Results and analysis of the 2013 ChaLearn cause-effect pair challenge

As is known, "correlation does not mean causation". More generally, observing a statistical dependency between A and B does not imply that A causes B or that B causes A; A and B could be consequences of a common cause. But, is it possible to determine from the joint observation of samples of two variables A and B that A should be a cause of B? There are new algorithms that have appeared in the literature in the past few years that tackle this problem. This challenge is an opportunity to evaluate them and propose new techniques to improve on them. We provided hundreds of pairs of real variables with known causal relationships from domains as diverse as chemistry, climatology, ecology, economy, engineering, epidemiology, genomics, medicine, physics. and sociology. Those were intermixed with controls (pairs of independent variables and pairs of variables that are dependent but not causally related) and semi-artificial cause-effect pairs (real variables mixed in various ways to produce a given outcome). This challenge was limited to pairs of variables deprived of their context. Thus constraint-based methods relying on conditional independence tests and/or graphical models were not applicable. The goal was to push the state-of-the art in complementary methods, which can eventually disambiguate Markov equivalence classes. The results are very promising: the winners achieved a score (symmetric AUC), which exceeded 0.8 (see the leaderboard) on a test set of over 4000 pairs. On real data (18% of he test data), the best participants achieved a score over 0.7.