PyData Sydney: Clustering on Unstructured Data - Jacky Wong

With more and more unstructured data (images, PDFs, etc.) being generated, it is becoming increasingly important to be able to capture insights and summaries of unstructured data via clustering. This talk discusses modern approaches such as vector databases, transformers and experimentation stacks that provide the foundation for Relevance AI's unstructured data platform.
About the Speaker
Jacky Wong is the founding data scientist at Relevance AI, the unstructured data experimentation platform that currently serves over millions of users across construction, gaming and education industries. Before Relevance AI, he worked across WooliesX, partnered with organisations like SalesForce and ranked highly (top 5%) across a number of data science competitions hosted by Google, Atlassian, EY ranging from natural language processing, tabular data, geospatial prediction to image processing.