Presented by Connie Yee – Data Scientist at Bloomberg

As the leading provider of financial and company data, Bloomberg has access to vast amounts of data on a daily basis. There are two common challenges when working directly with raw data. One is the need to discover and extract data represented in the natural document format that is not machine-readable. Another requirement is validating and ensuring that the data is of high-quality since it is required for building models for predictions, classifications, and various analytics tasks. This talk will cover ways in which data science and machine learning can be used to address these two challenges: (1) ingesting your data by extracting what is contained in natural document format and (2) cleaning your ingested data.