The profitability and success of a trucking company comes down to the decisions they make, including decisions on which loads to assign to assets. Choosing the right loads for their assets is a critically important task, and traditionally, load planners have relied on their experience, past decisions, and ability to interpret trends. While these methods had a place in the past, there are now more calculated ways of reaching optimal freight decisions through load scoring enabled by Artificial Decision Intelligence. With the ability to quantify the confidence that load planners can have in choosing any particular load, they can make choices that best align with the goals and capabilities of the business.
While the industry faces depressed freight volumes, load planners tend to accept any available load that seems profitable. However, this approach can undermine profits and EBITDA in the long run without a system for reliably evaluating loads. Taking on every load opens the door to inefficiencies, regardless of the type of freight market load planners are working with. The pendulum of freight volumes will eventually swing the other way, and when it does, trucking companies should have a system in place to strategically assess their load options. This ensures the company’s decisions can support them during lean times and position them to fully capitalize on opportunities when freight volume increases again.
The typical way for load planners to approach their decisions is by first asking the following:
These questions are often answered from a person’s own knowledge or a snapshot of limited historical data. This can cause important factors that influence the profitability of each load to be overlooked, especially when there is not easy access to more detailed information. Load planners may be unable to weigh the opportunity cost of choosing one load over another, predict the chance of available backhaul loads, and understand the impact of decisions on the overall efficiency of their network.
This imperfect system also brings the challenge of a steep learning curve when training someone new to the role. If most of the decision-making is based on past experience, it will take time for a new load planner to build up to the level of reaching the same conclusions as an experienced load planner. However, when the process is more objective, load planners are freed up to apply their experience to the business in other ways.
While load planners consider which loads they should accept based on the likelihood of assigning a truck to the load, there is also profitability to consider. The most straightforward approach would be to take the operating cost of a truck, for example, $2.00 per mile, multiply it by the number of miles for a load, and compare this number to the rate for the load. If a particular load is 1,500 miles, this process would dictate that the rate be at least $3,000 to be profitable.
The problem with this method is that it ignores what happens before and after the load. In actuality, the truck will not already be at the pickup location, and the delivery location will not be the same as the pickup location of the backhaul. There are empty miles on both ends, and these empty miles and loads all exist within a network of options—both options of available loads and trucks to assign to the loads. The only way to determine the optimal decision every time is to use a method that weighs all combinations of options available.
Load acceptance decision processes should factor in profitability and the ability to find a truck and driver for the load within the context of the entire network. This means exploring each scenario beyond a single iteration to understand the position the company will be in upon delivery of that load.
With many variables involved in each scenario, it would be mathematically impossible for a person to account for all this data. On the other hand, technology is best suited for quickly simulating many iterations of different scenarios to compare and determine the best one. This uses far more data and calculations than the limited information available to the load planner. With simulations to evaluate each option, companies can ensure they are making optimal decisions every time.
Optimal Dynamics created the Load Score to help load planners understand how to use the results of simulations. This metric bridges the gap between the simulation and the decision.
It's not enough for simulations to provide load planners with an optimal answer; they should also get a number to represent how confident the simulation is in the result. This keeps them in control of the process, giving them the Load Score and the option of making the final decision.
How exactly does Load Scoring work? If a load planner gets 50 loads tendered to them, they need to know which loads should go to their assets and which should go to brokerage. A load score is the confidence metric that a load the simulation is suggesting goes to assets that will, in fact, pick up the load. Optimal Dynamics runs 20 iterations for each load. If a load score is 100%, this means that after 20 iterations, the simulation was able to find an asset truck for the load all 20 times. If a load score is 95%, then 19 out of 20 times, it was able to find an asset truck.
The key to understanding Load Scoring is remembering the core objective—selecting the right loads for assets. The Load Score is simply a tool to help load planners navigate their decisions by making them more aware of how likely a given load is to work with their assets. This gives a metric to allow them to make informed decisions that lead to beneficial and profitable loads.
Optimal Dynamics’ Execute product was designed to transform the processes of how load planners and dispatchers make decisions. AI brings a new foundation, rooted in advanced simulations, for a more methodical approach.
With AI-powered Load Scoring, trucking companies can shift from relying solely on individuals’ experience and interpretation of complex scenarios with limited data and instead account for all factors like driver availability and new shipper requests and simulate many iterations of possibilities. In forecasting future scenarios, decisions can be made strategically with respect to future opportunities, helping to improve efficiency and profits.
Where traditional decision-making has relied on load planners’ past experience and limited knowledge of historical data, AI-powered load scoring roots decisions fully in data and simulations. Optimal Dynamics’ Load Score, available through Execute, quantifies the confidence that load planners can have in a given load, so they can select only the best fits for assigning to assets, helping them increase efficiency and profits one load at a time.
To learn more about Load Scoring for better decision-making, schedule a demo with Optimal Dynamics today.