Designing the Next-generation Platform for Logistics Services
From meal delivery to lodging and transportation, on-demand marketplaces are changing the way we do business, and this technology has opened the door for other industries to follow suit.
"There is a big platform revolution going on," said He Wang, assistant professor at the H. Milton Stewart School of Industrial and Systems Engineering. "Uber is revolutionizing the taxi industry, Airbnb is changing the hotel industry, and we want to do the same thing to logistics platforms."
Wang is working with a startup company in San Francisco to design an on-demand marketplace for long-haul freight transportation in the U.S., an industry that generates more than $700 billion in annual revenue. The main challenge with this market is that it is extremely fragmented — there are more than 500,000 freight carriers in the U.S. and most of these are independent truck owners or small fleets with fewer than six trucks. Because so many different companies are involved, freight brokers handle negotiations using legacy technologies like phone and email to connect drivers and shippers, while charging fees of 20% or more per load. Wang’s goal is to develop an app that will eliminate the need for brokers altogether and facilitate communications to increase efficiencies, lower costs, and better serve both parties.
In addition to these benefits, the on-demand platform will also optimize truck usage. Wang estimates that 28% of the trucks on the road drive empty, because they have dropped off their cargo at one location and are traveling to pick up the next load. This is a missed opportunity, and one he thinks he can help remedy.
"Companies have tried to build sites that connect drivers and shippers for years, but they are simply listing loads for drivers to pick. This is not very effective, because they don’t take advantage of all the information," explained Wang. "I want to use operations research tools to incorporate all of the information available to help define the pricing and matching mechanisms and facilitate better connections. It will go beyond information-sharing — it will be about decision-making."
The resulting mobile app will make the best use of empty trucks by allowing truck drivers to view the various loads waiting to be delivered along the route they are traveling, including compensation for transporting the load. While on the surface this appears to be a simple problem to solve, it is actually very complex due to supply heterogeneity — load size, weight, and delivery date all need to be factored into the decision, in addition to origin and drop-off locations.
"Ride-sharing apps are simpler because they have a homogeneous supply of passen”gers that need to move from one location to the next, so there is not a lot of variability," said Wang. "With cargo, not all shipment orders close to a driver’s current location will be feasible for them to transport. We need to create a model that takes all of this into account.
"By using all the data available, and creating a central decision-maker, we can make more efficient matches," concluded Wang. "I hope my research can make an impact on this industry."