What’s that coming over the hill – is it a monster? No, it’s just the 21st century. And whether Sarah Connor likes it or not, Artificial Intelligence (AI) and Chat GPT (also known as Generative AI – GenAI) are here to stay. But despite Skynet’s best efforts, it won’t take over, we are certain of that. We can live with it, in fact, even cohabit with it (almost) harmoniously in the spend data classification world, but not before it has been classified and checked by a human.  

Using AI and machine learning in data classification   

You may have been told by your suppliers or a potential supplier that they’re using AI, machine learning or more recently, Chat GPT/GenAI to classify spend data. You may even have heard phrases like “neural networks”, “algorithms” and “LLMs” being thrown around. It all sounds very technical and a bit scary, especially if they’ve not given you any more information or explained what it actually does. It sounds like it should work, so there can be an implied trust that it will work. But that isn’t always the case. 

Why AI isn’t a silver bullet for spend data classification 

In reality, AI and GenAI aren’t there just yet when it comes to spend data classification. It may sound like a wonderful tool where you can just press a button to magically classify your data. However, the reality is far different. That’s because AI has to learn from an immense number of training data sets. What’s more, these data sets need to be clean and accurate. How do we ensure this? We use people, preferably subject matter experts (SMEs), to check and verify those training data sets.  

To add more complexity to the mix, remember that context is hugely important in spend data classification. This is still an issue within AI, GenAI and Machine Learning and means we humans still need to be heavily involved. 

AI and spend data classification the – basics 

Let’s go back to basics for a moment. The AI, in whichever form, will learn from training data sets that have been previously classified and will keep learning as new data is added. This is particularly successful in areas such as MRO (Maintenance, Repair, Ops), where the items are hardware such as nuts, bolts and screws. Their classification is unlikely to change, allowing it to accurately classify large volumes of data. 

There are, however, other instances where it is not so clear-cut. For example, DHL could be classified as a courier in the training sets. This would mean the AI learns from this and classifies DHL as a courier whenever it shows up. But DHL is not always used as a courier. DHL can also be used for warehousing, distribution and logistics, depending on who the data set belongs to. This makes it important to make this distinction, particularly for spend management. 

Complicating things further are free text descriptions and the suppliers who provide multiple products or services. These both make it harder for the AI to learn. For example, with the description “taxi from hotel to restaurant”, how does the AI know which one to choose? With the prevalence of GenAI, we’re getting better, but you can’t blindly trust the tech. 

Humans still rule… 

All these reasons make it crucial for the AI to learn accurate data from a human from day one. What’s more, that data should be regularly checked for accuracy. What if there’s a glitch in the Matrix and the AI learns something it shouldn’t? (I know I’m mixing my movie metaphors here, but can you imagine what a film that’d be with Keanu Reeves AND Arnold Schwarzenegger?!). Imagine the implications of one tiny mistake in the early stages of the AI’s learning – let alone hundreds or thousands? That’s a lot of spend misclassified right there. 

Picture being several processes down the line and realising a whole section of data has been wrongly classified over and over and… over again. And it wasn’t spotted because the AI had been left to do its thang. Someone will then need to manually classify your data while the AI is retrained. Not to mention having to go back through, find and correct the earlier mistakes.  

To put it bluntly, without accurate human input, an expensive software or service will be about as much use as a cardboard box on four wheels during an episode of Robot Wars. 

When it comes to spend analytics tools, there’s no such thing as a perfect solution. There are a lot of different methods used in machine learning/AI for data classification because there’s currently no single system that’s better than any other. With GenAI entering the picture, this adds another layer of complexity while we learn to understand its capabilities and limitations. The result? You still need capable and adaptable humans who have the know-how to manually classify and check data. (I know a good book for that…) 

Enjoyed this blog? Read this one next 👉 Will AI take over the spend classification world?