Abstract: In the framework of Density Functional Theory (DFT), much effort is concentrated on finding the total ground state energy as a functional of the density, whereas other ground state expectation values are less studied. In this talk we will motivate the search for an expression for the one-body density matrix as a functional of the density. We will discuss strategies to develop approximations, and the multiple role that machine learning can play in this context [1,2]. [1] A. Aouina, M. Gatti, and L. Reining, Faraday Discussions 224, 27 (2020) [2] J. Wetherell, A. Costamagna,, M. Gatti, and L. Reining, Faraday Discussions 224, 265 (2020)