What is the Diatomic Molecule with the Largest Dipole Moment

We present a machine learning model for predicting the dipole moment of diatomic molecules using only atomic properties of the constituent atoms. First a training database of 273 diatomic molecules was constructed using experimental data and CCSD(T) calculated dipole moments. Using this we then constructed a large theoretical database consisting of 4851 diatomic molecules and this in turn allows us to answer the question "What is the diatomic molecule with the largest dipole moment". Similarly, our model identifies useful trends that explain the dipole moment of molecules, improving our intuition in chemical physics. We conclude with condensing our model into an analytical expression to predict the dipole moment in terms of atomic properties.