A novel framework for constructing partially monotone rule ensembles

In many machine learning applications there exists prior knowledge that the response variable should be non-decreasing in one or more of the features. For example, the chance of a tumour being malignant should not decrease with increasing diameter (all else being equal). While a number of classification algorithms make use of monotone knowledge, many are limited to full monotonicity (in all features). Taking inspiration from instance based classifiers, we present a framework for monotone additive rule ensembles that is the first to cater for partial monotonicity (in some features). We demonstrate it by developing a partially monotone instance based classifier based on L1 cones. Experiments show that the algorithm produces reasonable results on real data sets while ensuring perfect partial monotonicity.