Research method
Pattern recognition
Pattern recognition is a canonical archive-taxonomy method; this registry entry defines its inputs, output and use boundary.
- Output
- Conditional forecast or research filter
- Input
- Ordered price, volume or breadth observations
- Horizon
- A defined sampling interval and lookback
- Best use
- Compare an explicit quantitative baseline with an out-of-sample result.
- Input: Ordered price, volume or breadth observations.
- Output: forecast.
- Use boundary: Compare an explicit quantitative baseline with an out-of-sample result.
The graph3
How the method is built, and where it has been read
Depends on
Often reviewed together
Mechanical trading system5 readings
Often reviewed together
Breakout confirmation5 readings
Often reviewed together
Rule-based entry6 readings
Read in the archive24 of 51 readings
1986Construct a decision procedure that revises itself1988Serial dependence, trade excursions, and belief revision1989Evaluating weekday close direction with a counted baseline1989Auditing price motifs against binomial chance1989Finish the volume checklist before scoring the breakout1989Constructing supervised forecasts on moving averages1990Evaluating five-day soybean open-to-close rules1991A signed hourly swing catalog as a next-session chi-square check1991Candlestick labels as stacked construction tests1992Constructing fractal templates from successive index changes1992Walk-forward evaluation of weekly price-change patterns1993RSI price pattern templates and open interest1994Constructing a dual-net day-ahead index direction forecast1994A clocked stochastic second crest with a window-high stop1995Filtered swing ledger for MW pattern construction1996Volatility-ratio, inside-day and narrow-range-4 entry construction1996Volatility contraction and narrow-range breakout rules1997A two-gate held-out test of hand-labeled pullback nets1998Sliding-window correlation for cup-and-handle construction1998Timed breakout rules after a nested-bar contraction1998Constructing rounded-bottom cups as testable entries1999Rounded bottom landmarks, invalidation, and breakout rules1999A surviving weekly gap still needs a confirmation-breakout2000Constructing rectangles for breakout hypotheses
This registry entry describes a research method. It is not investment advice and does not make a performance claim.