LE MANOIR RICELIEU, QUEBEC - At the National Tank Truck Carrier's Summer Board Meeting, FleetRisk Advisors announced the production implementation of an advanced predictive modeling and risk analytics system for Dupre' Transport, LLC. The initiative began as a pilot project in 2005 using data aggregation and pattern recognition technology to identify risk signatures of drivers, vehicles, and schedules. The pilot focused on which drivers were most likely to be involved in an accident or service failure. The production phase began in the first quarter of 2006, enabling Dupre' to devise new risk management and performance monitoring strategies with the aim of simultaneously reducing operational costs and mitigating risks. The primary business objective of the production implementation was to combine historical data with the current month's operational data to predict next month's safety performance. In order to accomplish this, FleetRisk implemented a new processing platform at Dupre' which consists of the following “near” real-time interfaces to primary operational systems:
QUALCOMM FleetAdvisor fleet management system.
Circadian alertness simulator.
TMW dispatch system.
Profile XT – driver profiling.
Dupre's internal accident & incident system.
Dupre's internal human resources and training programs.
Dupre's internal vehicle & fixed asset systems.
Interfaces to external data such as population density, zip code, weather, traffic.
New predictive models incorporating the expanded datasets.
The system has been in production since the end of the first quarter. Click on the following link to view the results: www.fleetriskadvisors.com/news.html. At the end of each month the predictive models rank current drivers against a statistical and demographic profile of Dupre' Transport's theoretical best and safest driver. Each tier represents one-third of the current driver population. Tier 1 drivers represent the “best and safest” while Tier 3 represents those needing the most attention. At the end of each month, actual accident results are compared to the model's predictions. Tier 1 drivers (210 in total) have been responsible for only 6 percent of all preventable accidents in the aggregate, while Tier 3 drivers (210 in total) have been responsible for 65 percent of the overall accidents. This predictive segmentation allows Dupre to focus its training and risk mitigation efforts on a small subset of their drivers, rather than the entire driver team. Based on the initial results of the production system, Dupre's management team has designed a suite of targeted risk management and performance monitoring strategies, including:
Focused driver-training programs.
New Safety Field Representative training.
Terminal and management scorecards.
Driver scorecards and enhanced incentive programs.
Alerts from in-vehicle technology.
Dispatch training and incentive programs.
A modified recruiting and retention program.
