# Getting CICY High

## TL;DR

This paper demonstrates that machine learning models, trained on low Hodge number CICY geometries, can effectively predict properties of more complex geometries, improving accuracy with targeted training data.

## Contribution

It introduces a machine learning approach to predict string geometry properties, showing success with neural networks and SVMs on CICY datasets, especially with strategic seeding.

## Key findings

- Neural networks and SVMs predict trends in Kähler parameters.
- Training on low $h^{1,1}$ geometries generalizes to higher $h^{1,1}$.
- Seeding training data improves numerical accuracy.

## Abstract

Supervised machine learning can be used to predict properties of string geometries with previously unknown features. Using the complete intersection Calabi-Yau (CICY) threefold dataset as a theoretical laboratory for this investigation, we use low $h^{1,1}$ geometries for training and validate on geometries with large $h^{1,1}$. Neural networks and Support Vector Machines successfully predict trends in the number of K\"ahler parameters of CICY threefolds. The numerical accuracy of machine learning improves upon seeding the training set with a small number of samples at higher $h^{1,1}$.