AI Case Studies of Test Approaches adopted


I’m looking for real life examples of testing Machine Learning solutions, e.g. solutions that adopt random forest decision trees for example.

Where I am currently working I have a challenge of this ilk to address and the current view on the solution to the problem excludes testers - it’s along the lines of “only data scientists can do that”. I instinctively do not buy that so I’m looking for a proxy or two that allows me to assess a reality rather than a theory :slight_smile:



It is false that only data scientists can get involved in testing the AI as you have correctly predicted. We need testers too.
To train the AI, we need good input/output combinations (which we call a training dataset). So to work with modern software we need to choose this training dataset carefully as the AI starts learning from this and starts creating relationships based on what we give to it. Also, it is important to monitor how the AI is learning as we give different training datasets. This is going to be vital to how the software is going to be tested as well. Testers can be involved in this process of training the AI.

Also, it is important to ensure while working with AI the security, privacy and ethical aspects of the software are not compromised. All these factors contribute to better testability of the software. This is where a tester mindset is important and really beneficial.

In terms of real life example of using AI, I hosted a webinar on this and people talked about how they handled testing AI based systems. You can check it out here -

So no matter what algorithm you are using Random Forests, Boosted Trees, Kernel Vector, Linear Regression or Deep neural networks, testers can definitely get involved in the whole process.