Use machine learning to minimize carbon emissions in the trucking industry

Original article was published by SHAIK SAMEERUDDIN on Artificial Intelligence on Medium


Saenz says Flock Freight tackles data science harm and on-time delivery issues within the LTL sector, machine learning in their logistics planning applications.

“This optimum introduction of technology into the freight industry has seen [..] a 65 percent rise in the share of shipments of trucks,” Saenz added.

The machine learning-based product, FlockDirect, pools less-than-truck freight consisting of a few pallets together to create complete truck loads. It optimizes routes by pooling freight in the same direction so that the trucks pause at each drop-off, avoiding conventional terminals.

Saenz says to build shared truckloads, their pooling algorithms sift through an enormous number of potential shipment permutations to find only those that are feasible and economically beneficial to all parties.

“Origin, destination, weight, dimensions, type of product, scheduling, shipping costs — these are just a few of the various shipping constraints that our technology must account for in order to propose shared truckload pools that will actually work,” Saenz said.

Saenz claims that cooperative truckload transport negates the need for carbon-intensive terminals. “And, since shared freight shipments are loaded and unloaded only once, 99.9 percent of shipments arrive without damage, minimizing the environmental damage caused by the remanufacturing and re-shipping of duplicate goods.”