monte_carlo_returns_ts

property MonteCarlo.monte_carlo_returns_ts

Generate portfolio monthly rate of return time series with Monte Carlo simulation.

Monte Carlo simulation generates n random monthly time series with a given distribution. Forecast period should not exceed 1/2 of portfolio history period length.

First date of forecaseted returns is portfolio last_date.

Returns:

DataFrame

Table with n random rate of return monthly time series.

Notes

The draw is generated once and cached: repeated accesses return the same scenarios until a Monte Carlo parameter changes (distribution, distribution_parameters, period, mc_number or seed), which invalidates the cache. Set seed for reproducible draws (see MonteCarlo.seed). This shared cache is what keeps monte_carlo_wealth and monte_carlo_cash_flow consistent on the same scenario set.

Examples

>>> pf = ok.Portfolio(
...     ["SPY.US", "AGG.US", "GLD.US"],
...     weights=[0.60, 0.35, 0.05],
...     rebalancing_strategy=ok.Rebalance(period="month"),
... )
>>> pf.dcf.set_mc_parameters(period=8, mc_number=5000, seed=0)
>>> pf.dcf.mc.monte_carlo_returns_ts
                 0         1         2     ...      4997      4998      4999
2021-07 -0.008383 -0.013167 -0.031659  ...  0.046717  0.065675  0.017933
2021-08  0.038773 -0.023627  0.039208  ... -0.016075  0.034439  0.001856
2021-09  0.005026 -0.007195 -0.003300  ... -0.041591  0.021173  0.114225
2021-10 -0.007257  0.003013 -0.004958  ...  0.037057 -0.009689 -0.003242
2021-11 -0.005006  0.007090  0.020741  ...  0.026509 -0.023554  0.010271
           ...       ...       ...  ...       ...       ...       ...
2029-02 -0.065898 -0.003673  0.001198  ...  0.039293  0.015963 -0.050704
2029-03  0.021215  0.008783 -0.017003  ...  0.035144  0.002169  0.015055
2029-04  0.002454 -0.016281  0.017004  ...  0.032535  0.027196 -0.029475
2029-05  0.011206  0.023396 -0.013757  ... -0.044717 -0.025613 -0.002066
2029-06 -0.016740 -0.007955  0.002862  ... -0.027956 -0.012339  0.048974
[96 rows x 5000 columns]