Prediction is an unavoidable task for data scientists, and over the last decades statistics and machine learning became the most popular ‘prediction weapons’ in many fields. However, prediction should always be associated with a measure of uncertainty, because from it only we can reconstruct and falsify the model/algorithm decisions. Machine learning methods offer many point-predictions, but they rarely
yield some measure of uncertainty, whereas statistical models usually do a bad job in communicating predictive results. According to the Popper’s falsificationism theory, natural and physical sciences can be falsified on the ground of wrong predictions:
though, for social sciences this is not always true. We move then to a weak instrumentalist philosophy: predictive accuracy is not always constitutive of scientific success, especially in social sciences.
