Skip navigation
GettyImages-966248982_0.jpg

What’s the Role of Machine Learning in Procurement?

Here’s how machine learning can help buyers operate more efficiently while freeing them up to focus on their most critical tasks.

A data analysis method that automates analytical model building, machine learning is a branch of Artificial Intelligence (AI). Based on the idea that systems can learn from data, identify patterns, and make decisions with minimal human intervention, machine learning is making it into the business world as companies roll out pilot programs and integrate this advanced technology into their digital roadmaps.

Procurement is one department that could benefit from advancements in machine learning, and namely due to the many repetitive and manual tasks that most buyers have to go through on a daily basis. For example, Spend Matters points to unreliable spend data as one of procurement’s biggest challenges right now.  

“No matter how much time is spent cleaning up and classifying long-tail spend (i.e., any spend that takes place without a contract framework), the complexity of millions of line items of spend goes beyond the time and resources of even the most talented procurement teams,” Sammeli Sammalkorpi writes in “6 Ways to Leverage AI in Procurement Today.”

“Machine learning spend classification is already advancing long-tail spend management,” Sammalkorpi points out. In another example, he says procurement can leverage machine learning through the use of AI chatbots. Using Tradeshift’s Ada, for example, buyers can interact with users across their platforms and provide contextual suggestions based on real transaction and purchase order data.  

Speed, Accuracy, Agility

Machine learning is also making its way into the broader supply chain spectrum, where it can help alleviate pain points like supply shortages, excessive amounts of slow-moving inventory, uncompetitive pricing, and delivery delays.

“Recent innovations in machine learning make it easier for procurement and supply chain organizations to achieve a close-knit, family-like relationship that balances market opportunities with competitive challenges,” David Sweetman writes in “Five Ways Machine Learning Drives Competitive Advantage Through Supply Chain Speed, Accuracy, And Agility.”In the end, these tight procurement-supply chain relationships are the ones that have close alignment with their organizational priorities.”

Here are three examples of how this can work at the procurement level:  

Predictive analytics for stock in transit. Companies that issue and receive goods need to follow the status of their materials and products in transit so they can address emerging delays or issues before they happen. “By ensuring that every order is delivered on time,” Sweetman writes, “the company can avoid expediting activity to rush product across the supply chain, eliminating unnecessary payroll and logistics spend.”

Automated supply assignment sourcing. By increasing the automation of supply assignment sourcing, companies can reduce the need for manual interactions while securing materials with the best price, fastest delivery time, and highest quality. “The system must automatically create a bidding event when an internal source of supply is unavailable,” Sweetman points out, noting that AI acts like a “human purchaser” by sending the bid invitation to a defined list of preferred suppliers.

Better one-off and free-text purchase negotiations. “Using machine learning algorithms that look through the ‘free text,’” Sweetman writes, “requests can be compared against historical description patterns to recommend the addition of a product or service to the catalog. This enables prices for more than a one-off purchase to be negotiated.”

More to Come

These are just a few examples of how procurement and machine learning can intersect to create better efficiencies for buyers. Dassault Systèmes’ Louis Columbus says there’s more to come in the near future.

For example, Columbus sees machine learning as a logistics cost-reduction tool because it can find patterns in track-and-trace data, reduce forecast errors, and also lessen risk and the potential for fraud—all while improving both product and process quality. Machine learning is also helping to improve end-to-end supply chain visibility by providing both predictive and prescriptive insights that help companies react faster.

SourceESB Parts Banner

Hide comments

Comments

  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.
Publish