Siemens on the Importance of Data Storytelling in Shaping a Data Science Product

Siemens AG’s Data Analytics Solutions Expert, Vijay Pravin Maharajan, gives a deep dive into storytelling with data and how to make sure all your hard work on developing the right model and building the full-blown ML pipeline also result in a visually pleasing and simple-to-read visual dashboard for quick internal and external adoption.

Among the many AI-driven corporate innovators in the world today, Siemens is one of the leading market players in the locomotives and mobility industries. Its platform, Railigent, serves as a solution for operators to use rail data intelligently, optimize their maintenance and operations, and guarantee one hundred percent availability.

There are numerous use cases in the locomotive industry in which images or videos can be used as unstructured data sources, such as:

• To identify components that need maintenance and exactly which parts triggered maintenance. Engineers can save time and effort by accessing images directly and focusing on pre-filtered components and parts for maintenance
• To monitor the energy consumption of the locomotives – when the eco-cruise mode is turned on or off
• To track the number of passengers who board or disembark from a train
• To monitor the number of passengers and the location of passengers on a platform and many more

But once your AI application is almost ready for production, it’s important to address the visualization of the data product.

Watch this session to learn:

• Why data visualization is an important aspect of data science
• How data storytelling can impact the selling power of a data science product or an AI application
• How IT leaders make data-driven decisions that are beautifully crafted
• What open source and commercial tools are available for data visualization
• How to implement data visualization into your operational ML pipeline