Reifier Spark Summit 2014 Slides

  • Published on
    30-Jun-2015

  • View
    103

  • Download
    0

DESCRIPTION

Presentation on Reifier, fuzzy matching using Apache Spark and Machine learning

Transcript

1. Nube Technologies Fuzzy Matching With Spark 2. Nube Technologies About Us ALICE: This is impossible! THE MAD HATTER: Only if you believe it is. 3. Nube Technologies The problem According to Gartner, businesses are losing upto 25% potential revenue due to lack of holistic multichannel view of data. 4. Nube Technologies The problem 5. Nube Technologies Challenges Quadratic nature of the problem No standard notion of similarity Omissions, typos and other issues 6. Nube Technologies Use case - Cross and Upselling 7. Nube Technologies Lead Generation 8. Nube Technologies BFSI Personal Credit Ratings Fraud detection 9. Nube Technologies Other Use Cases Yellow Pages Catalog and Inventory Management 10. Nube Technologies Wishlist Works with any kind of data Scalable No manual configuration of rules or algorithms 11. Nube Technologies Spark Advantages Distributed Scalable In memory Machine Learning Sampling No need to orchestrate multiple jobs 12. Nube Technologies Reifier - Label Are these duplicates?(Y/N) 13. Nube Technologies Reifier Output 14. Nube Technologies Thank You !