How Freight Tiger solved transit visibility problems and managed journey exceptions with machine learning
The customer is a leading building materials manufacturer. Despite a booming construction market, competition is fierce, and profit margins are shrinking as businesses scramble to capture market share. Visibility into transportation becomes paramount to reduce cost, and on-time delivery to customers becomes the metric to measure the efficiency of the supply chain process.
18%
Reduction in average stoppage hrs for avoidable stoppages
15%
Reduction in TAT for the customer
Products used
Visibility, Mission Control
Industry
Building Materials Manufacturing
What's in this case study?
A leading building materials manufacturer was losing time to stoppages it could not see, in a market where thin margins make on-time delivery the measure of supply chain efficiency. Freight Tiger built a machine learning solution that separated avoidable stoppages from unavoidable ones and traced the avoidable ones to three sources: transporter behaviour, route conditions, and internal and external factors such as no-entry timings, loading delays, rest breaks and driver changes. Working from that, FT defined dispatch time slots per route built on the lowest transit time and least standard deviation across all trips, keeping trucks from idling against no-entry windows and holding plant teams and transporters to the exit timeslot.
The result: TAT fell 15%, average stoppage hours on avoidable stoppages dropped 18%, avoidable stoppage incidences fell 10%, and SLA adherence reached 98%+.
