Amy Wang is a Senior Solutions Architect at Databricks with a background in building Machine Learning models on distributed systems. Previously she spent a couple of year at H2O helping companies in the financial sector put risk and fraud models into production. Currently she works with start-ups in the Bay Area to scale their existing data pipelines with a technical focus on Structured Streaming, Data Warehousing, and Data Engineering workloads.
"For companies that make money off of interest on loans held by their customer, it’s always about increasing the bottom line. Being able to assess the risk of loan applications can save a lender the cost of holding too many risky assets. It is the data scientist’s job to run analysis on your customer data and make business rules that will directly impact loan approval. In this session, we will show you how to perform ad-hoc analysis of the loan risk data using Spark SQL and Databricks notebooks. We will then show how to apply Machine Learning specifically comparing GBT and XGBoost algorithms. Finally, we will show how to score this data in batch, streaming, and in real-time."