daniel2371 / casual-graph Goto Github PK
View Code? Open in Web Editor NEWThis project forked from 10-academy-quad-squad/casual-graph
Machine learning algorithms tend to focus on making the most accurate predictions or classifications rather than providing insights on the cause-and-effect relationships of features. But unlocking the cause and effect relationship can be important in decision making, especially in the sectors of health. It would also help to build more accurate models that exploits not only the data but also the cause and effect structure of the data. Casual inference is to infer what causes what. Casual inference enables us to answer questions like what causes what or what would be the effect if we improve some features ? This type questions can not be answered by machine learning algorithms only. we may calculate correlation or feature importance from machine leaning models, but machine learning algorithms captures association or correlation and not causation.