blockTrendBasedForecast

Trend-based forecast for an exponentially growing quantity

Extends from Interfaces.PartialConverters.InformationProcessing_SO (Information Processing Block).

Information

This information is part of the Business Simulation Library (BSL). Please support this work and ► donate.

The trend-based forecast makes use of a perceived present condition and a fractional growth rate computed by a →Trend block that follows the model proposed by Sterman [3, pp. 34 - 38].

The perceived present condition (PPC) will be "brought forward" to the actual time using linear extrapolation:

Extrapolated Present Condition = Perceived Present Condition · ( 1 + fractional growth rate · time to perceive present condition)

The actual forecast is then arrived at by using exponential growth and continuous compounding:

forecast = extrapolated present condition · EXP( fractional growth rate · forecast horizon)

See also

Trend

Parameters

TypeNameDefaultDescription
Units.RateinitialTrend0Initial trend (fracGrowthRate.initialTrend)
Timefcsth1Forecast horizon
Timetppc1Averaging time for perception of current quantity (i.e., the present condition)
Timethrc1Time horizon for reference condition
Timetpt1Time to perceive the trend (i.e., there is gradual adaptation to a new trend)
Structural Parameters
BooleansmoothTrendfalse= true, if the calculated trend is to be smoothed (fracGrowthRate.smoothTrend)

Connectors

TypeNameDefaultDescription
Interfaces.Connectors.RealInputuCurrent value as basis for trend formulation

Components

TypeNameDefaultDescription
RealOutputy (from InformationProcessing_SO)Information output signal