Ionic liquids can be considered as nonaqueous, highly concentrated electrolytes composed entirely of ions with melting points typically less than 100⁰C. Many ionic liquids are derived from an organic cation and an organic/inorganic anion, at least one of them possessing low charge density, rendering them liquids near ambient conditions. Properties such as negligible vapor pressure, nonflammability, and high thermal stability are primary drivers for using ionic liquids as potential electrolytes in the next-generation batteries and energy storage devices. Despite the favorable attributes, challenges surrounding low ionic conductivity and sometimes low electrochemical stability need to be surmounted. Although ionic liquid properties can be tuned by changing the cation, anion, and/or substituents on the ions, the chemical space is too vast to be navigated efficiently either experimentally or using atomistic simulation techniques. In this presentation, our efforts at addressing these challenges with machine learning techniques will be described.