Top 5 priorities to move from reactive to predictive quality management

Activities and measures have often been defined to move away from a purely reactive quality management. But it has never quite worked.
Can artificial intelligence (AI) deliver on the promise? In our opinion, “yes and no.” No, because even artificial intelligence still has to learn from historical data first. So it will take hundreds, if not thousands, of data sets to teach an algorithm how to arrive at predictive insights. But once this is done, AI can deliver valuable results with extremely high precision. For example, correlations between measurement criteria and external influences that can be used to make predictions that need to be linked to actions and measures before the proverbial horse has already left the barn.
But what do you need to watch out for and what can you already prepare today to be ready for the introduction of artificial intelligence with “Predictive Quality” capabilities?

We’ve compiled the top 5 for you:

1. Collect data. As explained earlier, every algorithm needs historical data. The more, the better. This data can be, for example, measurement data, machine data for maintenance, or photos of products and their defects. How many data points you need will depend mostly on the complexity of the problem. But you will likely never hear the phrase “we have too much data” from a data engineer.
   
2. Involve your IT department early. Data becomes especially valuable when it is collected and analyzed across departmental boundaries. This will absolutely require your IT. In our experience, this and many other reasons speak in favor of involving internal IT as early and in good time as possible.
   
3. Democratize quality management. Only if your organization accepts quality management standards and actively reports and remedies quality problems will “predictive quality” fall on fertile ground. Therefore, try to convince as many stakeholders as possible of the relevance of quality management and take them along for the ride.
   
4. Link insights to actions. Real added value will only come when you link your AI’s prediction to appropriate actions. For example, a basic first action is to put alerts in your QMS.
   
5. Determine a method to calculate ROI. After all, if measures lead to a reduction in quality costs in the future, for example, it will become increasingly difficult to measure the success for the effort expended and thus justify the costs. Therefore, create a framework and methods in advance, how you want to prove the ROI today but also in the future.

We would be happy to discuss the topic of forward-looking quality management with you. See for yourself how our QMS supports you and which predictive quality capabilities are already available “out of the box”.

Further information: 
How Much Training Data is required for Machine Learning?

Predictive ROI