2015issue C0544-48
From a drawn price shape to an event-cloud case study
A user can store a named, hand-drawn price shape, set how tightly later bars must match it, and only then view a subsequent-path cloud. This archive case study treats that cloud as a reading of past analog windows, not as a live prediction.
- A user can draw or adjust a price shape with connected points, name it, and store it in an event-library for later analog search.
- Pattern-match-sensitivity can be set to high, medium, or low so the search returns more loose matches or fewer closer matches.
- A pattern-quick-test slides the price series under the drawn shape so other segments can be judged before they are treated as analogs.
- The event-cloud is withheld unless the shape matches the series at least three times; one illustrated set summarized a cloud from the most recent 14 matching events.
A named shape becomes the search object
A user can draw or adjust a price shape with connected points, name that shape, and store it in an event-library for later analog search. The event-library is the saved collection of those named patterns.
The forecaster is the platform tool that stores the named pattern, finds analog events, and draws a subsequent-path cloud from those events. Pattern-recognition, in this workflow, means matching the user-drawn price shape against later bars in the same series.
Set how closely later bars must match
Pattern-match-sensitivity can be set to high, medium, or low. The setting controls how closely a later segment must resemble the drawn shape before it counts as an event. A looser setting returns more matches. A tighter setting returns fewer closer matches.
Check the fit before counting analogs
A pattern-quick-test lets the user slide the price series under the drawn shape to judge how well other segments fit. That visual check comes before those segments are treated as analogs and before a fuller analog search is run.
When an event-cloud is shown
Historical-analog-comparison collects prior windows that resemble the drawn shape and summarizes where price went after those windows. The event-cloud is the overlay of subsequent price paths from the matched events.
The platform withholds that cloud unless the drawn shape matches some part of the price series at least three times. One illustrated analog set summarized a cloud from the most recent 14 matching events.
How to read the case
Editorial reading: the event-cloud is a summary of paths that followed windows similar to the stored shape. It is a case study of those matched events, not a claim about the next move in the series.
All readings on this track · 19 readings
- 1988Crash fear fails the depression regime test
- 1990October 1987 cycle overlay and the loss-trap
- 1990Constructing nested four-year market cycles
- 1991Evaluating quarterly return runs with historical analogs
- 1992Evaluating split events across correction and bear regimes
- 1993Mining-bullion relative strength as a gold-sleeve regime
- 1994A two-horizon case study of a market-breadth oscillator
- 1994Extreme short-rate declines as equity regime context
- 1997Clustered true-range days as a regime label rather than a top forecast
- 2001Nearest-neighbor one-week forecast from log-price patterns
- 2001Constructing nearest-neighbor forecasts gated by a trend filter
- 2003Regime context for debt-era bear rallies
- 2004Testing a 1987 stock and gold analog by wave degree
- 2004Shifting calendar regimes and election-cycle analogs
- 2006Aligning sugar boom phases with seasonal analogs
- 2009Crowd consensus and failed targets as regime context
- 2011Treat a long-horizon chart analog as a regime scenario
- 2012Build a weekly analog as a dated forecast object
- 2015From a drawn price shape to an event-cloud case study