Novel ML Approaches for Treasury Forecasting - A Literature Survey

U.S. government bonds are affected by central bank decisions. Bonds are less easily traded than stocks and the public data about them are not abundantly avail- able. In this project, we review the state-of-the-art methods in machine learning (ML) and artificial intelligence (AI) methods employed in forecasting interest rates for U.S. treasuries of varying maturities. Our work will highlight how powerful AI techniques can be leveraged in more accurate predictions of movement in treasury/government bonds.