RPM is an international logistics and supply chain company based in Birmingham, Michigan. RPM specializes in freight transportation and vehicle logistics across North America and Europe. As a non-asset-based logistics company, RPM invests heavily in modern technologies and automation solutions.

RPM connects business clients with carriers to complete vehicle deliveries. RPM manually selects which carrier they choose to use for delivery. This is a time-consuming and complex decision process due to the large amount of data pertaining to carriers.

Our Carrier Performance Index Engine provides RPM employees with an intuitive web application dashboard that displays a performance score for each carrier. When a decision is made to select a carrier for a delivery, the Carrier Performance Index Engine uses available carrier data for an encompassing score grading how well the carrier performs.

The dashboard also includes different pages detailing individual carrier data, performance for each delivery made and an alerts page for monitoring risks and performance. RPM leverages our collected data to make reasoned decisions about carriers, mitigating potential failures during this process.

The details page shows which carriers have been improving over time and quantifies both risk and performance, using historic data to visualize the data for easy analysis at a glance.

Our web application deploys Streamlit for the front end and back end. The carrier and the delivery information is stored within a Sqlite3 database in tandem with NumPy and Pandas for data processing. The new stream of data is sent to the machine learning component which leverages scikit-learn and PyTorch. This data is run through our machine learning layer which calculates the Carrier Performance Index score for each carrier. Each of these components form the Carrier Performance Index Engine.