About Simfolio

Built by Investors, for Investors.

Simfolio uses academic research and gold-standard methodologies to create portfolio management tools, providing investors with the infrastructure to use them systematically.

Simfolio is self-funded, independent and built by a small team of investors focused on developing institutional-grade workflows.

For more details, please see the Methodology page.

Question #1

How has this investment performed historically?

Backtests — Analyze up to 125 years of daily historical data.
Returns — Compare portfolio and benchmark wealth paths, and review return histograms and tables at annual, quarterly, monthly, weekly, or daily frequencies.
Risk and return — Review risk-versus-return and seasonality charts, plus CAGR, volatility, and more than 100 performance metrics.
Drawdowns — Inspect historical drawdown paths and interactive episodes by depth, duration, and recovery.
Rolling horizons — Explore portfolio behavior and metrics over any selected rolling horizon, including holding-period outcomes.
Market history — Compare results across historical stress tests and market stress periods.
Allocations — Review current and historical holdings, portfolio weights, and benchmark comparisons.
Portfolio activity — Examine rebalancing, cash flows, inflation effects, turnover, and estimated trading costs.
Taxes — Review configured tax overlays and realized gains or losses when supported by the selected assumptions.
Risk diagnostics — Compare risk and return attribution, asset contributions, correlation, and beta.
Withdrawal analysis — See historical safe and perpetual withdrawal rate outcomes.

Question #2

How does Simfolio make portfolio simulations robust?

Simulation horizons up to 100 years, with predictive distributions and percentile wealth paths.
Default and Frontier simulation models
Model selection from 200+ evaluated methodologies
Rolling-origin out-of-sample validation across 80 multi-asset portfolios
Dynamic multiscale stochastic volatility
Empirical fat tails and cross-asset return dependence
Simulation drawdown and rolling-metric distributions
Simulation cash-flow funding and downside-risk analysis
Simulation-based portfolio optimization

Question #3

What drives this portfolio’s performance?

Risk and return attribution
Custom factor regression
CAPM, Carhart FF4, Fama–French FF3/FF5/FF6, and q-factor Q5 regressions
Market-adjusted BAB and QMJ regressions, plus exploratory FF8 and FF10 extensions
Custom return factors
Factor loadings, significance, premiums and return contributions
Rolling factor exposures and residual diagnostics
Principal component analysis with variance, loading and stability views
Correlation and beta matrices
Diversification, concentration, timing and illiquidity diagnostics
Benchmark-relative performance and risk metrics

Question #5

How can we integrate AI infrastructure to improve research?

Read workspace defaults and list or inspect your saved workspaces and research.
Create workspaces from completed analyses, rename or delete workspaces, and create, update, or delete saved portfolios.
Run backtests and simulations, check run progress, and search or page through website-equivalent results.
Run Backtest and Simulation Optimizers, Factor Regression, Principal Component Analysis, Rolling Metrics, and Simulation Drawdown.
Run Lump Sum vs DCA, Statistical Evidence, Rebalancing Sensitivity, Rebalancing Timing Sensitivity, and Start Year Sensitivity.
Explicitly save completed workspace results and reopen saved research without rerunning the analysis.