Guided Analytics Learnathon: Building Applications for Automated Machine Learning

Abstract: This event will focus on automated machine learning and data visualization, and we'll work in groups to build a simple application for automated machine learning (ML).

We will build an input page to explore the data and to insert the settings for data preparation, model training, and hyper-parameter optimization and we will build an output dashboard to visualize model insights and performance. At the conclusion of the event, the application is deployed on a KNIME Server and run from a web browser.

The tool of choice for this Learnathon is open source KNIME Analytics Platform, which also offers great integrations with R, Python, SQL, and Spark.

After an initial introduction to KNIME Analytics Platform and automated ML, we split in two groups, with each group building one of the following:

Group 1: the start dashboard for visual data exploration and automated ML settings
Group 2: the final dashboard to visualize model accuracy and speed performance
We will provide the dataset, jump-start workflows, and final solutions, and of course data visualization and ML experts.

Please bring your own laptop with KNIME Analytics Platform pre-installed.
To install KNIME Analytics Platform, follow the instructions provided in these YouTube videos:
● Windows: https://youtu.be/yeHblDxakLk
● Mac: https://youtu.be/1jvRWryJ220
● Linux: https://youtu.be/wibggQYr4ZA
If you would like to get familiar with KNIME Analytics Platform, you can explore KNIME E-learning course (https://youtu.be/8HMx3mjJXiw).
Before the event, we will share the link to download all workshop material (jump-start workflows, slides, and instructions).

Bio: Scott Fincher works for KNIME, Inc as a Data Scientist. He has presented several talks on KNIME's open source Analytics Platform, and enjoys assisting other data scientists with optimizing and deploying their models. Prior to his work at KNIME, he worked for almost 20 years as an environmental consultant,with a focus on numerical modeling of atmospheric pollutants. He holds an MS in Statistics and a BS in Meteorology, both from Texas A&M University.