Contrast data mining for the MSSM from strings

TL;DR

This paper uses data mining techniques to identify patterns in string theory landscapes that help efficiently find MSSM-like models, leading to the discovery of many new models especially in previously hard-to-access regions.

Contribution

It introduces contrast pattern mining to string landscape analysis, enabling targeted searches for MSSM-like models across various orbifold geometries.

Findings

Identified contrast patterns with physical interpretation.

Enhanced search efficiency for MSSM-like models.

Discovered novel models with specific flavor symmetries.

Abstract

We apply techniques from data mining to the heterotic orbifold landscape in order to identify new MSSM-like string models. To do so, so-called contrast patterns are uncovered that help to distinguish between areas in the landscape that contain MSSM-like models and the rest of the landscape. First, we develop these patterns in the well-known $\mathbb{Z}_6$-II orbifold geometry and then we generalize them to all other $\mathbb{Z}_N$ orbifold geometries. Our contrast patterns have a clear physical interpretation and are easy to check for a given string model. Hence, they can be used to scale down the potentially interesting area in the landscape, which significantly enhances the search for MSSM-like models. Thus, by deploying the knowledge gain from contrast mining into a new search algorithm we create many novel MSSM-like models, especially in corners of the landscape that were hardly accessible by the conventional search algorithm, for example, MSSM-like $\mathbb{Z}_6$-II models with $\Delta(54)$ flavor symmetry.