CH.8 FORECASTING & DEMAND PLANNING

MEAN ABSOLUTE DEVIATION

(MAD) -ERROR MEASURES -AVERAGE OF THE SUM OF THE ABSOLUTE ERRORS

MEAN SQUARE ERROR

(MSE) -ERROR MEASURE -AVERAGE OF THE SQUARED ERROR large errors are magnified, giving them greater penalty. This can be a useful error measure in environments where large errors are particularly destructive

STRENGTHS OF QUANTITATIVE FORECASTING

-CAN CONSIDER MANY VARIABLES AND COMPLEX RELATIONSHIPS -OBJECTIVE -CONSISTENT -CAN PROCESS LARGE AMTS OF INFO

WEAKNESSES OF QUALITATIVE FORECASTING

-CANNOT CONSIDER MANY VARIABLES -INFLUENCED BY SHORT-TERM MEMORY -DIFFICULTY IN UNDERSTANDING RELATIONSHIPS -BIASED (OPTIMISM, WISHFUL THINKING, POLITICAL MANIPULATION, LACK OF CONSISTENCY)

TYPES OF FORECASTING

-CRIME FORECASTING -CLIMATE CHANGE -HEALTH FORECASTING -POLITICAL FORECASTING -FORECASTING DECISION IN CONFLICTS -TOURISM FORECASTING

STRENGTHS OF QUALITATIVE FORECASTING

-HIGHLY RESPONSIVE TO LATEST CHANGES IN ENVIRONMENT -CAN INCLUDE INSIDE AND SOFT INFO DIFFICULT TO QUANTIFY -CAN COMPENSATE FOR ONE TIME OR UNUSUAL EVENTS -PROVIDE USER W/A SENSE OF OWNERSHIP

QUALITATIVE FORECASTING METHOD

-JUDGEMENTAL, SUBJECTIVE, BASED ON OPINIONS -made by people, subject to bias=managers, sales staff or customers "intention surveys"=asking customers if they would buy a particular product "sales force composite"=sales staff make a group forecast about upcoming sales

WEAKNESSES OF QUANTITATIVE FORECASTING

-ONLY AS GOOD AS THE DATA AND MODEL -SLOW TO REACT TO CHANGING ENVIRONMENTS -COSTLY AND TIME CONSUMING TO MODEL SOFT INFO -REQUIRE TECHNICAL UNDERSTANDING

FORECASTING IMPACT ON THE ORGANIZATION:

-PLANS AT ALL LEVELS ARE MADE BASED ON FORECASTING, DRIVES DECISIONS OF EVERY ORGANIZATION FUNCTION -MARKETING:develop estimates of demand and future sales, Marketing forecasts size of markets, new competition, future trends, emerging markets, and changes in consumer preference. -Financing, in turn, uses forecasting to assess financial performance, capital investment needs, and set budgets. -Operations makes decisions regarding production and inventory levels, conducts capacity planning and scheduling. -Sourcing uses forecasts to make purchasing decisions and select suppliers.

EXECUTIVE OPINION

-QUALITATIVE FORECASTING METHOD -GROUP OF MANAGERS, EXECS, OR SALES STAFF MEET AND COLLECTIVELY DEVELOP A FORECAST -often used to forecast sales, market trends, make strategic forecasts, forecast new products -can be used to modify existing forecasts due recession or special promo -ADVANTAGE=ability to include latest info -DISADVANTAGE=subject to human biases, and bc its a group decision one opinion may dominate

DELPHI METHOD

-QUALITATIVE FORECASTING METHOD -reach consensus among group of experts on a particular topic -propagation of a disease, climate changes, or tech innovation -Questionnaires are sent to experts, the findings summarized, and the process repeated, until consensus is reached. -time consuming, but excellent to forecast long range demand, technological change, and scientific advances in medicine

MARKET RESEARCH

-QUALITATIVE FORECASTING METHOD -uses surveys and interviews to determine customer likes, dislikes, and preferences, and to identify new product ideas

CASUAL MODELS

-QUANTITATIVE FORECASTING METHOD -based on modeling relationships between variables -Variable being forecast is related to other variables in the environment. EX=university enrollment may be related to unemployment rates, recession levels, or salary levels.

TIME SERIES MODELS

-QUANTITATIVE FORECASTING METHOD -generate forecasts from an analysis of time series of the data (data over time taken at regular intervals). Example is student enrollment per semester over the past five years.

TIME SERIES FORECASTING MODEL: EXPONENTIAL SMOOTHING

-SPECIAL WEIGHTED AVERAGE PROCEDURE TO OBTAIN FORECAST -EASY TO USE & UNDERSTAND, GOOD FORECAST RESULTS 3 ITEMS NEEDED: 1.CURRENT PERIOD'S FORECAST 2.CURRENT PERIOD'S ACTUAL VALUE 3.VALUE OF A SMOOTHING COEFFICIENT, a, WHICH VARIES BETWEEN 0 AND 1 -NAIVE METHOD=USES LAST PERIODS ACTUAL VALUE TO GENERATE FORECAST

TIME SERIES FORECASTING MODEL: TREND ADJUSTED EXPONENTIAL SMOOTHING

-USES BASIC EXPONENTIAL SMOOTHING EQUATION AND ADDS TREND COMPONENT TO COMPENSATE FOR ADDITIONAL PATTERN

TIME SERIES FORECASTING MODEL: simple & weighted moving average

-averaging a specified number, n, of the most recent data rather than the entire data set. -As new data become available, the oldest are dropped, and the number of observations used to compute the average is kept constant. -simple moving average "moves" through time. -Like the mean, this model is only appropriate for level data patterns. -advantage of being responsive by averaging only the most recent observations. WEIGHTED=computation is the same as the simple moving average, except more or less weight to certain data points (simple all data are weighted equally 1/n)

FORECASTING IMPACT ON SCM:

-forecast of demand is critical to the entire supply chain, as it affects the plans made by each company in the chain. -collaboration between suppliers and manufacturers in generating the forecast, all entities are responding to the same level of demand. -Independent forecasting by members of the supply chain gives rise to the bullwhip effect (volatility in orders as they propagate through the supply chain).

QUANTITATIVE FORECASTING METHOD

-objective, consistent, based on mathematical concepts -capable of handling large amounts of data, can uncover complex relationships -more accurate than qualitative methods if provided good data

SALES & OPERATIONS PLANNING (S&OP)

-organizational process intended to match supply and demand through functional collaboration -requires teamwork among sales, distribution, and logistics, operations, finance, and product development -enables firms to provide better customer service, lower inventory, reduced customer lead times, and stabilize production schedules -process is designed to coordinate activities between marketing and sales, with those of operations and sourcing, to ensure that supply meets demand requirements.

TIME SERIES FORECASTING MODEL: THE MEAN

-simplest forecasting model, average of all data -only appropriate for a level data pattern -reasonable for stable and mature products -as more data is collected over time, forecast become more stable

ACQUIRING NEW RESOURCES(planning decision)

-takes time to acquire new facilities, new tech, and new equipment -Plans must be made well in advance, and procedures to acquire new resources and capabilities put in place well ahead of time.

SCHEDULING EXISTING RESOURCES(planning decision)

-to be competitive, it must use its current resources in the most efficient way possible. -This includes the production process, transportation, labor, facilities, and capital.

PREDICTIVE ANALYTICS

-uses statistics, modeling, and data mining to analyze current and historical facts to make predictions about the future

DETERMINING FUTURE RESOURCE NEEDS(planning decision)

-what resources are needed in the future -depend on forecasts of emerging market opportunities, new technology, new products, and competition

FACTORS IN METHOD SELECTION (4):

1. Amount and type of available data: Different forecasting methods require different types and quantities of data. 2. Degree of accuracy required: The costs of the forecasting method need to justify the importance of the forecast. 3. Length of the forecast horizon: Some forecasting methods are better suited for short term forecasts whereas others are better suited for long term. 4. Patterns in the data: It is critical to select a forecasting model that is appropriate for the identified patterns in the data.

5 STEP PROCESS FOR S&OP:

1. Generate quantitative sales forecasts. 2. marketing adjusts the forecast based on introduction of new products or elimination of old products. 3. Operations checks forecasts against existing capability. And resources such as inventory, production capacity, scheduling, and labor for meeting demand. 4. Marketing, operations, and finance jointly review forecast and resource issues. Attempts are made to solve capacity issues and balance supply and demand. The forecast is converted into dollars to see if it meets the financial plan of the organization. 5. Executives meet to finalize forecast and capacity decision. Executives meet and reach agreement to convert it into the operating plan for the organization.

TYPES OF TIME SERIES FORECASTING MODELS (6):

1. THE MEAN 2.SIMPLE MOVING AVERAGE 3. WEIGHTED MOVING AVERAGE 4.EXPONENTIAL SMOOTHING 5.TREND ADJUSTED EXPONENTIAL SMOOTHING 6. SEASONALITY ADJUSTMENT

2 TYPES OF QUANTITATIVE FORECASTING METHODS

1. TIME SERIES MODELS 2. CASUAL MODELS

VICS 5-STEP PROCESS FOR CPFR

1.CREATE JOINT OBJECTIVES 2.DEVELOP A BUSINESS PLAN 3.CREATE A JOINT FORECAST 4.AGREE ON REPLENISHMENT STRATEGIES 5.AGREE ON TECHNOLOGY PARTNER TO BRING CPFR TO FRUITION

STEPS IN FORECASTING(5):

1.DECIDE WHAT TO FORECAST 2.ANALYZE APPROPRIATE DATA 3.SELECT FORECASTING MODEL 4.GENERATE THE FORECAST 5.MONITOR FORECAST ACCURACY

QUALITATIVE FORECASTING METHODS(3):

1.EXECUTIVE OPINION 2.MARKET RESEARCH 3.DELPHI METHOD

PRINCIPLES OF FORECAST

1.FORECASTS ARE RARELY PERFECT:too many factors in business environment to predict a perfect forecast, involves uncertainty, forecasters know they have to live w/a certain amt of error (diff between forecast and what actually happened)-maintain overall good forecast accuracy 2.FORECASTS ARE MORE ACCURATE FOR GROUPS THAN INDIVIDUAL ITEMS:Higher degree of accuracy can be obtained when forecasting for a group than for individual items , their individual high and low items cancel each other out. 3.FORECASTS ARE MORE ACCURATE FOR SHORTER THAN LONGER TIME HORIZONS:Shorter time horizons the lower the degree of uncertainty. As time horizon increases, so does a greater likelihood of changes. Data does not change much in the short run.

2 TYPES OF FORECASTING METHODS

1.QUALITATIVE 2.QUANTITATIVE

TIME SERIES FORECASTING MODEL:SEASONALITY ADJUSTMENT

Adjusting for seasonality simply involves computing the seasonal index—or percentage—and using it to adjust the forecast. This is detailed in the following steps: Step 1 Compute average demand for each "season." Total annual demand is divided by the number of "seasons" per year. For quarterly data the number of "seasons" would be 4, whereas for monthly data it would be 12. Step 2 Compute a seasonal index for each season. A seasonal index is obtained by dividing the actual demand for each season by the average demand for each year. An average seasonal index is then obtained by averaging across the number of years available. Step 3 Adjust the average forecast for next year by the seasonal index. Generate a forecast for next year using any of the methods we discussed, and calculate average demand per season. Use seasonal indexes to generate seasonally adjusted forecasts.

COLLABORATIVE PLANNING, FORECASTING, AND REPLENISHMENT (CPFR)

COLLABORATIVE PROCESS OF DEVELOPING JOINT FORECASTS AND PLANS W/SUPPLY CHAIN PARTNERS, RATHER THAN DOING THEM INDEPENDENTLY -Trading partners jointly set forecasts, plan production, replenish inventories, and evaluate their success in the marketplace. -RETAILERS AND SUPPLIERS JOINTLY ACHIEVE HIGHER SALES, DECREASED INVENTORY, AND IMPROVED STOCK LEVELS, WHILE LOWERING LOGISTICS COST

FORECAST ERROR

DIFFERENCE BETWEEN ACTUAL DEMAND AND THE FORECAST FOR A GIVEN PERIOD 2 COMMONLY USED ERROR MEASURES: 1. MEAN ABSOLUTE DEVIATION (MAD) 2. MEAN SQUARE ERROR (MSE)

QUANTITATIVE: CASUAL MODEL FORECASTING: MULTIPLE REGRESSION

It extends linear regression by looking at a relationship between the independent variable and multiple dependent variables. For example, the dependent variable might be university student enrollment per semester and the independent variables might be unemployment rate and per capita income.

QUANTITATIVE: CASUAL MODEL FORECASTING: LINEAR REGRESSION

LINEAR REGRESSION It is a forecasting model that assumes a linear or straight line relationship between two variables. The variable being forecast, called the dependent variable, is linearly related to another variable, called the independent variable. For example, if we assume that a person's weight is related and height are linearly related, we can use the model to forecast weight based on a person's height.

MEASURING FORECAST ACCURACY

Measuring forecast accuracy tells us how our forecasting methods are performing and enables us to improve performance over time. The first step in measuring forecast accuracy is to measure the forecast error.

STEP 1: DECIDE WHAT TO FORECAST

Remember forecasts are made in order to help plan for the future. We have to decide what forecasts are actually needed to guide the plan.

STEP 2: ANALYZE APPROPRIATE DATA

analyzing data and identifying patterns: -level or horizontal=simplest patter and easiest to predict, common for commodity products in the mature stage of life cycle, i.e table salt -trend=increasing or decreasing pattern over time, simplest type of a trend is a straight line, or linear trend, other form are exponential trend -seasonality=pattern that regularly repeats itself, ice cream in summer or snow shovels in winter -cycles=created by economic fluctuations, not predictable or repeating, MOST DIFFICULT TO PREDICT

STEP 5: MONITOR FORECAST ACCURACY

evaluate forecast performance by measuring error -information should be used to improve forecasting process -forecasting is ongoing process

STEP 4: GENERATE THE FORECAST

once a model is selected, forecast is generated

STEP 3: SELECT THE FORECASTING MODEL

once data patterns are identified, select an appropriate forecasting model -important to select forecasting model best suited for pattern -narrow down to 2 or 3 models and test w/historical data for accuracy

DEMAND MANAGEMENT

process of attempting to influence demand through promotional campaigns/ads, sales incentives, and cost cutting

FORECASTING

process of predicting future events, forecasting product demand -any time we try to predict future events its forecasting -forecast drives the plan -IMPORTANT AS IT DRIVES ALL OTHER BUSINESS DECISIONS -Decisions such as which markets to pursue, which products to produce, how much inventory to carry, and how many people to hire are all based on forecasts. -consequences can be costly in terms of lost sales or excess inventory that cannot be sold

PLANNING

process of selecting actions in anticipation of the forecast -response to forecast -INVOLVES 3 DECISIONS: 1.scheduling existing resources 2.determining future resource needs 3.acquiring new resources