CH 12 - Demand Planning: Forecasting and Demand Management

statistical model forecasting

forecasting techniques transform numerical data into forecasts using one of the 4 methods 1. time series analysis 2. casual studies 3. stimulation models 4. artificial intelligence see table 12-2

delphi method

forecasts developed by asking a panel of experts to individually and repeatedly respond to a series of questions

root mean squared error (RMSE)

gives an approximation of the forecast error standard deviation

3. demand management

influencing either pattern or consistency of demand (when and how they order)

3. demand management

is a decision process where managers attempt to influence patterns of demand -usually involves the use of pricing and promotional activities -Demanding planning lets operations managers know what customers they should serve and at what levels of service *especially difficult when product have highly varying and uncertain demand patterns 1. influence the timing or quality of demand through pricing changes, promotions, or sales incentives 2. manage the timing of order fulfillment 3. substitute by encouraging customers to shift their orders from one product to another, or from one provider to another

big data

large amounts of data made available through sensors and interconnected systems

autocorrelation

the correlation of current demand values with past demand values *if values of demand at any given time are highly correlated with demand values from the recent past, then it's HIGHLY AUTOCORRELATED

components of demand

the demand patterns: these patterns suggest that some systematic forces are influencing data. forecaster's objective is to uncover and describe the processes generating these time series patterns

forecast error

the difference between a forecast and the actual demand unexplained component of demand bc it's random in nature. the straight line in each panel in 12.2 represents forecast and the curved represents actual demand, then the differences between the whole is the forecast error

trend

the general sloping tendency of demand, either upward or downward, in a linear or nonlinear fashion e.g. new products in the growth phase of the life cycle

forecast accuracy

the measurement of how closely the forecast alights with the observations over time every error, whether the forecast was too high or too low, reduces accuracy positive forecast- error indicates overly pessimistic --> sold more than forecasted negative forecast- value indicates overly optimistic forecast --> sold less

tracking signal

the ratio of a running total of forecast error to MAD that indicates when the pattern of forecast error is changing significantly essentially a comparison of forecast bias (sum of errors, rather than MFE) to forecast accuracy

judgement- based forecasting

- built upon the estimates and opinions of people, most often exports who have related sales or operational experience - seek to incorporate factors of demand that are difficult to capture in statistical models - useful when there is a lack of quantitative historical information (new products)

4. Document and apply the proposed technique to the data gathered for the appropriate business process

- entire set of assumptions and steps included in the forecasting process should be well understood by all people involved

designing a forecasting process

- forecasting process attempts to understand the various components of demand so that it can CONVERT DATA IMPUTS INTO RELIABLE PREDICTIONS of future events - primary goal of designing a forecasting process is to generate forecasts that are usable, timely, and accurate. follow the 5 steps: 1. Identify the users and decision-making processes that the forecast will support - time horizon - level of detail - accuracy vs cost - fit with existing business processes 2. Identify likely sources of the best data inputs 3. Selecting forecasting techniques that will most effectively transform data into timely accurate forecasts over the appropriate planning horizon 4. Document and apply the proposed technique to the data gathered for the appropriate business process 5. Monitor the performance of the forecasting process for continuous improvement

3. Select forecasting techniques that will most effectively transform data into timely accurate forecasts over the appropriate planning horizon

- in short-term planning for stable demand environments, forecasters can usually create suitable forecasts using only simple statistical models based on historical demand - in longer-term planning, it requires multiple inputs including judgements, historical data, leading indicator data

postponable product

a product designed so that it can be configured to its final form quickly and inexpensively once actual customer demand is known

mean absolute deviation (MAD)

the average size of forecast errors, irrespective of their directions. also called mEAN ABSOLUTE ERROR

weighted average equation

a forecasting model that assigns a different weight to each period's demand according to its importance

focused forecasting

a combination of common sense inputs from frontline personnel and a computer stimulation process

stable pattern

a consistent horizontal stream of demands e.g. shampoo, milk

regression analysis

a mathematical approach for fitting an equation to a set of data

collaborative planning, forecasting, and replenishment (CPFR)

a method by which supply chain partners periodically share forecasts, demand plans, and resource plans in order to reduce uncertainty and risk in meeting customer demand 1. market planning 2. demand and resource planning 3. execution 4. analysis

mean squared error (MSE)

a more sensitive measure of forecast errors that approximates the error variance

exponential smoothing

a moving average approach that applies exponentially decreasing weights to each demand that occurred farther back in time

shift or step change

a one-time change in demand usually due to some external influence on demand e.g. major product promotional campaign, or sudden economic shock

smoothing coefficient

a parameter indicating the weight given to the most recent demand

adaptive forecasting

a technique that automatically adjusts forecast model parameters in accordance with changes in the tracking signal

grassroots forecasting

a technique that seeks inputs from people who are in close contact with customers and products -major limitation is that "experts" may unconsciously base their forecasts on their more recent experiences, rather than their entire set of experiences

seasonal index

an adjusted factor applied to forecasts to account for seasonal changes or cycles in demand

mean percent error (MPE)

average error represented as a percentage of demand

simulation models

create representations of previous events to evaluate future outcomes

2. demand forecasting

decision PROCESS where in which managers predict future customer demand (how many units?) - process should be sophisticated enough to achieve acceptable levels of forecast accuracy, but simple enough so that steps involved are understood by users

2. Identify likely sources of the best data inputs

e.g. experts, corporate records, transactional data, data from internet, government, suppliers, sellers of sales and customer databases

5. Monitor the performance of the forecasting process for continuous improvement

forecasters should carefully track and study the accuracy of the forecasts and work with users to refine the forecasting process

moving average equation

forecasting model that computes a forecast as the average of demands over a number of immediate past periods

time series analysis models

forecasting models that compute forecasts using historical data arranged in the order of occurrence

1. Identify the users and decision-making processes that the forecast will support

forecasting process needs to be designed with following users' characteristics and needs in mind: - TIME HORIZON: forecasting process should suit the period of time over which the user's current actions will affect future business performance (LEAD TIME IS IMPORTANT) - LEVEL OF DETAIL: forecasts can be for product, product family, entire business/industry, location, country, worldwide - ACCURACY VS COST: greater forecast accuracy requires greater effort and greater forecast system sophistication. important to weigh the costs - FIT WITH EXISTING BUSINESS PROCESSES: FP must be integrated into other business processes

marketing research

forecasting technique that bases forecasts on the purchasing patterns and attitudes of the current or potential customers

historical analogy

forecasting technique that uses data and experience from similar products to forecast the demand for a new product e.g. when next gen electronics are introduced, managers use sales patterns for previous generations along with other info to predict the life cycle stages for the new products

executive judgement

forecasting techniques that use input from high-level, experienced managers

seasonality and cycles

regular demand patterns of repeating highs and lows e.g. restaurants with peaks for breakfast, lunch, din

causal studies

search for cause and effect relationships among variables (e.g. snow)

naive model

simple forecasting approach that assumes that recent history is a good predictor of the near future (stable demand pattern)

forecast bias

simple the average error

situational drivers of forecast accuracy

some demand forecasting situations create greater challenges than others. the following rules give an indiction of how situational characteristics tend to affect forecast accuracy: Rule 1: short term forecasts are usually more accurate than long term forecasts- as time forecasting increases, more and more potentially unknown factors can affect demand Rule 2: Forecasts of aggregated demand are usually more accurate than forecasts of demand at detailed levels Rule 3: Forecasts developed using multiple information sources are usually more accurate than forecasts developed from a single source

stimulation models

sophisticated mathematical programs that offer forecasters the ability to evaluate different business scenarios that might yield different demand outcomes helps forecasters understand how different variables and drivers of demand relate to one another

1. demand planning

the COMBINED PROCESS of FORECASTING and MANAGING CUSTOMER DEMANDS to create a planning PATTERN OF DEMAND- which meets the firms OPERATIONAL and FINANCIAL GOALS reduce variability- drives almost all other activities in operations management

mean absolute error

the MAD represented as a percentage of demand

time series analysis

uses historical data arranged in order of occurance