How AI enhances the transportation sourcing process

The freight landscape has witnessed significant changes in recent years. The demands and expectations of the supply chain have soared, making transportation sourcing a crucial differentiator and customer-facing activity.

Sourcing remains one of the key value drivers for shippers around the globe. Over the years, sourcing of freight has evolved from mailing out spreadsheets to utilizing web-based combinatorial optimization tools.

The sourcing process itself can be time and labor intensive for both the shipper creating the RFP and the carrier responding to the RFP. There’s a large data lift to ensure accuracy in providing information to the market, and at times this lift can be manual depending on system and data availability.

Additionally, reviewing and evaluating RFP responses can be time consuming, as there can be literally tens of thousands of lines of bid submissions that need to be modeled.

To meet these challenges, companies are leveraging new technologies. This is where the concept of artificial intelligence (AI) comes into play. AI refers to the application of advanced technologies and analysis that optimizes decision-making, improves efficiency, and enhances
sustainability in the transportation sourcing process.

By leveraging AI, organizations may be able to automate and optimize the bidding process, improving accuracy, efficiency, and cost-effectiveness. This can lead to increased bid competition, streamlined interaction between shippers and carriers, and ultimately, better transportation outcomes.

In this article, we hypothesize several areas where AI can be utilized to revolutionize the transportation sourcing process. Let’s take a look at where AI can help simplify and streamline the sourcing process by reviewing how it affects each portion of the transportation bid process.

RFP creation

Over the course of the years, RFP development has evolved from paper bid sheets to Excel files on disks, to now on-line sourcing tools that can be quickly configured. The collection of data has typically been very manual.

Trying to obtain data from multiple sources in multiple formats has historically been problematic. Cleaning data to remove anomalies that can skew the baseline and eventual forecasted volume has been a very time-consuming process.

Where AI can enhance this process is by leveraging machine learning algorithms to analyze historical data related to transportation sourcing bids. By analyzing past bid outcomes, pricing trends, and supplier performance, AI provides valuable insights. Additionally, anomalies in data can be quickly evaluated and removed. This enables shippers to make more informed decisions when preparing their RFPs based on this analysis.

Specifically, AI can help with adjusting the historical forecast utilizing the following methods.

Reviewing internal data. Ping multiple sources of historical data and help to understand the underlying factors that influence the forecasting accuracy; specifically addressing peaks and valleys in demand to accurately evaluate shipping trends.

Improving forecasting accuracy. By learning from the historical data, AI can generate insights and recommendations for adjusting the shipper’s forecast. It can suggest adjustments based on the identified patterns and trends, external market fluctuations such as industry, consumer and macro GDP trends, current social and political events, and can be modeled into the forecast to improve accuracy.

Bid validation

AI automates the process of validating bids by comparing predefined criteria and business rules. This ensures that bids meet the necessary requirements and comply with regulations. AI can identify discrepancies or errors in bid submissions, allowing carriers to correct the mistakes. Following is how it assists in bid validation.

Evaluating bid parameters. Quickly evaluates bid parameters such as pricing, service levels, equipment type, and capacity. It ensures compliance with the sourcing requirements by comparing the bids against predefined criteria.

Real-time feedback. Provides real-time feedback on bid validity. It highlights any discrepancies or deviations from the desired criteria, enabling efficient bid validation and timely feedback. This will enable a more cohesive collaboration between the shipper and carrier to help streamline the process and eliminate confusion and delays that often plague sourcing events.

Market rates development. Create a market value rate (MVR) for subsequent rounds utilizing external freight pricing sources (e.g. DAT) and comparing with submitted bids and capacity. Historically, this MVR was often just an average of the rates on a lane, however, with additional criteria though AI such as service, mode, equipment type, and capacity, it can be evaluated and used to set the MVR.

Evaluation of responses

AI assists in evaluating bid responses by using natural language processing (NLP) techniques to extract relevant information from submitted documents. Shippers can quickly analyze and compare bids based on factors such as pricing, service offerings, and delivery capabilities.

AI also identifies patterns or trends in responses, providing valuable insights for decision-making. AI expedites the evaluation process by automatically analyzing and extracting key information from carrier responses. Here is how it facilitates expedited and fact-based evaluation of responses.

Automated analysis. Analyzes carrier responses and extracts key information. It saves time and effort by automating the evaluation process.

Fact-based evaluations. Comparing responses against predefined evaluation criteria and business rules, AI generates fact-based evaluations. It highlights strengths, weaknesses, and areas for improvement in carrier responses.

Efficient feedback. Provides feedback to carriers in a timely manner. It ensures that carriers receive prompt feedback, allowing them to make necessary improvements.

Scenario modeling

AI enables shippers to perform scenario modeling to assess the impact of different variables on the bid process. By simulating various scenarios, such as changes in pricing or service requirements, mode shifting, carrier type (asset versus broker), shippers can evaluate potential outcomes and make data-driven decision with quick understanding of the financial impact.

Historically, scenario modeling could be very complex, as more layers of rules typically will cause the solution to become unfeasible and may not necessarily be easy to implement. AI will help to optimize the bid strategy and improve the probability of success.

Scenario modeling is the lynch pin to having a successful sourcing event. Rules need to be based on a shipper’s business requirements, as well as realistic evaluation of carrier bids.

This helps to set the shipper up for success and avoid the “six-week later” trap, where carriers may have been over-awarded or did not have the actual equipment/service type needed to support the lane.

Rule creation. AI can also help in creating constraints for scenario modeling using a logic language model (LLM). This enables business operators to mimic functional requirements to ensure a scenario outcome that’s feasible.

Simulating different scenarios. By modeling different scenarios, AI helps in decision-making. It provides insights into the potential impact of different sourcing strategies, aiding in informed decision-making. This can clarify the impact of certain rules and to help filter out unnecessary constraints. Shippers can quickly identify the financial value of service trade-offs for various decisions that are made. This is important to understand, as certain decisions by operations or procurement can affect the overall benefit case.

Negotiation and awards

AI supports shippers in the negotiation process by providing real-time insights and recommendations. By analyzing bid data, market trends, and supplier performance, AI suggests optimal negotiation strategies and helps shippers achieve favorable outcomes.

Additionally, AI assists in the awarding process by considering multiple factors, such as pricing, service quality, and compliance, to select the most suitable suppliers.

Data-driven insights. AI generates fact-based historical data, market trends, and other relevant factors. It provides negotiators with valuable information to support their negotiation strategies.

Optimal negotiation strategies. AI supports negotiators by suggesting ideal negotiation strategies. It identifies potential trade-offs and provides counterarguments based on the available data, helping negotiators make informed decisions.

Compliance: Integrating post-bid routing guide into TMS

AI can help integrate the post-bid routing guide into your transportation management system (TMS) by leveraging its contextual understanding. Here’s how it ensures compliance.

Analyzing routing guide requirements. It analyzes the routing guide requirements and maps to the capabilities of the TMS system. It also ensures that the TMS system is aligned with the routing guide.

Recommendations and guidelines. AI can recommend and set guidelines for ensuring compliance with the routing guide. It enables efficient and accurate execution of transportation operations by providing guidance on compliance.

It’s a wrap

In conclusion, the hypothesis that AI can transform the transportation sourcing RFP process
is well-founded—and promising. By integrating AI into the transportation RFP lifecycle, both shippers and carriers benefit from streamlined and efficient operations.

For shippers, AI enhances RFP creation by automating data collection and anomaly detection, leading to more accurate forecasting and informed decision-making. Bid validation becomes more
precise with AI’s ability to quickly assess compliance and provide real-time feedback, reducing errors and streamlining communication.

The evaluation of responses is accelerated through NLP, enabling shippers to quickly assess bids based on key criteria. Scenario modeling, powered by AI, allows shippers to simulate various outcomes and make data-driven adjustments to optimize their sourcing strategies.

Negotiations are strengthened with AI-generated insights, leading to more favorable outcomes and effective supplier selection. Finally, compliance with routing guides is ensured through AI’s contextual analysis, aligning transportation
management systems with bid requirements.

Overall, AI not only makes the RFP process more efficient, but also improves its accuracy and effectiveness, leading to improved outcomes and enhanced value for all parties involved. As AI continues to evolve, its role in revolutionizing transportation sourcing will likely become even more significant, driving future innovations and efficiencies.