Thought Leadership
An Asset-Based Operator's Guide to Optimizing a Load Acceptance Plan
June 15, 2023
June 15, 2023
The ability to thrive in a competitive freight market depends on making well-informed decisions. For asset-based trucking companies, load acceptance is one type of decision that falls into this category. The process by which companies decide which loads to accept for fleet assignment, which to accept for brokerage, and which to reject entirely, directly affects operations and profits. If they want to improve profitability, as well as efficiency and optimization, they must take a close look at the process they use and ensure it supports their goals.
An effective load acceptance plan should sort loads into three categories — loads for the company’s assets, loads for the brokerage, and loads to reject. If the process is equipped to handle every important factor, it can easily determine whether a load is compatible or incompatible with the given assets and resources.
The process flow is to first evaluate for asset factors, followed by brokerage factors, and finally, if any load fails to qualify for either, that load is rejected.
The decision-making process should first handle various asset factors to identify the loads best suited to be serviced by the fleet’s assets. Fleet-assigned loads will align with the company's operational capacity, existing routes, driver availability, and business rules. These are the loads that can be efficiently and profitably managed internally.
One method is to approach load selection using a load scoring system, which weighs different variables to rank the available options and find optimal loads for a company's assets.
At the most basic level of qualification to accept a load, an asset must be able to accommodate:
Provided the basic qualification of available capacity has been met, fleet managers may have many combinations of options for assigning assets to loads. This level involves consideration to:
Lastly, two categories of consideration have some flexibility, but nevertheless, fleet managers want to weigh them when they make load acceptance decisions:
Loads can be labeled for brokerage assignment once the load is given a load score. A lower load score than a predetermined threshold indicates shipments that may be more challenging to cover with the company’s own assets. These loads may not fit well with established routes, driver schedules, or business rules and strategies. Loads may also be less desirable for the fleet if they are higher risk or less profitable than other options. These are best for the company to assign to the brokerage division or reject. In this way, companies can focus on profitability and strategy for their own assets, for example, ensuring they have the flexibility to handle additional load requests through third-party collaborations.
One of the main challenges in creating a load acceptance plan is the sheer complexity of the task and the dynamic nature of the factors that make up each decision. It involves constantly monitoring everything from shipper requests and driver availability to asset allocation, route optimization, and more.
Despite this complexity, there is an even bigger challenge: unpredictability and uncertainty associated with load management. A load score algorithm will project capacity and enable fleet managers to make informed decisions even when the future is not certain.
There is an ever-present possibility of changes due to several factors:
These and more factors can introduce unpredictability. To account for this, fleet managers must have a way of representing uncertainty for every available option.
Determining which loads to accept is similar to a game of chess. For every move, there are possible moves the opponent can make; some are more likely than others. Playing chess involves seeing possible outcomes and taking a chance on the opponent's next move. Similarly, planning load acceptance involves taking a chance on future loads' availability. It isn’t known for certain how the options will play out, but fleet managers need to set themselves up for a higher chance of desirable future loads.
Even for a single truck, optimized load decisions are too complex for a person to make manually. With a fleet of 10, 100, or 500+ trucks, this becomes exponentially more difficult. Human decision-making is prone to error and bias, and it is nearly impossible for humans to account for the multitude of factors and potential combinations in real time. Decisions based on gut feeling or incomplete information can result in inaccuracy. A person is likely to inadvertently choose loads that lead to less desirable future outcomes, overburden certain routes, or under-utilized assets.
Manual decision-making opens the door to poor planning and is a missed opportunity for optimization. Fleet managers can leave money on the table by making less-than-optimal decisions with respect to profitability. A pattern of accepting loads that do not fit well with the company's assets and routes can lead to wasted resources, increased operational costs, and dissatisfied drivers. In the long run, this could lead to driver turnover, reduced business growth, loss of market competitiveness, and decreased overall profitability.
Technology and digital transformation are shaping new paradigms in many areas of trucking and logistics, including load acceptance planning.
Integrating artificial decision intelligence can simplify and streamline this traditionally complex and multifaceted process. An AI solution can process high volumes of data in real time and generate accurate forecasts of capacity, shipper requests, and driver availability. It can calculate load scores, assess network fit, and simulate the entire network, helping simplify planning. A tech stack with AI optimization technology helps fleet managers ensure that decisions are grounded in accurate and complete data. The benefit is improved asset utilization and maximized profits, while reducing waste and inefficiencies. And when unforeseen circumstances arise or new loads become available, artificial decision intelligence can reevaluate and adjust decisions accordingly.
Execute by Optimal Dynamics is designed to streamline and optimize the daily decision-making process, including asset versus brokerage load assignment decisions. With CORE.ai technology, Execute uses artificial decision intelligence to analyze thousands of options and present the best ones using a Load Score to represent how well a load fits with the business’ capabilities and priorities. The Load Score algorithm factors in asset availability, established business rules, and profitability to provide valuable insights that help drive decision-making.
Optimal Dynamics’ Load Score contains detailed algorithms finely tuned for complex decision-making. It takes in the big-picture context rather than just assessing a single load. In addition to Loaded Mileage, Empty-to-Pickup Mileage, and Empty-to-Home Mileage, the Load Score shows the breakdown of the following factors influencing overall profitability.
With Optimal Dynamics' Execute product, trucking companies can unlock the most valuable loads and optimize their decisions, backed by artificial decision intelligence.
When BCB Transport, based in Mansfield, Texas, sought to optimize operational decision-making, it partnered with Optimal Dynamics to implement artificial decision intelligence. With the automation of AI-powered load acceptance and dispatching decisions, BCB saw a revenue increase of over 19% per truck per week, and the opportunity to operate with 16% fewer tractors, despite low market volumes and rates.
“Our dispatchers are planning 60% more freight in the same amount of time, while even more importantly exceeding our operational efficiency goals,” said Rick Larkin, Chief Information Officer at BCB.
Read more about BCB Transport’s success using artificial decision intelligence.
Artificial decision intelligence is the tool that allows trucking companies to manage increasing complexity and uncertainty within their load acceptance decisions. Optimal Dynamics’ solution provides a way for fleet managers to achieve optimal decision-making with less time and effort, with the calculation of thousands of possibilities plus forecasting that plans for uncertainty. With the Execute and Plan products, companies can take the proactive approach necessary to stay competitive.
Get a demo with Optimal Dynamics and learn more about optimizing load acceptance.
With AI technology, asset-based trucking companies gain optimization for load acceptance decisions, determining which loads to assign to their fleet, send to brokerage, or reject.
Connect with us to see the power of AI in action on your network.
