SecondOrder Homology
v1.2.1

About SecondOrder Homology

SecondOrder Homology is an interactive bilingual market research workspace. It studies how stock relationships change through persistent homology, including Vietoris–Rips filtrations, H0 and H1 persistence diagrams, barcodes, and persistence landscapes.

How to Explore

Choose assets and a history range. Inspect market geometry and historical analogues. Compare subsequent price behavior and run walk-forward validation. Supporting views cover correlations, risk, price paths, distributions, candles, and price-volume order.

Data and Limitations

Live market history depends on a data provider. Uploaded CSV and explicitly selected synthetic data are alternative sources. Historical similarities and validation results do not establish trading profitability or future predictive performance.

SecondOrder Homology 是一个双语市场研究工作台,展示股票相关结构、持久同调、历史相似区间及滚动验证。可使用市场历史数据、CSV 或明确标注的合成数据。历史相似性不保证未来预测表现。

SecondOrder · Homology

Does Market Topology Add Information Beyond Correlation?

Compare asset relationships across time and test historical matches against a correlation benchmark.

Historical ResultsPrediction Error on Shared DatesMAE on shared scored dates · lower is better1415161718Original Study5 paired dates15.23415.673+0.438Δ MAE · ppExtended History6 paired dates16.09417.137+1.043Δ MAE · ppMAE · percentage pointsCorrelation benchmarkTopology · H₀ + H₁
Each study compares the same scored dates. These are historical results; the independent test is still pending.
Market Workspace

META Meta Platforms

Loading market data…
Chart view only

Slide the bar below or drag in the chart to browse history. Choose Select period or hold Shift while dragging to select analysis dates. Ctrl + scroll zooms.

Loading market data…
Select a Period

Choose the Observation Period

The same dates and asset basket drive structure, historical search and supporting views. Select 10–120 completed sessions.

Selected Candle

Daily OHLC does not reveal the order of the high and low.

Historical Analogues

Where Have We Seen Similar Structure?

Which earlier periods had similar relationships between assets?

Interpretation

Historical outcome horizon

How to Read Homology

This compares relationships between assets, not just the selected stock’s price shape. Each future horizon uses earlier periods whose later outcomes are already complete before your selection. Matching stability measures whether references remain similar after small changes to the input data. Low stability means caution. Changing the horizon changes the historical group; it does not forecast your selected stock.

Robust linear and rank correlation distances feed exact Rips H₀/H₁ diagrams. Diagrams lose asset identity. Each outcome horizon has its own mature cohort. References are separated by the window plus horizon. Sensitivity uses eight joint block resamples against a fixed shortlist of at most 30 candidates per horizon.

Other Models

Relationships, local network curvature and risk, price behavior, and path order provide context for the retrieval experiment.

These views share data. Multiscale state summarizes the same observations; it is not an independent vote.

Validate the Current Dataset

Window30 retained observations
Horizon
References3–6
Stride20 retained observations