Dash, Recurring Neural Networks (RNN), and SHAP for Predictive Maintenance

with Vaex co-Founder, Jovan Veljanoski 

Wednesday September 15, 2021 @ 2pm EDT

Knowing when a fault may occur in a production line is of great importance to numerous industries. Knowing why such a fault may occur is even more valuable, and will lead to not only a timely but a precise and efficient action.

In this webinar, Maarten Breddels and Jovan Veljanoski of Vaex.io will show you how to build a Dash app to predict the lifetime of airplane engines. The key topics discussed will be:

  • using Vaex for efficient and greatly simplified way of preprocessing the data
  • using Keras to build a Recurrent Neural Network model
  • provide model interpretability via SHAP
  • productionization of the entire model pipeline via Vaex
  • using Dash to bring it all together and create an informative application
  • About Jovan Veljanoski

    Jovan is a senior data scientist & researcher at Cloud Technology Solutions, where he creates predictive models and data pipelines for a variety of domains and use cases. Working mostly with Python in the Jupyter/PyData ecosystem, he has considerable experience in creating dashboards, clustering analysis and predictive modeling. Jovan has a PhD in Astrophysics, is a co-founder of vaex.io, and is interested in novel machine learning technologies and applications.