When to do machine learning

I realized that before starting on technical details of methods I should write some about when to use machine learning, or when it is intelligent to use artificial intelligence ? In fact, in most of the cases avoid machine learning as much as possible. In first place, you use machine learning when your measurements, sensor values, data is not sufficiently descriptive to get final result that you are looking for. For example, covid tests works with very high precision currently. If your input is the result of the test you don't need machine learning. However, if you are detecting covid from chest x-ray you have many small tiny pixel transparancy measurements thus you need some kind of learning. In this case, you should ask while the alternative way is providing good quality result do we really need this learning ? In summary you should try to get descriptive data as possible in the first place. Later, if you have only small amount of samples, the best you can do is use them as test samples for your rule based system. You could use some manual statistical quantities as your learning tool at most. In the other extreme if you have too much data and low dimension you don't have to do machine learning either in most cases. Just pick the few closest point should be good enough estimate. Yes, we name this method as k-nearest neighboors machine learning method. In fact no learning is happening here, just memorization. Still, there are many variations and improvements in this line of research. Another point to consider if somebody already published a model that is close to your task. We will name some good quality pretrained models later. They could be in the forms of REST APIs or downloadable binary files. Lastly, if you don't see any other way rather than training your own model start with the simplest first. Understand your data and let the fun start for you.