DP Statistical Forecasting
DP Statistical Forecasting
DP Statistical Forecasting
Demand Planning
Statistical Toolbox
Univariate Forecasting
– Moving Average
– Simple Linear Regression
– Exponential Smoothing
– Holt-Winters
– Croston’s Model (for sporadic demand)
Causal Analysis
– Multiple Linear Regression
Composite Forecasting
– Weighted Averaging of Multiple Models
2 5/28/2018
SAP APO Demand Planning
Model parameters
Forecast strategy,
Strategy, seasonal length,
Periods per season,
smoothing parameters
Parameters: a, b, g, s
Control parameters
Without Leading Zeros,
Outlier correction, adjustment Outliers,
of corrected history,
workdays correction Days in Period
4 5/28/2018
SAP APO Demand Planning
5 5/28/2018
SAP APO Demand Planning
History
500
400
Units
300
200
100
0
Y-4 Y-3 Y-2 Y-1 Y+1
Time Now
6 5/28/2018
SAP APO Demand Planning
History Trend
500
400
Units
200
100
0
Y-4 Y-3 Y-2 Y-1 Y+1
Now
7 5/28/2018
SAP APO Demand Planning
Model Seasonality
400
Units
300
200
100
0
Y-4 Y-3 Y-2 Y-1 Y+1
Now
8 5/28/2018
SAP APO Demand Planning
400
Units
300
200
100
0
Y-4 Y-3 Y-2 Y-1 Y+1
Time Now
9 5/28/2018
SAP APO Demand Planning
10 5/28/2018
SAP APO Demand Planning
11 5/28/2018
SAP APO Demand Planning
Ex post forecast
12 5/28/2018
SAP APO Demand Planning
13 5/28/2018
SAP APO Demand Planning
Past Future
14 5/28/2018
SAP APO Demand Planning
The most common values for alpha lie, between 0.1 and 0.5.
15 5/28/2018
SAP APO Demand Planning
16 5/28/2018
SAP APO Demand Planning
17 5/28/2018
SAP APO Demand Planning
18 5/28/2018
SAP APO Demand Planning
19 5/28/2018
SAP APO Demand Planning
20 5/28/2018
SAP APO Demand Planning
Outliers
5/28/2018
SAP APO Demand Planning
Smaller the sigma factor, Less the tolerance, greater the control
22 5/28/2018
SAP APO Demand Planning
values
23 5/28/2018
SAP APO Demand Planning
24 5/28/2018
SAP APO Demand Planning
25 5/28/2018
SAP APO Demand Planning
26 5/28/2018
SAP APO Demand Planning
27 5/28/2018
SAP APO Demand Planning
28 5/28/2018
SAP APO Demand Planning
Moving Average –
– Assumption : Data varies 12
Series 3 point MA 5 point MA
Volume
Weighted Moving Average –
– Assumption : Data varies 10
around a constant value and
shows no seasonality and
trend
9
Jan Apr Jul Oct Jan Apr Jul Oct Jan Apr Jul Oct
– Every historical value is
History Future
weighted with a factor
29 5/28/2018
SAP APO Demand Planning
Volume
2
30 5/28/2018
SAP APO Demand Planning
Manual Forecast –
– Assumption – Not interested in system to propose basic & trend values
– Define Basic, trend value yourself.
Croston Method
– Assumption : Demand Occurs every X period
31 5/28/2018
SAP APO Demand Planning
Auto Model I
– Assumption : Data has visible trend & seasonal pattern, 1st order
exponential smoothing required
– System checks intermittent pattern in historical data – If data is not there
for more than 66% of total period, Propose Croston Model.
– System checks seasonal effect by determining Auto co-relation
– System checks trend by trend significance test
– If any of these checks are not valid, results in no forecast
Auto Model II
– Assumption : Data has visible trend & seasonal pattern, 1st order / 2nd
order exponential smoothing required
– System checks intermittent pattern in historical data – If data is not there
for more than 66% of total period, Propose Croston Model.
– System checks white noise, if it finds, Propose Constant model.
– Checks for Constant / Trend / Seasonal / Seasonal trend / Seasonal
Linear Regression starting from alpha / beta / gamma equal to 0.1
32 5/28/2018
SAP APO Demand Planning
33 5/28/2018
SAP APO Demand Planning
34 5/28/2018
SAP APO Demand Planning
– Step 3 –
• Every historical value is divided
by the corresponding average
seasonal index
• This results in historical data
corrected by seasonality
– Step 4 –
• Linear regression is carried out
for the corrected historical data
• The linear regression forecast is
multiplied by the seasonal index
35 5/28/2018
SAP APO Demand Planning
Croston Method -
36 5/28/2018
SAP APO Demand Planning
37 5/28/2018
SAP APO Demand Planning
38 5/28/2018
SAP APO Demand Planning
39 5/28/2018
SAP APO Demand Planning
40 5/28/2018
SAP APO Demand Planning
41 5/28/2018
SAP APO Demand Planning
42 5/28/2018
SAP APO Demand Planning
43 5/28/2018
SAP APO Demand Planning
Forecast Errors
Error Total
– Used primarily as a measure of systematic error
– Bias: Measure of error that can create large cumulative error
44 5/28/2018
SAP APO Demand Planning
45 5/28/2018
SAP APO Demand Planning
From all the available methods for forecast errors most common is:
– Mean Absolute Percent Error (MAPE)
Reason -
– It’s easy to Understand
– It’s relatively easy to calculate and correlate with the business results
– All errors weighted equally
46 5/28/2018
SAP APO Demand Planning
Forecast Bias
Definition-
– Variance of historical sales volume over the forecasted sales volume as a
positive or negative percentage.
– Positive is oversell or under-forecasted &
– Negative is undersell or over-forecasting
Develop Custom Reports for generating forecast bias, This is a good method
to keep track of forecast Vs. current sales.
– In APO there is no default calculation for forecast bias.
47 5/28/2018
SAP APO Demand Planning
???
48 5/28/2018