Freight truck manufacturer drives down cost with predictive analytics
Daimler Trucks North America (DTNA), a Daimler company that manufactures, sells and services Class 4-8 trucks under the Freightliner, Western Star, Detroit and Thomas Built Buses brands, is engaged in the perpetual pursuit of quality. As the leader in the North American commercial trucking market, DTNA is focused on providing the best trucks on the road and delivering uncompromising value and customer satisfaction. It does so through a commitment to technological innovation and superior engineering.
Total cost of ownership (TCO), which measures the overall direct and indirect costs of a commercial vehicle over its entire lifecycle, is an important marker in the commercial trucking market – and one considered by many to be more important than a vehicle’s initial purchase price. It includes everything from acquisition to the end of a truck’s operating life, incorporating taxes and registration fees, fleet employee salaries, uptime, maintenance and repair expenses, fuel costs and more. Fleet size and miles driven play a role, as does the length of time a company keeps a truck in operation. TCO is a key driver in the trucking industry, which reported $676.2 billion in revenue in 2016,1 and it is pushing manufacturers and suppliers to implement cost-effective technologies.
With such varied inputs, and ones that vary by fleet, calculating TCO can be difficult. DTNA turned to PK for help.
Historically, DTNA had faced challenges in integrating customers’ data sets into TCO calculations due to constantly changing file and data type formats. With an IT-centric support model that leveraged the data platform Informatica for extract, transform, load (ETL) processes, DTNA was unable to respond to changes in data formats quickly.
PK partnered with DTNA to replace Informatica workflows, which required IT support, with Alteryx workflows supported by analysts. Alteryx offers a repeatable workflow for self-service BI, data preparation, data blending and analytics. The implementation lowered project expenses and enabled a more responsive, agile data environment – one in which teams were able to perform advanced analyses and create robust predictive models without IT involvement.