In extreme value statistics, the tail index is used to measure the occurrence and the intensity of extreme events. In many applied fields, the tail behavior of such events depends on explanatory variables. This article proposes an ensemble learning method for tail index regression which is called Hill random forests and combines Hill's approach on tail index estimation (Hill (1975)) with the aggregation of randomized decision trees based on the gamma deviance. We prove a consistency result when the tail index function is a multiplicative function.