Spendata uses classic AI mechanisms to automatically family and map spending. We use a combination of heuristics trained on spend data along with knowledge bases derived from existing spend cubes and other sources. This approach is analogous to the methods used by chess-playing programs on bespoke devices such as game consoles. Such programs have memorized the standard openings of the game — their knowledge base — and supplement that knowledge with heuristics to evaluate potential moves.
Depending on your data, Spendata's automatic mechanisms can perform the lion's share of vendor familying, as well as a solid chunk of commodity mapping. This is typically enough to start seeing some interesting opportunities. You will want to do more -- and that's where Spendata really shines. We provide you with simple yet powerful mapping tools that make refining that initial cube quick and easy.
However, there's a key difference between Spendata's mapping and "opaque" mapping provided by, for example, neural-net based AI's. Those solutions provide the mapping as a fait accompli. You can neither review what they've done, nor understand why they've done it. They just give you the answer.
In contrast, Spendata's auto-familying and auto-mapping routines produce human-understandable rules, organized such that you can review them and understand them. These are exactly the same rules as are produced by Spendata's manual familying and mapping functions. So, you can easily understand the reasoning behind the mapping, and trace the mapping of any transaction back to the rule that moved it.
No more embarrassment when a business unit manager asks why a particular piece of spending was mapped somewhere — you have the answer. Most importantly, if it's mapped incorrectly, you can fix it on the spot in seconds. The manager feels empowered; critics retire to the back benches; and the savings initiative moves forward smoothly.