SEC filings · portfolio models · research methodsPUBLIC OVERVIEW
FINANCIAL DATA & QUANTITATIVE ANALYSIS
Company financials, portfolio risk, and strategy testing.
QuantForge analyzes historical SEC company filings and provides working portfolio, risk, and valuation models. Explore reported financial trends, change model assumptions, and examine how strategies are evaluated. Public investment examples use simulated returns; a separate MFA-protected workspace uses available historical market data for personal research.
What the project covers
From filings to model evaluation
01 · DATA ENGINEERING
SEC financial data
Annual company facts with filing dates, fiscal-year selection, reported values, calculated margins, and missing-data checks.
02 · QUANTITATIVE ANALYTICS
Portfolio risk
Estimate covariance, apply position limits, compare allocations, and inspect volatility and downside assumptions.
03 · STATISTICAL RESEARCH
Strategy evaluation
Walk-forward testing with past-only training, separate evaluation windows, modeled costs, and benchmark comparisons.
04 · SOFTWARE ENGINEERING
Data and application engineering
Python processing, documented data sources, an authenticated research API, automated tests, and deployment checks.
More research in the private workspace
Separate data and access
Public examples can be explored without signing in. The private workspace adds historical market observations, investment selection, portfolio studies, and saved research. Methods and source code can be reviewed without access to private holdings or licensed data.
TIME SERIESWalk-forward testing
Past-only training, non-overlapping evaluation, costs, passive and rebalanced benchmarks.
Statistical validation
PORTFOLIO RISKConstrained optimization
Covariance estimation, weight caps, risk diagnostics, alternative allocation rules.
Optimization + risk
COMPANY FINANCIALSSEC scenario forecasting
Reported annual filings, FCF proxies, discounting, terminal-value and sensitivity analysis.
Financial modeling
APPLICATION DESIGNAuthenticated analytics
Read-only market feeds, owner-only storage, MFA, content security, and CI.
Explore reported annual revenue, operating income, growth, and cash flow from the reviewed SEC Company Facts snapshot. Filing dates and fiscal periods are shown alongside the figures.
Quick company examples:
Financial performance by company
SEC annual filings
Annual revenue trend
Reported · fiscal year
Reported annual figures
Compare companies
Latest available fiscal year
Rankings compare the latest available annual filing for each issuer, not a synchronized period or a sector-neutral investment signal. Missing values are unranked.
Inspect source tags and filing provenance
Source: SEC EDGAR Company Facts.
SEC company financials are real, historical disclosures. The margin scenario is hypothetical. Public portfolio, Quant, DCF and Company peers use illustrative or simulated inputs; they are not actual market results, valuations, or investment recommendations.
Portfolio simulator
Try virtual purchases, examine portfolio weights, and calculate a rebalance using example prices. Nothing connects to a brokerage account or uses live quotes.
Total value—
Cash—
Holdings—
Positions
Simulated trade
Assumed 0.05% transaction fee; no real orders
ETF holdings overlap
Illustrative ETF weights, not actual fund holdings
Rebalancing plan
Target weights sum to 100% including cash. Suggestions only; no transactions.
Risk and allocation models
Compare portfolio allocations under concentration limits, using simulated daily returns. Estimated volatility and downside outcomes depend on the chosen assumptions.
Portfolio assumptions
276 simulated sessions · 1,800 Monte Carlo paths
DCF scenario model
Change projected growth, margins, and discount rates to see how a hypothetical discounted cash flow estimate changes. Inputs are illustrative, not reported company forecasts. For observed company accounts, use SEC company financials.
Discounted cash flow inputs
Peer comparison model
See how standardized financial ratios affect company similarity rankings. This example uses synthetic feature data; the SEC company financials page contains reported figures.
Five features: revenue growth, operating margin, net margin, free-cash-flow margin and debt/assets.
FINANCIAL FINDINGS & QUANTITATIVE MODELS
Analysis dashboard
Explore three working analyses: SEC company trends, minimum-variance portfolio allocation, and rolling strategy evaluation. Each view displays calculated results, charts, and the assumptions needed to interpret them. SEC financials are historical facts; investment return examples are simulated.
Data engineeringSEC ingestion, alignment, validation and provenance
Data analytics & BIRevenue KPIs, comparisons, trends and findings
Data scienceModel fitting, rolling evaluation and sensitivity
Financial analysisMargins, growth, company financial statements
Quantitative financeCovariance, constrained allocation, fees and drawdowns
01 · Company performanceHistorical SEC data
Select a company to compare revenue, year-over-year change, and operating margin across available fiscal years. Charts and figures come from the reviewed SEC snapshot; missing figures are labeled unavailable.
Adjust the maximum position size to compare equal weighting with an estimated minimum-variance allocation. The model uses synthetic returns and a shrinkage-adjusted covariance estimate; results are fitted, not observed market performance.
Changing settings updates both quant exhibits below
03 · Walk-forward comparisonSimulated past-only rolling experiment
Two strategies use the same five simulated investment baskets. Each 20-session test window follows a separate training window; both paths include modeled rebalancing costs. Compare their ending wealth and drawdowns without treating the result as historical investment performance.
04 · Code, inputs, and testsEngineering evidence
Company charts read the reviewed SEC snapshot. Portfolio and walk-forward charts use seeded synthetic returns. The source files and tests show the calculations, validation checks, and separation from authenticated research data.
Public calculations and regression tests
Projection to weight constraints, covariance construction, train/test separation, and missing SEC-data behavior.
The authenticated workspace uses selected historical investments and separate portfolio models. Implementation files are public; personal results and market-data access are not.
Interpretation: the public charts demonstrate an implemented statistical workflow, not independently validated market-beating performance. The current SEC snapshot is historical. The public synthetic return generator is not a market data provider, forecast, or estimate of live asset risk.
RESEARCH SYSTEMS · PUBLIC TECHNICAL EXHIBIT
Research methods
These notes explain the data pipeline, portfolio mathematics, time-series evaluation, and valuation methods used in QuantForge. Examples identify their input sources and known limitations. Private investment records and market observations are not shown.
Real SEC disclosures in public explorerIllustrative diagrams belowPrivate datasets stay private
From source data to tested output
Architecture at a glance
01 / DATA ENGINEERINGIngest & normalizeSEC annual facts; Alpaca historical equity, ETF and supported crypto observations in the private workspace
02 / VALIDATIONTrust the inputsFiscal periods, market calendars, aligned prices, missing values, source attribution and SHA-256 dataset fingerprints
03 / MODELSQuantify trade-offsPortfolio risk, constrained allocation, scenario DCF proxies, historical-momentum research and stress tests
04 / EVALUATIONChallenge the resultPast-only fitting, out-of-sample windows, fees, passive benchmarks, leave-one-window-out robustness and research reports
The public deployment hosts static demonstrations and a reviewed SEC snapshot. Market observations and personal virtual accounts are only accessed in authenticated private workflows.
Observed financial relationships in SEC filings
Reported annual facts · calculated comparisons
Annual revenue growth and operating margin are calculated from the public SEC Company Facts snapshot. Each point represents a company and its latest comparable fiscal periods. Unlike the illustrated strategy charts below, these values come from reported company filings.
Reported financial comparisons are available when the verified SEC snapshot is present.
This is an exploratory comparison, not a factor-return model or a company ranking. Fiscal year-ends differ, and operating margin and revenue growth alone do not determine a stock's future performance.
Implementation and test references
Algorithms · diagnostics · engineering judgment
QUANTITATIVE FINANCE / NUMERICAL OPTIMIZATION
01. Constrained portfolio optimization
Allocation weights are fitted from observed returns and an estimated covariance matrix, subject to feasibility and concentration limits.
Implemented privately
min wᵀΣw subject to Σwᵢ = 1; 0 ≤ wᵢ ≤ cap
Why it matters: the objective is predicted portfolio variance, not a guarantee of realized return. The private optimizer supports a covariance-based minimum-risk allocation and alternative inverse-volatility / return-tilt allocations.
Align price histories to comparable observations before estimating returns.
Apply covariance stabilization/shrinkage and reject impossible weight caps.
Compare annualized volatility, drawdown, tail loss and alternative allocations.
Implementation and verification detail
Estimated portfolio volatility is √(wᵀΣw) × √annualization; optimization remains sensitive to return sampling, correlated assets and constraints. Tests check symmetry, finite prices, positive covariance diagonals, feasibility and weight normalization.
Schematic risk vs. return trade-off
Illustrative positions, not an empirical efficient frontier or a private portfolio result.
STATISTICAL VALIDATION / TIME SERIES
02. Rolling walk-forward evaluation
A model trains on past observations, then is evaluated on the following unseen sessions. The allocation is refitted at later boundaries.
Implemented privately
Train[t₀:t₁] → Fit w₁ → Test[t₁:t₂] → Roll forward
The private study supports non-overlapping evaluation windows, modeled turnover and basis-point transaction fees, two rebalanced strategies, and a passive equal-weight buy-and-hold comparison.
Run each allocation rule against matched evaluation dates.
Reconcile per-window fees to total reported costs.
Perform leave-one-window-out diagnostics; a changed winner signals sample dependence.
Preserve observations and model settings in versioned research manifests.
Where bias can still enter
Past-only fitting reduces mechanical look-ahead within the test, but cannot eliminate survivorship bias, post-hoc asset selection or tuning parameters after seeing outcomes. Omitting a window without refitting is a sensitivity check, not independent validation.
Rolling evaluation boundaries
Window 1
Window 2
Model portfolioBenchmark
Diagram only; wealth paths are drawn for explanation, not copied from private analysis.
FINANCIAL MODELING / SEC DISCLOSURES
03. SEC-backed forecast sensitivity
Observed company financials are kept distinct from hypothetical revenue-growth, cash-flow-margin and discounting assumptions.
Real source + modeled scenarios
FCFₜ = Revenue₀(1+g)ᵗ × margin
PV = Σ FCFₜ/(1+r)ᵗ + TV/(1+r)ᴺ
Real SEC annual statements establish the observed baseline. The model projects three- to seven-year hypothetical scenarios and produces a sensitivity grid for revenue growth and the discount rate.
Report free cash-flow proxy as operating cash flow less cash PP&E purchases.
Distinguish discounted cash-flow proxy from an equity value or share-price target.
Display how much present value comes from the terminal component.
Reject impossible assumptions and missing SEC cash flows instead of fabricating data.
Terminal-value risk
Terminal value extrapolates cash flows beyond the explicit projection horizon. When the terminal share dominates, small changes in discount and perpetual growth rates can materially change the result. Debt, excess cash and capital-structure adjustments are not included in this proxy.
How scenarios respond to assumptions
Change
Effect on modeled proxy
Higher assumed revenue growth
Usually higher
Higher assumed FCF margin
Higher
Higher discount rate
Lower
Higher terminal growth (r > g)
Usually higher
Directional sensitivities are mathematical examples, not measured company forecast accuracy. Real reported values are available in SEC Financials.
DATA SCIENCE / EXPLAINABLE RESEARCH
04. Historical investment screening
A private shortlist compares price momentum, realized volatility and drawdown, while displaying available SEC fundamentals separately.
Owner-only research
Score = Σ (lens weightₖ × normalized metricₖ)
Growth, balanced and risk-aware lenses change how much weight the model places on trailing return, recent momentum, annualized volatility and historical drawdown. The score is an explainable heuristic, not a probability of gain.
Use selectable investment names rather than requiring ticker memorization.
Flag sparse histories and report the period and IEX/SIP source.
Show SEC revenue growth and FCF margins only when disclosed facts support them.
Keep ranking and trade execution separate; no brokerage orders are placed.
Why a top-ranked investment may still be unattractive
Momentum and low observed volatility do not measure whether a stock is expensive relative to its future cash flows. Future returns also depend on valuation, concentration, news and unforeseeable events. The research lens is for comparing candidates, not picking guaranteed winners.
Explainability layers
EvidencePrice history, volatility, drawdown and optional SEC context
ScoreWeighted, bounded and traceable to its inputs
DecisionManual research and hypothetical portfolio workflow, not an order
The private browser uses real historical observations when authorized; no private rankings or selected holdings are displayed here.
Research integrity and engineering controls
Reproducibility + security
Source lineage
Issuer and fiscal-year filtering, filings and cutoffs, calendar alignment, adjusted-provider-price attribution and unavailable-value handling.
Reproducible manifests
Versioned exports include investment symbols, settings, evaluation dates, fee rules and SHA-256 input fingerprints; raw licensed prices are not exported.
Testable calculations
Python and JavaScript tests include invalid prices, impossible allocation caps, missing filings, look-ahead prevention, fee reconciliation and prior-window comparisons.
Release gates
GitHub Actions checks Python 3.11 and 3.12, the private regression suites, privacy review, script syntax and compiled Content Security Policy hashes.
PUBLICCloudflare PagesReal SEC snapshot and labeled browser-only illustrative models
EDGEScoped API proxyRestricted configured upstream; private backend credentials not returned
PRIVATE APIRender / FastAPIAuthorized requests for market observations and personal state
IDENTITY & DATASupabase MFAAuthenticator step-up and owner-scoped virtual account records
The diagrams document intended and tested boundaries, not a claim that any production system is immune to attack. SHA-256 fingerprints detect changed in-memory inputs but do not authenticate the provider or replace archived source data.
Implementation and test evidence
Source code · numerical checks
The public exhibits document methods that are implemented in the project. The source files and focused regression tests provide a direct way to inspect the algorithms, data boundaries, and handling of failure cases without signing into the private workspace.
SEC data preparation
Annual Company Facts selection, derived metrics, filing lineage, and CSV validation.
These source references verify the implementation and test coverage, not the profitability of any allocation strategy. Private research datasets, account details, and credentials are not part of the public exhibit.
PUBLIC MODELS
Explore the calculations
Reported SEC annual statements and illustrative statistical models are available publicly. Historical market-data research and personal virtual accounts remain authenticated.
METHODS
Data and engineering
Where the data comes from, how the models are checked, and how the public site is separated from private research.
Private models and public source code
Implementation references
The private workspace supports historical market analysis, portfolio optimization, strategy evaluation, investment screening, and SEC-based valuation scenarios. The methods page explains the underlying calculations; the repository contains the implementations and tests.
The public browser does not request raw filings or private market quotes. A locally generated and reviewed snapshot is embedded when the site is built. Figures do not auto-refresh.
Missing values remain unavailable rather than zero-filled. Company fiscal year-ends are not aligned; broad sector groupings are editorial and are not normalized industry classifications.
Public examples and their data
Interactive · illustrative
Portfolio simulator
Virtual positions, example prices, rebalancing weights, and estimated fees. Everything stays in the browser session and does not place orders.
Quantitative modeling
Simulated returns, covariance, constrained allocation, and Monte Carlo downside. Results are not calibrated forecasts of market risk.
DCF sensitivity
Illustrative cash-flow assumptions with discounting and terminal-value sensitivity. These are not live company valuations.
Company similarity
Standardized synthetic fundamentals demonstrate nearest-neighbor comparisons. Use SEC Financials for actual company comparisons.
Private API credentials stay server-side. No Alpaca observations, personal positions, or authenticator secrets are bundled into the public demonstration. Research scripts have deterministic tests, and GitHub CI validates both Python and JavaScript with a restrictive Content Security Policy.
Engineering checks
Architecture and tests
Data engineering
Named SEC issuer identifiers, annual-period filtering, filing cutoffs, input validation, recorded sources and accession details.
Python backend, static hosted frontend, automated Python and JavaScript checks, continuous integration, and a restrictive script Content Security Policy.
Privacy boundary
Public research data is separate from the owner-only workspace. Private holdings and Alpaca access are protected by authenticated endpoints and authenticator MFA.
The private workspace provides real market observations and virtual trading for the owner only. Public visitors cannot use that API as an open data source.
Data and model validation
Quality gates and failure cases
Layer
Example invariants
Why it matters
Historical data
Finite positive prices; aligned time series; observed-versus-derived SEC metrics
Rejects inconsistent or fabricated model inputs
Optimization
Weights sum to one; asset caps feasible; covariance symmetric; finite estimates
Prevents invalid portfolios from appearing plausible
Walk-forward
Past-only fitting; disjoint test windows; transaction-fee reconciliation
Reduces leakage and makes comparisons auditable
Forecast
Growth and discount assumptions valid; unavailable FCF remains unavailable
Tests confidentiality and deployed script integrity
CI runs Python 3.11 and 3.12 along with JavaScript checks. Passing tests provide scoped evidence, not investment performance claims or complete security assurance.
Historical financial disclosures may be updated or restated. Model scenarios are not investment advice.
Private workspace
Private · Sign in required
Personal holdings, market-history analysis, and company valuation. Sign-in and authenticator verification required.
Sign in
Owner access only. Password and authenticator verification are required.
Authenticator verification
Enter a six-digit code from your authenticator app.
Scan the code with an authenticator app. Keep the authenticator and its recovery options secure.
Private portfolio · authenticated
Research investments
Used in Market data, Optimization, Backtests and Walk-forward
Choose 2–5 investments and a time period, then load their price history. Optimization, backtesting and walk-forward testing use the same loaded observations. Changing the selection or period requires reloading and recalculating.
Choose investments to compare.
Selected investments:None selected
Historical data loaded:No historical data loaded
No market history loaded for the current selection.
Virtual portfolio value—
Available cash—
Invested value—
Holdings
Holdings by weight
Add virtual holdings to see allocation.
Proposed purchase impact
Check how a hypothetical cash-funded purchase changes your current virtual portfolio weights, using available market observations. This calculation neither records a virtual trade nor places a brokerage order.
Choose from screened investments or current virtual holdings.
Prices and virtual trades
Request the latest available stock, ETF, or supported cryptocurrency observation, then record a simulated trade if desired. Prices are source- and time-stamped; no brokerage order is sent.
No investment selected
No quote loaded.
HISTORICAL PRICE AND FINANCIAL DATA
Investment screening
Compare selected stocks and ETFs using historical momentum, volatility, drawdown, and available SEC fundamentals. Scores rank candidates under the selected criteria; they do not estimate future returns or recommend trades.
Screening list
Choose companies by name or use the starting shortlist.
HISTORICAL DECISION SUPPORT
Screening summary
Summarizes comparative measures, overlap with existing holdings, and unresolved risks. Historical ranks are not trade recommendations.
Reading the scores
A higher research score indicates a more favorable balance of past momentum and realized risk under the selected lens. It is not an estimated probability of profit, expected return, or price target. SEC results describe past business finances separately; ETFs generally do not have comparable company income statements. Reassess against valuation, diversification, fees, tax impact, investment horizon, and the risk of loss before any real-money decision. IEX-only bars are not consolidated market-wide prices.
Historical prices and risk
Load daily stock, ETF, or supported USD cryptocurrency prices from the private Alpaca connection. Equity prices are price-only, excluding dividends; cryptocurrency trades seven days a week.
Check the Research investments panel above for selected symbols, loaded observations, and date coverage.
Load a historical series to begin.
Optimize an allocation
Use the loaded historical returns to calculate long-only weights subject to concentration limits. Review correlations and risk contributions before interpreting the proposed allocation. Results do not alter your virtual holdings.
Select 2–5 investments in Market data, load their history, then calculate an allocation.
Risk diagnostics
Risk estimates use historical returns and a 20% diagonal covariance shrinkage. Correlations, drawdowns, and tail-loss statistics describe the selected sample; they do not predict future outcomes.
Risk diagnostics appear after an allocation is calculated.
Buy-and-hold vs. rebalancing
Compare equal-weight buy-and-hold and monthly rebalancing on the loaded historical price series, after modeled transaction fees. These are retrospective calculations, not an executable trading record.
Walk-forward strategy comparison
Fit portfolio weights on earlier prices and evaluate on subsequent periods, refitting at each boundary. Compare against equal-weight rebalancing using the same transaction-fee assumptions. No brokerage orders.
Load price history in Market data to begin.
Performance and risk diagnostics
Benchmark and sensitivity checks
Compare a passive benchmark, alternative weight rules, larger fees, and leave-one-window-out sensitivity on matched evaluation dates. Select a longer history in Research investments and reload if the analysis has too few test windows.
Run Walk-forward first, then check robustness.
Model uses price-only historical returns; no dividends, borrow costs, slippage, taxes, or corporate-action simulations. Backtests remain subject to selection bias and do not establish future performance.
SEC-based valuation scenarios
Start with company cash-flow disclosures and vary growth, discount, and terminal-value assumptions. Alpaca prices are separate market observations, not accounting data. Scenario values are not price targets.
No company selected
Market price and financial context
SEC-reported shares and annual cash flows are compared with the latest available Alpaca market observation. Ratios depend on disclosure dates and quote coverage; they are not fair-value estimates.
Multi-year cash-flow scenarios
Projections use the selected company’s reported SEC annual baseline and hypothetical revenue growth, FCF-margin, and discount-rate assumptions. Conservative and optimistic cases vary growth by 4 percentage points and FCF margin by 3 points. Reported statements remain unchanged.
Load SEC statements for a selected company first.
Valuation sensitivity
Company comparison
Virtual cash balance
Add or withdraw simulated cash, or reset virtual holdings and transaction history. These changes do not move actual money. Saved research notes are preserved after a portfolio reset.
Saved research notes
Watchlist: None
Choose an investment
Search by company or fund name; ticker symbols are optional.