EchoTimeExplainable time-series similarity for humans and agents.
Scientific report surface
similarityraw_series

BTC vs VIX: Pearson r 0.06, Spearman rho 0.09, Kendall tau 0.05. The weakest agreement appears in shape similarity and trend similarity, so timing or regime differences probably matter.

Start with familiar coefficients, then inspect the time-series radar and component bars. This page does not treat the internal aggregate score as the main verdict.

Pearson r0.06linear level match
Spearman rho0.09rank-order match
Mutual info0.12nonlinear dependence
Diff r-0.32local change match

Component mean 0.16 across 5 time-series-specific metrics.

Recommended next actions

  • Plot both series after z-score normalization to show the shared shape without scale differences.
  • Run rolling or windowed similarity if you expect the relationship to change over time.
  • Use structural-profile similarity when scales, frequencies, or observation modes differ too much for raw-shape comparison.
Use this as an interpretable comparison summary. If you need alignment paths or distance matrices, pair the result with a lower-level similarity library.
Similarity radarSimilarity radarRadar over the time-series metrics. Read it together with Pearson, Spearman, and mutual info.ShapeDTWTrendDerivativeSpectral
EchoTime series previewSeries previewBTCVIX
EchoTime similarity componentsSimilarity componentsComponent mean 0.16 across 5 time-series metrics.Spectral0.41DTW0.40Shape0.00Trend0.00Derivative0.00
Rolling component meanRolling component meanmean=0.19, min=0.12, max=0.32 across per-window metric means

Familiar statistics

MetricValue
Pearson r0.06
Spearman rho0.09
Mutual info0.12
Diff r-0.32
Kendall tau0.05
Best-lag r0.33

Notes and guardrails

  • Rhythms or periodic structure match more closely than exact levels, so cycle-aware comparisons may be more informative than raw overlays.
  • Dynamic-time-warping similarity is stronger than direct shape correlation, suggesting similar patterns with shifted timing.

Compact agent context

{
  "type": "similarity",
  "headline": "BTC vs VIX: Pearson r 0.06, Spearman rho 0.09, Kendall tau 0.05. The weakest agreement appears in shape similarity and trend similarity, so timing or regime differences probably matter.",
  "overall_similarity": 0.14204606516906731,
  "qualitative_label": "very low",
  "top_components": [
    {
      "name": "spectral_similarity",
      "score": 0.4126499855177079,
      "level": "moderate"
    },
    {
      "name": "dtw_similarity",
      "score": 0.4007428367070557,
      "level": "moderate"
    },
    {
      "name": "shape_similarity",
      "score": 0.0,
      "level": "very low"
    }
  ],
  "profile_similarity": null,
  "rolling_summary": null,
  "suggestions": [
    "Plot both series after z-score normalization to show the shared shape without scale differences.",
    "Run rolling or windowed similarity if you expect the relationship to change over time."
  ],
  "notes": [
    "Rhythms or periodic structure match more closely than exact levels, so cycle-aware comparisons may be more informative than raw overlays."
  ]
}