Employee Spotlight: Meet Marshall SmithMarch 15, 2023
As someone with over 25 years’ experience in predictive analytics, I lend my expertise to growing LMI’s capabilities with predictive analytics, focusing on asset future performance and APM. Successful asset performance–focused predictive analytics depends on analytical facets across data operations, model operations, and effective and timely outcome communications. As a solution architect, I continuously combine many analytical techniques, including the development of innovative solutions, to create higher fidelity outcomes more efficiently for our customers. I was one of the principal designers and technical leads for the development of our LogSmart™ Fleet application, which integrates predictive analytical models for predictive maintenance and demand forecasting with supply chain optimization and comprehensive logistics considerations.
Why do you like working at LMI or why did you pick to work at LMI?
LMI has a focus on culture that enhances employees’ ability to innovate collectively and collaboratively. LMI combines the resources of a large company and has a historic reputation while offering the family-friendly oriented culture of small companies. It is a privilege to come to work every day with such innovative and caring people. The technical work is amazing too, but the people make all the difference. This culture is contagious and emanates outward to our customers, enabling more efficient communication and, therefore, higher value-added solutions.
What has been the most impactful project you have supported while working at LMI?
The many impactful projects that I’ve participated in across multiple customers make picking one difficult. But, if I had to choose one, it would be the prognostic and predictive maintenance work LMI conducted for a DoD customer. We developed, demonstrated, and left behind a well-documented capability to use LMI’s extension to reliability-centered maintenance analysis using part-level reliability characterizations to forecast future part demands accurately based on usage. Our method showed a significant improvement over existing demand forecasting for multiple parts. This extension is but one of our many tools for APM and lends itself well to integration with our other solutions for supply chain optimization. It also lays a solid foundation for informing sensor-based demand forecasting.
What’s the part of your job that makes you excited to come to work every day?
This one is simple. I get excited about the teams I work with every day, including LMI data scientists, data engineers and architects, and visualization professionals as well as our customers.