Scribd
Upload
1 views

OPC Module2.1.2

Opc

Uploaded by

Jayesh Borse
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
1 views

OPC Module2.1.2

Opc

Uploaded by

Jayesh Borse
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

Module 2

Forecasting

Prasad Bari
Forecasting

Exponential Smoothing Method


Simple ‘n’ period moving average gives equal weightage to the last ‘n’
periods. Exponential smoothing effect gives greater weightage to recent
data and lesser weightage to older data.

Also moving average forecasting is laborious operation of maintaining


the data for all the previous year, but exponential smoothing method
requires only the current demand and the forecasted demand for the
current month.
Forecasting
Let,
Ft = Forecast for the period t
Ft-1 = Forecasted demand for the last period
Dt-1 = Actual demand for the last period
∝ = Smoothing constant

Ft = ∝Dt -1 + (1-∝) Ft -1

Now, value of selected ∝ is small if the demand pattern is stable and large
value of ∝ is selected if the demand is fluctuating.
Forecasting
The demand for the disposable plastic tubing for a General Hospital is
300 units and 350 units for September and October respectively. Using
200 units as forecasted demand for September, compute the forecast for
the month of November. Assume ∝ = 0.7.

Solution:-
Ft = ∝Dt -1 + (1-∝) Ft -1
Dt-1 = Demand for September = 300
Ft-1 = Forecast for September = 200
Forecast for October = Ft = 0.7*300 + 0.3*200 = 270
Now, forecast for November
Ft =∝Dt -1 +(1-∝) Ft -1
0.7*350 + 0.3*270 = 326 units
Forecasting

Estimate the sales forecast for the year 2020 using exponential
smoothing forecast. Take ∝ = 0.5 and the forecast for the year 2015
as 160*105 units.

Year 2015 2016 2017 2018 2019


5
Sales (Rs.) (10 ) 180 168 159 170 188
Forecasting
Solution:-
Ft =∝Dt -1 +(1-∝) Ft -1
Year Sales Forecast
2015 180 160
2016 168 170
2017 159 169
2018 170 164
2019 188 167
2020 177.5
The forecast demand for the year 2020 is 177.5 units
Forecasting
Forecasting Error
It is the numerical difference between the forecasted demand and the
actual demand.
This error should be minimum.
Average forecast error is measured by mean absolute deviation (MAD)
without direction.

MAD = sum of absolute value of forecast error for all the periods
number of periods

MAD expresses the magnitude but not the direction of the error.
Forecasting
Forecasting BIAS
It measures the forecast error with regard to direction and tendency to
over forecast or under forecast.

BIAS = sum of forecast error for all the period


number of period

It indicates the directional tendency of forecast errors. If the forecast


repeatedly overestimates actual demand BIAS will have a positive value
and underestimation will be indicated by a negative value.
Forecasting
Forecasting

You might also like