Abstract
For most active investors treasury bonds (govs) provide diversification and thus reduce the risk of a portfolio. These features of govs become particularly desirable in times of elevated risk which materialize in the form of the flight-to-safety (FTS) phenomenon. The FTS for govs provides a shelter during market turbulence and is exceptionally beneficial for portfolio drawdown risk reduction. However, what if the unsatisfactory expected return from treasuries discourages higher bonds allocations? This research proposes a solution to this problem with Deep Target Volatility Equity-Bond Allocation (DTVEBA) that dynamically allocate portfolios between equity and treasuries. The strategy is driven by a state-of-the-art recurrent neural network (RNN) that predicts next-day market volatility. An analysis conducted over a twelve year out-of-sample period found that with DTVEBA an investor may reduce treasury allocation by two (three) times to get the same Sharpe (Calmar) ratio and overper-forms the S&P500 index by 43% (115%).