Module 3: Sources of Demand/Forecasting

Question 1

Business-to-business commerce (B2B)

Answer 1

-business conducted over internet between business

-implication is that this connectivitiy will cause businesses to transform themselves via supply chain management to become virtual orgs - reducing costs, improving quality, reducing delivery lead time and improving due-date performance

Question 2

Business-to-Consumer Sales (B2C)

Answer 2

-business being conducted between businesses and final consumers, largely over internet

-it includes traditional brick and mortar businesses that also offer products online and businesses that trade exclusively on the internet

Question 3

Distribution Channels

Answer 3

-the distribution route, from raw materials through consumption, along which products travel

Question 4

Transaction Channel

Answer 4

-a distribution network that deals with change of ownership of goods/services including the activities of negotiation, selling, and contracting

-addresses transfer of funds and ownership between selling org. and customer

Question 5

Direct/Internal Distribution Channel

Answer 5

-often used for transfers to other plants or business units or for B2B sales; demand could be for inventory or ETO/MTO goods

-B2C typically rely on network of distribution centers rather than directly shipping from the manufacturer; demand is directly from the customer

Question 6

Exclusive and Select Distribution Channel

Answer 6

-distributor is shown placing the orders

-distributor is a business that does not manufacture its own products but instead purchases and resells these products –> usually maintains a finished goods inventory

Question 7

Complex Distribution Channel

Answer 7

-demand is from an internally owned distribution center, which is likely directly connected to manufacturer’s master production schedule through a distribution requirements planning module

Question 8

Independent Demand

Answer 8

-demand for an item that is unrelated to the demand for other items

-demand for finished goods, parts required for destructive testing and service parts requirements are examples

-will be for items that org. sells as individual units

-comes from different internal/external sources:
1. forecasting
2. end customers (finished goods and service parts)
3. replenishment orders (come from downstream business customers such as distribution centers)
4. interplant demand or intercompany transfers (e.g. between subsidiaries)
5. internal use (e.g. R&D, quality control, marketing use)

Question 9

Dependent Demand

Answer 9

-demand that is directly related to or derived from the bill-of-material structure for other items or end products

-such demands are therefore calculated and need not and should not be forecast

-will be for materials used to make those units

-a given inventory item may have both dependent and independent demand at given time e.g. a part may simultaneously be the component of an assembly and sold as a service part

Question 10

Forecast

Answer 10

-estimate of future demand

-forecast can be constructed using quantitative methods, qualitative methods or combination of methods; can be based on extrinsic (external) or intrinsic (internal) factors

-various forecasting techniques attempt to predict one or more of the four components of demand: cyclical, random, seasonal, and trend

Question 11

Forecasting

Answer 11

-business function that attempts to predict sales and use of products so they can be purchased or manufactured in appropriate quantities in advance

Question 12

Demand Forecasting

Answer 12

-forecasting the demand for a particular good, component, or service

Question 13

Actual Demand

Answer 13

-actual demand is composed of customer orders (and often allocations of items, ingredients, or raw materials to production or distribution)

-actual demand nets against or consumes the forecast, depending upon rules chosen over a time horizon

-example: actual demand will totally replace forecast inside the sold-out customer order backlog horizon (or demand time fence) but will net against forecast outside this horizon based on chosen forecast consumption rule

Question 14

Forecast Horizon

Answer 14

-period of time into future for which forecast is prepared

-needs to be as long as required by process it supports

Question 15

Forecast Interval

Answer 15

-time unit for which forecasts are prepared, such as week, month or quarter

-weekly: necessary for master scheduling and can be achieve by dividing monthly product family forecasts into weekly buckets for individual products ; increases data management and can impart false sense of precision

monthly - not too detailed, but gives adequate level of precision; most common choice for forecasters (allows detection of seasonal patterns that are hidden in quarterly forecasts)

quarterly - more appropriate in ETO environments; may hide seasonal demand patterns

Question 16

Time Bucket

Answer 16

-number of days of data summarized into a columnar or row-wise display

example weekly time bucket contains all relevant data for an entire week; considered to be the largest possible (at least in near/medium term) to permit effective materials requirements planning

Question 17

Seasonality

Answer 17

-predictable repetitive pattern of demand measured within a year where demand grows and declines

-calendar-related patterns that can appear annually, quarterly, monthly, weekly, daily and/or hourly

-repeats over analysis period and can be isolated from other sources of variation and removed temporarily so that is won’t influence forecasting

Question 18

Trend

Answer 18

-general upward or downward movement of a variable over time; can also be flat

Question 19

Cycle

Answer 19

-usually refer to wavelike patterns observed in growth and recessions trends of economy over years

-unlike seasonality, economic cycles do not repeat over a predictable period of time -> this type of forecasting left to economists

Question 20

Random Variation

Answer 20

-any variation left over after seasonality and trends have been accounted for

-reflects that customers vary when, where, and in what quantities they buy products

-if random variation is small, forecasting will be fairly accurate; if large errors will be high

Question 21

Backorder

Answer 21

-unfilled customer order or commitment

-immediate (or past due) demand against and item whose inventory is insufficient to satisfy demand

Question 22

Mix Forecast

Answer 22

-forecast of proportion of products that will be sold within a given product family, or proportion of options offered within a product line

-product/option mix as well as aggregate product families must be forecasted

-even though appropriate level of units is forecasted for a given product line, an inaccurate mix forecast can create material shortages and inventory problems

Question 23

Qualitative Forecasting Techniques

Answer 23

-approach to forecasting that is based on intuitive or judgmental evaluation

-used generally when data is scarce, not available, or no longer relevant

Question 24

Quantitative Forecasting Techniques

Answer 24

-approach to forecasting where historical demand data is used to project future demand

-extrinsic and intrinsic techniques are typically used

Question 25

Historical Analogy

Answer 25

-technique based on identifying sales history that is anagolous to a present situation, such as the sales history of a similar products and using that past pattern to predict future sales

-type of qualitative forecasting method

Question 26

Panel Consensus

Answer 26

-judgmental forecasting technique by which a committee, sales force, group of experts arrives at a sales estimate

-tracking these adjustments separately from any quantitative component will help in determining whether the modifications are increasing or decreasing in accurary and in showing whether they are introducing bias by being consistently high or low

Question 27

Delphi Method

Answer 27

-qualitative forecasting technique where opinions of experts are combined in a series of iterations

-results of each iteration are used to develop the nxt, so that convergence of experts’ opinions is obtained

anonymity to prevent groupthink and stake in ground mentality

Question 28

Pyramid Forecasting

Answer 28

-qualitative forecasting technique that enables management to review and adjust forecasts made at an aggregate level and to keep lower-level forecasts in balance

Question 29

Extrinsic Forecasting Method

Answer 29

-also known as causal forecasting, associative correlation or explanatory forecasting

-best for long-term forecasting at aggregate level

-uses cause-and-effect associations to preduct and explain relationships - or correlation - between variables

-forecast method using correlated leading indicator

example: estimating furniture sales based on hoursing starts

-more useful for large aggregations, such as total company sales, than for individual product sales

-internal or external data sources

Question 30

Correlation

Answer 30

-relationship between 2 sets of data such that when one changes, the other is likely to make a corresponding change

-if changes are in same direction, there is positive correlation

-when changes tend to occur in opposite directions, there is a negative correlation

-where there is little correspondence or changes are random, there is no correlation

-macroeconomic observation

does not equal causation –> just because an effect be reliably observed over time does not mean one thing caused the other thing (could be some 3rd force affecting both variables)

Question 31

Regression Analysis

Answer 31

-statistical technique for determining best mathematical expression describing functional relationship between one response and one more independent variables

Question 32

Leading Indicators

Answer 32

-a specific business activity index that indicates future trends

example: housing starts is a leading indicator for the industry that supplies builders’ hardware

Question 33

Least-Squares Method

Answer 33

-method of curve fitting that selects a line of best fit through plot of data to minimize sum of squares of deviations of given points from the line

-used to make an association between the dependent variable y (thing you’re trying to predict) and independent variable x (the predict)

Question 34

Curve Fitting

Answer 34

-approach to forecasting based on a straight line, polynomial or other curve that describes some historical time series data

Question 35

Multiple Regression Model

Answer 35

-model involves more than one independent variable

Question 36

Life Cycle Analysis

Answer 36

-quantitative forecasting technique based on applying past patterns of demand data covering introduction, growth, maturity, saturation, and decline of similar products to a new product family

-comparative technique that analyzes and adapts existing data and patterns and extrapolates them to create a forecast based on historial information

Question 37

Seasonal Index

Answer 37

-number used to adjust data to seasonal demand

-provides info on how much seasonal period’s demand has varied from average demand in past, and index is therefore used to estimate how much seasonal demand will vary from average demand ina future seasonal period

Question 38

Base Series

Answer 38

-standard succession of values of demand-over-time data used in forecasting seasonal items

-average value of base series over a seasonal cycle is 1.0

Question 39

Moving Averages

Answer 39

-arithmetic average of a certain number (n) of most recent observations

-as each new observation is added, oldest observation is dropped

Question 40

Weighted Moving Average

Answer 40

-places weight on periods being averaged usually to put greater emphasis on more recent periods and relatively less on more distant periods

-divide sum of weight rather than number of periods

-drawback to moving averages is that to do forecasting you need to assemble data from multiple periods

Question 41

Exponential Moving Forecast

Answer 41

-type of weighted moving average forecasting technique in which past observations are geometrically discounted according to their age

-heaviest weight is assigned to the most recent data

-smoothing is termed exponential b/c data points are weighted in accordance with an exponential function of their age

technique maes use of a smoothing constant to apply to the difference between the most recent forecast and critical sales data, thus avoiding necessity of carrying historical sales data

-can be used for data that exhibits no trend or seasonal patterns

Question 42

Smoothing Forecast

Answer 42

-in exponential smoothing, weighting factor is applied to most recent demand, observation or error

-error is defined as difference between actual demand and forecast for most recent period

-range of alpha is 0.0 to 1

-smooths or random or irregular spikes or dips in actual demand by placing more weight on prior forecast

Question 43

Extrapolation

Answer 43

-estimation of future value of some data series based on past observations

example: statistical forecasting

Question 44

Mean

Answer 44

-arithmeitc average of group of values

Question 45

Median

Answer 45

-middle value in a set of measured values when items are arranged in order of magnitude

Question 46

Mode

Answer 46

-most common or frequent value in group of vales

Question 47

Normal Distribution

Answer 47

-particular statistical distribution where most of observations fall fairly close to one mean, and a deviation from mean is as likely to be a plus as it is to be minus

-when graphed, takes form of a bell-shaped curve

Question 48

Outlier

Answer 48

-data point that differs significantly from other data for a similar phenomenon

Question 49

Probability Distribution

Answer 49

-table of numbers or a mathematical expression that indicates frequency with which each of all possible results of an experiment should occur

Question 50

Sample

Answer 50

-portion of a universe of data chosen to estimate some characteristics about the whole universe

-could consist of customer orders, number of units of inventory, number of lines on purchase order

Question 51

Sampling Distribution

Answer 51

Distribution of values of a statistics calculated from samples of a given size

Question 52

Forecast Error

Answer 52

-difference between actual demand and forecast demand

-can be stated as an asbolute or a percentage

Question 53

Bias

Answer 53

-consistent deviation from mean in one direction (high or low)

-a normal property of a good forecast is that it is not biased

Question 54

Distribution of Forecast Errors

Answer 54

-tabulation of forecast errors according to frequency of occurence of each error value

-errors in forecasting are in many cases normally distributed even when observed data does not come from a normal distribution

Question 55

Mean Absolute Deviation

Answer 55

-average of absolute values of deviations of observed values from some expected value

-MAD can be calculated based on observations and arithmetic means of those observations

Question 56

Demand Filter

Answer 56

-standard set to monitor sales data for individual items in forecasting models

-usually set to be tripped when demand for a period differs from forecast by more than some number of mean absolute deviations

Question 57

Tracking Signal

Answer 57

-ratio of cumulative algebraic sum of deviations between forecasts and actual values to mean absolute deviation

-used to signal when validity of forecasting model might be in doubt

Question 58

Standard Deviation

Answer 58

-measurement of dispersion of data or of a variable

-computed by finding differences between average and actual observations, squaring each difference, adding squared differences, diving by n-1 (for a sample) and taking square root of result

measures difference between period actual demand average demand during a forecast horizon

-not a measure of forecast error

-measure of how far results tend to deviate from average result

Question 59

Forecast Management

Answer 59

-process of making, checking, correcting, and using forecasts

-includes determination of forecast horizon

Question 60

Focus Forecasting

Answer 60

-system that allows user to simulate effectiveness of numerous forecasting techniques, enabling selectionof most effective one

Question 61

Bullwhip Effect

Answer 61

-extreme change in supply position upstream in supply chain generated by small change in demand downstream in supply chain

-inventory can quickly move from being backordered to being excess

-caused by serial nature of communicating orders up the chain with inherent transportation delays of moving product down the chain

Question 62

Collaborative Planning, Forecasting, and Replenishment (CPFR)

Answer 62

-collaboration process whereby supply chain trading partners can jointly plan key supply chain activities from production and delivery of raw materials to production and delivery of finals products to end customers