Conditional market patterns
What it shows
The list of detected conditional patterns: “after a day meeting condition X, the next day was up in Y% of cases”. Each row shows the base rate, the conditional rate, the edge in percentage points, n, the 95% (Wilson) confidence interval and the quality badges. Only patterns that passed the significance threshold are published.
How to read it
Sorting by strength puts the best-documented patterns on top. Even a full set of badges only says the tendency WAS present in the data; it does not mean that it will repeat. A few percentage points of edge describe historical statistics, never a day “to buy” or “to sell”.
Parameters
- Edge (pp)
- The difference between the conditional and the base rate, in percentage points. Measures how much the condition historically shifted the frequency of up days.
- n (sample size)
- How many historical days back the group. A small n (the “low sample” badge) = a result too noisy to take seriously.
- Whiskers / 95% CI
- Whiskers are the 95% confidence interval of the mean: a realistic range for the true value. A narrow interval = a more confident reading.
- Positive reading: The whole interval on one side of zero: a clear tendency across the data window.
- Negative reading: Whiskers crossing zero: the interval contains 0, so it may just as well be noise.
- FDR-significant
- The green badge: the result passed the multiple-comparison correction (Benjamini–Hochberg). Without it, with ~30 tests per profile, a few “significant” results are pure chance.
- Walk-forward confirmed
- A pattern detected on the earlier part of the data kept its direction on the later, unseen part too: a stability-over-time test.
Example
“After a Friday down ≥1%, the next day was up in 58% of cases (base 51%, edge +7 pp, n=64, CI 46–69%): historically a bounce occurred more often than average, but the confidence interval shows how wide the uncertainty margin is.