Skip to main content

Navistar Analytics 50 Submission


Dan Pikelny, Vice President, Analytics





Business Challenge

Navistar, as other manufacturers, needs to support its products in the field. The product is trucks, and the key measure of success is uptime—the proportion of time that a truck is operable rather than in the shop for repairs. From an analytics perspective, the challenge is detecting problems in the vehicle before customers experience it.

Analytics Solution

Navistar uses a remote diagnostics system: OnCommand Connection. The system gives the company access to vehicle and engine data, on all makes and models, by interfacing with telematics systems that fleet customers use such as PeopleNet and Omnitracs. From an analytic perspective, the IoT data is available to train machine learning models to predict which vehicles are at risk and which components are potentially problematic. The analytics team developed algorithms to detect emerging problems in as few as five vehicles in a population of tens of thousands. The algorithm predicts the lifetime failure rate and sets alerts on future risk instead of focusing on historical experience. In addition, the team uses AI techniques to predict which individual vehicles based on IoT sensor data are highest risk for the resulting failures.


OnCommand Connection has allowed Navistar to achieve the following successes:

  • Detection of major issues for customers occurs four to six months earlier using a predictive model of failures for more than 40,000 combinations of diagnostic trouble codes by make, model and year of vehicle
  • Using dozens of “synthetic” fault codes to communicate to customers to make proactive repairs
  • Identifying the top fleets starting to experience issues and contacting customers to set up proactive repairs and part changes before failure