SynthLog: A Language for Synthesising Inductive Data Models

We introduce SynthLog, an extension of the probabilistic logic programming language ProbLog, for synthesising inductive data models. Inductive data models integrate data with predictive and descriptive models, in a way that is reminiscent of inductive databases. SynthLog provides primitives for learning and manipulating inductive data models, it supports data wrangling, learning predictive models and constraints, and probabilistic and constraint reasoning. It is used as the back-end of the automated data scientist approach that is being developed in the SYNTH project. An overview of the SynthLog philosophy and language as well as a non trivial example of its use, is given in this paper.