Download Slides: https://www.datacouncil.ai/talks/building-a-knowledge-graph-using-messy-real-estate-data?hsLang=en
ABOUT THE TALK
Building an effective knowledge graph requires a combination of data science skills and domain knowledge. Commercial real estate data provides many NLP challenges, requiring triangulation across multiple sources to be able to build a dynamic knowledge graph. We share some of the data science and data engineering challenges that we’ve encountered along the way, and how we plan to utilize this data to drive future ML-based real estate technology.
ABOUT THE SPEAKER
John Maiden is a Senior Data Scientist at Cherre, developing ML/AI solutions to enhance commercial real estate data. His focus is on end-to-end solutions, collaborating with business and technology partners on the initial business concept and working all the way to delivering a product that can face live customers in real-time.
John's interest in data science was sparked by an opportunity to work for a technology recruiting startup, writing code and developing models to facilitate effective connections between employers and candidates. Prior to Cherre, he worked at JP Morgan Chase, where his work was delivered to millions of personal consumer customers. He has a BA from Hamilton College and a PhD in Physics from University of Wisconsin - Madison.