Chai Wah Wu from IBM’s TJ Watson Research Center has built a machine-learning algorithm using data from OEIS to learn to identify if a sequence will be interesting or not:
Abstract: "We explore the possibility of using machine learning to identify interesting mathematical structures by using certain quantities that serve as fingerprints. In particular, we extract features from integer sequences using two empirical laws: Benford's law and Taylor's law and experiment with various classifiers to identify whether a sequence is nice, important, multiplicative, easy to compute or related to primes or palindromes."
MIT technology review has made an article about this paper: https://www.technologyreview.com/s/611272/this-algorithm-can-tell-which-number-sequences-a-human-will-find-interesting/