PROJECT TITLE :

The Visual Causality Analyst: An Interactive Interface for Causal Reasoning

ABSTRACT:

Uncovering the causal relations that exist among variables in multivariate datasets is one amongst the ultimate goals in knowledge analytics. Causation is connected to correlation but correlation does not imply causation. While a range of casual discovery algorithms are devised that eliminate spurious correlations from a network, there aren't any guarantees that all of the inferred causations are indeed true. Hence, bringing a website skilled into the casual reasoning loop can be of great profit in identifying erroneous casual relationships advised by the discovery algorithm. To handle this need we tend to gift the Visual Causal Analyst-a unique visual causal reasoning framework that permits users to apply their experience, verify and edit causal links, and collaborate with the causal discovery algorithm to spot a valid causal network. Its interface consists of both an interactive 2D graph view and a numerical presentation of salient statistical parameters, such as regression coefficients, p-values, and others. Each help users in gaining a smart understanding of the landscape of causal structures significantly when the amount of variables is massive. Our framework is also novel in that it can handle both numerical and categorical variables within one unified model and come plausible results. We demonstrate its use via a collection of case studies using multiple practical datasets.