Reducing deadhead miles with smart matching

Machine Learning


introduction

Deadhead miles pose a persistent problem for the logistics and transportation industry.

The business of transportation is the transportation of goods and people from point A to point B for a fixed fee. Transportation costs include leasing or purchasing, operating, operating, and maintaining a fleet. To earn an income, you have to transport goods and people. Without cargo, there is no income. Therefore, headhaul, backhaul, and deadhole are very important concepts in transportation.

The headhole, or outbound trip, is where demand exceeds supply. So in a free market economy, carriers control prices simply because there aren’t enough ships or trucks to carry the cargo. Time is of the essence in transportation, as the goods may be perishable, seasonal, or input into a process to create another product. Moreover, faster movements that save time are preferred by all parties.

Backhaul is the return trip that returns equipment to its original location for the next run. In the case of backhaul, buyers are in control as supply exceeds demand. Truck drivers need freight (paid miles) to get back to base to cover their costs.

A deadhole (empty equipment) is a net loss, and with no cargo, the vehicle returns to base with no revenue. The goal of every carrier is to minimize deadholes, or at least aim for break-even. An alternative is to price headhaul travel deadhead miles so that backhaul travel costs are covered.



Source link