Skip to main content
Track Exponential smoothing
10 / 41
Search the archiveLibrary
Library

1991issue C081-2

Competing certainty rules from exponential-average conditions

A mechanical-trading-system can induce a buy-or-sell action from an exponential moving average, a direction reading, and the index price. A trend-gate, a certainty-factor, and a selection-bias-coefficient then decide whether that action may fire and how strongly it may speak among competing rules.

  • Under a trending-market classification, buy-or-sell rules can be induced from the joint state of an exponential moving average, a computed direction reading, and the current index price.
  • A generated rule is a named object with a certainty-factor, preconditions, facts to assert if selected, and coefficients used in rule selection.
  • One exponential-moving-average rule has a certainty-factor of 63, is only marginally confident on its own, and stays blocked until the system is already at least 65 confident the market is trending.
  • If selected, the rule writes a buy decision by combining a 100-strength buy fact with its certainty-factor, and a selection-bias-coefficient of zero lets it compete on even terms.
Entries in this reading3 entries
Current trackExponential smoothing183 readingsMechanical trading system322 readingsMoving average597 readings

Buy-or-sell action from joint indicator states

Under a trending-market classification, a mechanical-trading-system can induce buy-or-sell rules from the joint state of an exponential moving average, a computed direction reading, and the current index price. The induced action depends on each indicator's value today and yesterday and on the inequalities among those values.

A TradersWeek editorial reading is that construction here is rule assembly rather than a single overlay. Exponential-smoothing supplies the comparison level. The direction reading supplies the sign. A trend-gate supplies permission. The certainty-factor then decides how strongly the resulting action is allowed to speak when several rules compete.

The generated rule as a named object

A generated rule is specified as a named object with a certainty weight, a set of preconditions, facts to assert if selected, and coefficients used in rule selection.

A precondition must already be established before a rule is allowed to fire. After a selected rule fires, a resultant-fact is added to the working database. The certainty-factor stored on the rule scales how strongly its asserted decision is written into the working facts.

Preconditions on direction, price, and the average

One exponential-moving-average rule carries a certainty-factor of 63 and is treated as only marginally confident on its own, so other activated rules are expected to reinforce it.

The remaining preconditions are that today's direction reading is at least zero, yesterday's price is at or below yesterday's exponential moving average, and today's price is strictly above today's exponential moving average.

The moving-average is a lookback baseline computed from an ordered price series and used to test whether the current or prior price sits above or below that level. Exponential-smoothing is the sequential update that forms that comparison level by giving the latest observation more weight than older ones.

Resultant-facts after selection

If every precondition holds and the rule is selected, the system writes a buy decision and either starts or upgrades the buy attribute by combining a 100-strength buy fact with the rule's certainty-factor.

Even competition with similar rules

A selection-bias-coefficient of zero assigns no extra conceptual cost to the rule, so it competes on even terms with other rules that have similar certainty-factors.

A TradersWeek editorial reading is that even terms do not make this rule self-sufficient. Because it is only marginally confident on its own, the construction still expects other activated rules to reinforce the buy decision.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
10 of 41 in the Exponential smoothing track
19911-14 pp.Next on Exponential smoothingHybrid construction of a mechanical timing system from smoothed signalsA mechanical-trading-system can produce entry, exit, and no-trade outcomes from one inspectable procedure rather than from an unexplained score.
All readings on this track · 41 readings
  1. 1984Matching average age across price filters
  2. 1984Residual-impact construction of exponential smoothers
  3. 1988Constructing simple and exponential moving averages as specified filters
  4. 1989Evaluating smoothed free reserves and funds-discount spreads
  5. 1990Integer construction of moving averages and exponential smoothing
  6. 1990Constructing incremental moving average filters
  7. 1991Constructing a double-smoothed stochastic oscillator
  8. 1991Constructing an exponential average from a smoothing weight
  9. 1991Constructing a double-smoothed momentum oscillator family
  10. 1991Competing certainty rules from exponential-average conditions
  11. 1991Hybrid construction of a mechanical timing system from smoothed signals
  12. 1991Constructing an exponential smoother from a moving-average length
  13. 1991Equivalent relative-strength-index constructions from a ratio and from smoothed momentum
  14. 1991Constructing the true strength index from double-smoothed momentum
  15. 1991True strength index from signed, double-smoothed momentum
  16. 1992Constructing exponential averages from simple lookbacks
  17. 1992Constructing exponential averages by the smoothing constant, startup length and lag
  18. 1992Nested range smoothing and windowed high-low damping
  19. 1992A weekly equity stance from the discount-bill spread
  20. 1993Double-smoothed stochastics momentum index construction
  21. 1993Constructing the true strength index with double exponential smoothing
  22. 1994Polarized fractal efficiency with a shared exponential smoother
  23. 1994Five-interval exponential smoothing of ten-interval signed path-efficiency
  24. 1994Hand-ranked price-volume series with stacked smoothing and stochastic
  25. 1995Range expansion filter on multi-horizon averages
  26. 1995The exponential smoothing constant from averaging lag
  27. 1997Construct a nested-average rainbow band and oscillator
  28. 1998Filter stacks that combine a moving average with exponential smoothing
  29. 2002Smoothed relative-strength construction from wilder-averaging and a price prefilter
  30. 2003Reverse-engineered RSI price targets
  31. 2004Piecewise trend quality from moving-average reversals
  32. 2004Nested smoothing recipes versus unaudited oscillator experiments
  33. 2008Weight construction beyond the N-day label
  34. 2010A consensus filter for objective RSI and smoothing construction
  35. 2012Sentiment-zone oscillator from signed closes
  36. 2012Classic RSI one-over-N smoothing versus the standard exponential average
  37. 2013Why exponential smoothing uses two over n plus one
  38. 2015Constructing ratio indicators with moving-average and exponential-smoothing weights
  39. 2015Slow relative-strength index from an exponentially smoothed price
  40. 2017Rebuilding the relative strength index as open-scale buy-sell pressure
  41. 2017Comparing Wilder and exponential smoothing inside a relative-strength index
By fieldDecision process416 readingsBy year1991166 readings
All 183 readings tagged Exponential smoothing
Also on Exponential smoothing5 readings
1991Hybrid construction of a mechanical timing system from smoothed signals1992A weekly equity stance from the discount-bill spread1984Constructing TRIX from a cutoff to one shared alpha1984Matching average age across price filters1984Residual-impact construction of exponential smoothers