machine learning engineers rewrite the code (typically in another programming language) in a way that is easy to integrate with production services. This process has some disadvantages: 1) It is time consuming; 2) slows the impact of data science team on business; 3) code rewriting is prone to errors. A possible solution to overcome the aforementioned disadvantages would be to implement a deployment strategy that easily embeds/transforms the model created by data scientists. Packages and products such as jPMML, MLeap, PFA, Amazon SageMaker, and PMML among others are developed for this purpose. In this talk we review some of the mentioned packages along with a coding exercise, motivated by a real world project at Meredith Corp. The project involves development of a near real-time recommender system, which includes a predictor engine, paired with a set of business rules.

Speakers
avatar for Mostafa Majidpour

Mostafa Majidpour

Senior Data Scientist, Meredith
Mostafa Majidpour is a Senior Data Scientist with Meredith (previously Time Inc) working on harvesting the power of machine learning for various user experience related recommendation engines. Previously at ZEFR, he has been involved in building/improving their forecasting engine... Read More →


Saturday October 20, 2018 2:30pm - 3:00pm
Ballroom # 403B