About Us+
Products+
Solution+
Cases+
AI Lab+
Investor+
Contact+
Join Us +
Trial+
In the field of interpretable machine learning, the simplest way to obtain interpretability is to use traditional interpretable statistical models, such as linear regression, logistic regression, decision tree model and so on. However, the traditional statistical model often has the disadvantage of low accuracy. In order to pursue higher accuracy, people often choose some popular machine learning models, including black box model. The accuracy of black box model is very high, but the interpretability is poor. People can not know why the model gives this result, let alone how to judge the rationality of the result. In order to solve this problem, scientists propose a model agnostic interpretable method. It can analyze some interpretable properties after the model training, so as to get rid of the limitation of the model itself.