Data Connect: North America

In this Data Connect, we’ll deal with data parsing from contract PDFs to find those with errors or potential fraud. In this 1 hour presentation, John Emery (Principal Consultant at Tessellation) will present how to extract data from PDFs using the KNIME Analytics Platform. Then Victor Palacios (KNIME Team Member), will examine the extracted data to isolate suspicious PDFs using 3 outlier detection techniques in the KNIME Analytics Platform. Our special MC for the event will be Nick Rivera (Business Analyst at EMR). Meet all the data wizards in the 1 hour networking event immediately following the presentation! During our 1 hour networking time, we'll also be hosting a 30 minute Beginner's Corner where new KNIME users can learn about our Beginner's Space - a collection of workflows for neophytes! As well, we'll talk about our Just KNIME It! challenges which we post and create each week and other KNIME resources.

Using KNIME, we’ll:

1. Extract data from PDFs
2. Implement outlier detection with 3 methods
3. Identify abnormalities in data

✅ We welcome new and expert KNIME users, developers, educators, and researchers to this event!

✅ Beginner's Corner Blurb:
During our 1 hour networking time, we'll also be hosting a 30 minute Beginner's Corner where new KNIME users can learn about our Beginner's Space - a collection of workflows for neophytes! As well, we'll talk about our Just KNIME It! challenges which we post and create each week.

✅ At the end, we will open up the virtual event area - for you to meet other attendees and KNIMErs. Let’s talk about your data science best practices, the tools you’re using, your research focus... Bring your topics to the beach!

AGENDA:

05:00PM- 05:05PM- Door Open & Welcome

05:05PM- 05:30PM- PDF Extraction

05:30PM- 06:00PM- Suspicious PDF Isolation

06:00PM- 06:30PM- Beginner’s Corner

06:00PM- 07:00PM- Networking Hour