You are on page 1of 18

Forecasting in Supply Chain

Management
3 Important Roles Of
Forecasting
 Pivotal in Strategic Business
Planning

Expansion planning
budgeting
Financial planning
Risk Assessment
Profit Margins
 Initiating all push–processes:

 Raw material planning


 Purchasing
 Inbound logistics
 Manufacturing
 Driving all pull–processes:
Order Management
Packaging
Distribution

Better forecast improves the


distribution and logistics and increases
customer service levels. 
Demand Forecasting

Demand forecasting in the supply chain is a process Demand Forecasting facilitates critical business activities like
used by organizations to determine potential future budgeting, financial planning, sales and marketing plans, raw
material planning, production planning
requirements of customers.
Why Demand
Forecasting?
 In the supply chain, forecasting can
help to deal with the 'bullwhip effect'
caused by the distorted flows of
information up and down the supply
chain. Excessive inventory quantities,
poor customer service, cash flow
problems, stock outs, high material
costs
 Bullwhip Effect:
The bullwhip effect is a supply chain
phenomenon describing how small
fluctuations in demand at the retail level
can cause progressively larger fluctuations
in demand at the wholesale, distributor,
manufacturer and raw material supplier
levels
Characteristics of Forecasts:

FORECAST LONG TERM AGGREGATE FARTHER A


ERRORS/DEMAND FORECASTS ARE FORECASTS ARE SUPPLY CHAIN
UNCERTAINTY. LESS ACCURATE USUALLY MORE FROM THE
THAN SHORT- ACCURATE THAN CONSUMER, THE
TERM DISAGGREGATE GREATER THE
FORECASTS. FORECASTS. DISTORTION OF
INFORMATION IT
RECEIVES
(COLLABORATIVE
FORECASTING).
 Relationship between Few Factors and Demand.

 Human Input.

 Information about Market Conditions.

 Past Demand. Components of


Forecast:
 Price Discounts.

 State of the Economy.

 Advertising/Marketing Efforts.
Forecasting Methods:

 Forecasting methods are classified according to the following four types:

1. Qualitative
2. Time series
3. Causal
4. Simulation
Qualitative:
 Primarily subjective and rely on human judgment.
 Used when little historical data is available.
 Forecasts demand several years into the future in new industries.

Time Series:
 Uses historical demand to make a forecast.
 Assumption of ‘Past demand history is a good indicator for future demand’.
Forecasting  Best fit when Variance in demand pattern is very less in years.

Methods: Causal:
 Correlation between demand & environmental factors (Economy, Interest Rate).
 Impact of price promotions on demand.

Simulation:
 Imitate the consumer choices that give rise to demand to arrive at a forecast.
 combine time-series and causal method.
 Impact of Price Promotion?
 Impact of competitor opening a store Nearby?
Basic approach to forecasting
Intergrade demand planning Identify major factors that
Understand the objective of
& forecasting throughout influence the demand
forecasting
the supply chain forecast

Forecast at the appropriate Establish performance &


level of aggregation error measure for forecast
Forecasting Method Applicability

Moving Average No trend or seasonality

Simple Exponential Smoothing No trend or seasonality

Holt’s Model trend but no seasonality

Winter’s Model trend & seasonality

Time series forecasting method


Application of Time Series

Weather forecast

Health Care

Engineering

Environmental studies
Not usable for all situation

Data analyst should know the


Uses of Time limitations
Series

It shows how data changes over


time
 Time Horizon
Time maters
Easy to forecast shorter time with fewer variables
Variable predicting increase with horizon
Forecasting Short term data can create short term forecast

Considerations  Dynamic & Static States


Depends on when to use
Static are stoned once it is made
Dynamic can be updated constantly with new information
Data Quality

 Data should be as per the standard required


 Make sure data is complete,
 is not duplicated or redundant,
 was collected in a timely and consistent manner,
 is in a standard and valid format,
 is accurate for what it is measuring,
 and is uniform across sets.
Thank You

You might also like