We present forecasts of the Social Security trust fund, modeling key demographic and economic variables as time series. We evaluate plans for achieving long-term solvency by raising the normal retirement age (NRA), increasing taxes, or investing some portion of the fund in the stock market. Stochastic population trajectories by age and sex are generated using the Lee- Carter and Lee-Tuljapurkar mortality and fertility models. Economic variables are modeled as vector autoregressive processes. With taxes and benefits by age and sex, we obtain inflows to and outflows from the fund over time. Under current legislation, we estimate a 50% chance of insolvency by 2032. Investment in the market cannot keep the median fund solvent, even when the balance stays positive on average. The NRA must be raised to 71 by 2022 for a 66% chance of solvency beyond 2070. Solvency can also be achieved by raising the NRA to 68 by 2020, investing in the market, and increasing taxes one percent.