Businesses are changing systems
Study growth and operating outcomes as processes, not merely snapshots of financial statements.
StockPhys is building computational tools to explore how companies grow, change, and create value. Our models connect business fundamentals, quantitative dynamics, and uncertainty—without pretending any single price forecast is certain.
Research software in development · Not investment advice · No live user registration yet
Explore how a hypothetical price-target distribution changes across simplified scenarios. This is an illustration, not a calculated value for any security.
Synthetic distribution. Arbitrary normalized price index; no ticker, market data, calibration, or investment signal. Scenarios are purely illustrative.
Study growth and operating outcomes as processes, not merely snapshots of financial statements.
Explore plausible scenarios without mistaking mathematical sophistication for predictive certainty.
Judge calculations against later reported fundamentals. Show misses and limitations alongside successes.
Explore our retrospective PLTR 2023 Growth Dynamics Model backtest. See what the numerical run predicted for adoption, revenue and operating income, then compare each with what the company reported.
Point-in-time retrospective analysis with Feb. 28, 2023 information cutoff. Backtest, not an archived live forecast. Includes substantial misses.
We begin with historical company information and define assumptions about customer acquisition, market opportunity, monetization, and profitability. StockPhys then uses its private calculation engine to explore how those business drivers may translate into measurable company outcomes.
Reported company fundamentals and the relevant information cutoff define the available evidence.
Scenario inputs describe customer growth, market opportunity, revenue generation, and operating economics.
Supported outputs can include customer counts, revenue, and operating income. We compare historical calculations with realized results and disclose misses.
This is a conceptual explanation, not a full disclosure of the mathematical implementation. Specific assumption-to-output relationships must be validated for each enabled model.
We’re building a small research community rather than opening access indiscriminately. The first accounts will have a personal workspace, controlled simulations, saved cases, and a feedback channel once the secure beta backend passes launch checks.
View beta programServer-enforced admission quota; registration closes when the tenth account is admitted.
No payments or plans in the initial beta. Paid research capabilities will be a separate release.
Published policies and account controls before any personal information is collected.