Supply Chain Chapter 2: Forecasting And Demand Planning

How to alleviate the Bullwhip Effect

1) Collaboration: Sharing info through the use of electronic data interchange (EDI), point of sale (POS) data, and web based systems can facilitate collaboration 2) Synchronizing the Supply Chain: Supply Chain participants coordinate planing and inventory management to minimize the need for reactionary corrections 3) Reducing Inventory: Through the use of just in time (JIT), vendor managed inventory (VMI) and quick response (QR)

Advantages of Jury of Executive Opinion (2)

1) Decisions are enriched by the experience of competent experts 2) Companies don't have to spend time and resources collecting data by survey

Advantages of Delphi Method (3)

1) Decisions are enriched by the the experience of competent experts 2) Decisions are not likely a product of groupthink 3) Very useful for new products

Disadvantages of Delphi Method (4)

1) Experts may introduce some bias 2) Companies must spend time & resources collecting data by survey 3) If external experts are used there is a risk of loss of confidential info. 4) The Delphi Method can be time-consuming and is best for long-term forecasting

Disadvantages of Jury of Executive Opinion (2)

1) Experts may introduce some bias 2) Experts may become biased by their colleagues or a strongly opinionated leader

Advantages of Customer Survey (3)

1) It is a direct method of assessing information from the primary sources. 2) Simple to administer and comprehend. 3) It does not introduce any bias or value judgment particularly in the census method if the questions are constructed carefully.

Advantages of Personal Insight (2)

1) It is the fastest and cheapest technique 2) Can provide a good forecast

Measurement of Forecast Errors

1) Mean Absolute Deviation (MAD) 2) Mean Absolute Percent Error (MAPE) 3) Mean Squared Error (MSE)

5 Types of Quantitative Forecasting Techniques

1) Naive 2) Simple Moving Average 3) Weighted Moving Average 4) Exponential Smoothing 5) Linear Trend

Advantages of Sales Force Estimation (2)

1) No additional cost to collect data because internal sales people are used 2) More reliable forecast as it is based on the opinions of salespersons in direct contact with the customer

Disadvantages of Sales Force Estimation (3)

1) Not ideal for long-term forecasting 2) Salespersons may introduce bias 3) Salespersons may not be aware of the economic environment

5 Qualitative Models

1) Person Insight 2) Jury of Executive Opinion 3) Delphi Method 4) Sales Force Estimation 5) Customer Survey

Disadvantages of Customer Survey (3)

1) Poorly formed questions may lead to unreliable information. 2)Customers do not always answer the questionnaire. 3) It is time consuming and costly to survey a large population.

2 Basic Forecasting Techniques

1) Qualitative 2) Quantitative

Benefits of CPFR

1) Reduce Bullwhip Effect (reduction of safety stocks) 2) Better customer service 3) Lower inventory costs 4) Improved quality 5) Reduced cycle time 6) Better production methods

Disadvantages of Personal Insight (2)

1) Relies on one person's judgement and opinions, but also on their prejudices and ignorance 2) Unreliability: someone who is familiar with the situation ofter provides a worse forecast than someone who knows nothing

Considerations about a Forecast (2)

1) They will be inaccurate but still useful 2) Is the basis for most "downstream: supply chain planning decisions

2 Models of Quantitative Forecasting

1) Time Series 2) Cause & Effect

4 Variations that data should be used to evaluate when creating Quantitative forecasts

1) Trend Variations 2) Random Variations 3) Seasonal Variations 4) Cyclical Variations

7 Fundamentals of Forecasting

1) Your forecast is most likely wrong 2) Simple forecast methodologies trump complex one. Complex ones may hide key assumptions 3) A correct forecast does not prove your forecast method is correct. (Could have been chance) 4) If you don't use the data regularly, trust is less when forecasting 5) All trends will eventually end 6) It's hard to eliminate bias, so most forecasts are biased 7) Tech is not the solution to better forecasting (tech isn't the answer, but it's a tool)

Cause and Effect Forecasting

2 Models can be used 1) Simple linear regression model-One DV 2) Multiple linear regression model-More than 1 DV Regression uses the historical relationship between an IV and a DV to predict the FV of the DV i.e. demand

Forecast Bias

A consistent deviation from the mean in one direction ∑ Forecast Error = ∑ Actual Demand - ∑ Forecast Demand If forecast error is not 0, theres is bias in the forecast If negative, actual demand was consistently less than the forecast If positive, actual demand was greater than forecast demand A forecast process with bias will eventually create significant problems in the supply chain if left unchecked. Good supply chain planners are aware of these biases. A best practice is to measure for forecast bias routinely and then make corrections accordingly.

Bullwhip Effect

A distribution channel phenomenon in which forecasts yield supply chain inefficiencies. Refers to increasing swings in inventory in response to shifts in customer demand as one moves further up the supply chain.

Qualitative Forecasting

Based on intuition and opinion Used when data are limited, unavailable, not currently relevant

Time Series Forecasting

Based on the assumption that the future is an extension of the past Most frequently used among all forecasting models Predicting the future by understanding the past

Forcasting

Business function that estimates future demand for products so that they can be purchased or manufactured in appropriate quantities in advance of need

Collaborative Planning, Forecasting, and Replenishment (CPFR)

Business practice that combines the intelligence of multiple trading partners who share their plans, forecasts, and delivery schedules with one another in an effort to ensure a smooth flow of goods and services across a supply chain The real value comes from the sharing of forecasts among firms, rather than firms relying on sophisticated algorithms and forecasting models to estimate demand

Good Forecasting...

Can benefit a company by facilitating more effective planning, which can lead to reduced inventories, reduced costs, reduced stockouts, and improved customer service

Forecast Error

Can measured in units or percentages Companies need to track the forecast against the actual demand Difference between actual demand and the forecast demand (Quantified as an absolute value or %)

Advantage of Linear Trend Forecasting

Can provide an accurate forecast into the future even if there is random variation

Error Measurement

Critical role in tracking forecasting accuracy, monitoring for exceptions, and benchmarking the forecasting process

Customer Survey

Customers are directly approached and asked to give their opinions about the particular product

Dependent Demand

Demand for an item that is directly related to other items or finished products, such as a component or material used in making a finished product

Independent Demand

Demand for an item that is unrelated to the demand for other items, such as finished product, a spare part, or a service part [Forecasted]

Forcast

Estimate of future demand

Disadvantage of Simple Moving Average

Fails to identify trends or seasonal effects Can create shortages when demand is increasing because it lags behind actual demand

Personal Insight

Forecast is based on the insight of the most experienced, most knowledgeable, or most senior person available

Linear Trend Forecasting

Imposing a best fit line across the demand data of an entire time series Used as the basis for forecasting FV's by extending the line past the existing data and out into the future while maintaining the slope of the line

Random Variations

Instability in the data caused by random occurrences Generally Short-term, can be caused by weather emergencies, natural disasters

Mean Squared Error (MSE)

Magnifies the errors by squaring each one before adding them up and dividing by the number of forecast periods MSE = ∑ (A-F) ² / n

Factors that Influence Demand

Market Changes Competitive Activity Pricing Change in Consumer preferences

Mean Absolute Percent Error (MAPE)

Measures the size of an error in percentage terms Easier for most people to understand forecast error and forecast accuracy in percentage terms rather than in actual units MAPE = ∑ ((|A - F|)/ A)) / n

Mean Absolute Deviation (MAD)

Measures the size of the forecast error in units MAD = ∑(|A - F|) / n

Goal of Forecasting and Demand Planning

Minimize forecast Error

Advantage of Weighted Moving Average

More accurate than a simple moving average if actual demand is increasing or decreasing

Advantage of Naive Forecasting

Mores well for mature products and is very easy to determine

Trend Variations

Movement of a variable over time ex) fashion products

Demand

Need for a particular product or component Can come from various sources such as a customer order, a forecast, the manufacturing of another product, etc.

Jury of Executive Opinion

People who know the most about the product and the marketplace would likely form a jury to discuss and determine the forecast panel conduits a series of forecasting meetings to discuss the forecast until the panel reaches a consensus agreement

Demand Planning

Process of combining statistical forecasting techniques and judgement to construct demand estimate for P/S

Running Sum of Forecast Errors (RSFE)

Provides a measure of forecast bias RSFE indicated the tendency of a forecast to be consistently higher or lower than actual demand If positive, RSFE indicates that the forecasts were generally too low, underestimating demand; Stockouts are likely to occur If negative, RSFE indicates that the forecasts were generally too high, overestimating demand; excess inventory and higher carrying costs are likely to occur

Advantage of Simple Moving Average

Provides a very consistent demand over long periods of time and smooths out random variations

Seasonal Variations

Repeating pattern of demand from year to year, or over some other time interval ex) holiday shopping

Exponential Smoothing

Requires 3 Basic Elements: 1) Last Period's Forecast 2) Last Period's actual demand 3) Smoothing factor (0-1)

Disadvantage of Linear Trend Forecasting

Seasonal and cyclical variations are softened, making this method more useful for annual forecasts than for monthly forecasts

Naive Forecasting

Sets the demand for the next time period to be exactly the same as the demand in the lsat time period

Sales Force Estimation

Similar to Jury of Executive Opinion except that it is performed specifically with a group of sales people Individuals working in the sales function bring special expertise to forecasting because they maintain the closet contact with customers

Delphi Method

Similar to Jury of Executive Opinion, EXCEPT that the input of each of the participants is collected separately so that people are not influence by one another Done in several rounds until consensus forecast is achieved

Weighted Moving Average

Similar to a simple moving average except that not all historical time periods are valued equally

Tracking Signal

Simple indicator that forecast bias is present Determines if the forecast is within acceptable control limits and provides a warning when there are significant unexpected departures from the forecast RSFE/MAD

Simple Moving Average

Uses calculated average of historical demand during a specified number of the most recent time periods to generate the forecast ex) March 80,000 April 90,000 May 100,000 June 120,000 July 97,500 (120,000+100,000+90,000+80,000)/4=97,500

Quantitative Forecasting

Uses mathematical models and historical data to make forecasts

Cyclical Variations

Wavelike pattern that can extend over multiple years and therefore cannot be easily predicted ex) business cycles, GDP, market fluctuations

Advantage of Exponential Smoothing

Will create a forecast more responsive to trends than previous methods

Disadvantage of Weighted Moving Average

Will still lag behind actual demand to some degree Difficult to decide on the weight for each period

Disadvantage of Exponential Smoothing

Will still lag behind trends, especially upward trends since the smoothing factor would need to be greater than 1 to approach an accurate forecast

Disadvantage of Naive Forecasting

Works only for mature products. Any variations in demand will create inventory issues

Bad Forecasting...

can be the root cause for creating high inventories, high stockouts, high costs, and customer dissatisfaction