SCM 186: Chapter 4 Forecasting

factors in forecast method selection

• Amount and type of available data • Degree of accuracy required • Length of forecast horizon • Patterns in the data (Two types of methods - quantitative and qualitative)

7 steps in the forecasting system

1. Determine the use of the forecast 2. Select the items to be forecasted 3. Determine the time horizon of the forecast 4. Select the forecasting model(s) 5. Gather the data needed to make the forecast 6. Make the forecast 7. Validate and implement results

sale force composite

- Base on salespersons' estimates of expected sales - Each salesperson estimates what sales will be in his or her region - They are then combined at the district and national levels to reach an overall forecast

exponential smoothing

- Another weighted moving average forecasting method

trend projections

A time-series forecasting method that fits a trend line to a series of historical data points and then projects the line into the future for forecasts

jury of executive opinion

Uses the opinion of a small group of high-level managers to form a group estimate of demand

naive approach

- Assumes that demand in the next period is equal to demand in the most recent period - ex: If January sales were 68, then February sales will be 68 - Most cost effective and efficient objective forecasting model - May not be accurate, but can at least provide a good starting point

standard error of the estimate

- Gives a measure of the variability around the regression line

components of demand

- Average demand line is useless - Trend component tells us more info - Seasonal peaks occurs on actual demand line - x-axis: time in years - y-axis: demand for product or service

demand management

The process of influencing demand

random variations

- "Blips" in data caused by chance and unusual situations - Follow no discernible pattern, so they cannot be predicted - Random fluctuations - Short duration and non repeating

planning vs. forecasting

- *forecasting:* the process of predicting future events - *planning:* the process of selecting actions in anticipation of the forecast - planning involves scheduling existing resources, determining future resource needs, acquiring new resources - *Forecasting drives planning*

Sales and Operations Planning (S&OP)

- A collaborative process for generating forecasts that all functional areas agree upon Five-Step Process: 1. Generate quantitative sales forecast 2. Marketing adjusts the forecast 3. Operations checks forecast against existing capability 4. Marketing, operations, and finance jointly review forecast and resource issues 5. Executives finalize forecast and capacity decisions

seasonality

- A data pattern that repeats itself after a period of days, weeks, months, or quarters - Due to weather, customs, etc. --> Example: ice cream sales higher in summer months - Occurs within a single year - 6 common seasonality patterns

tracking signal

- A measurement of how well a forecast is predicting actual values - If the tracking signal is consistently negative, the forecasting technique consistently​ over-predicts - If the tracking signal is consistently positive, the forecasting technique consistently under-predicts

regression forecasting

- A set of "if, then" statements - Based on y = a + bx If... "we increase promotions" and/or "we decrease price" and/or "economic indicators favor us" ---> Sales will INCREASE If... "we decrease customer service" and/or "competition increases" and/or "economic indicators are bad" ---> Sales will DECREASE

economic forecasts

- Address the business cycle by predicting inflation rates, money supplies, housing starts, and other planning indicators - Help organizations prepare medium to long range forecasts

multiple-regression analysis

- An associative forecasting method with more than one independent variable

forecasting error in supply chain

- End use user needs 1,000 boots - If we keep ordering a safety amount of 10% each time, it creates an error that adds but to 46.4% - With information sharing and coordination: - The end use customer represents the *independent demand* - The retailer, wholesaler, manufacturer, and supplier represent *dependent demand* - Only one safety stock of 10% will be ordered so there will only be a 10% error - In segway example, the independent demand is the number of segways people buy, and the dependent demand is all the parts: tires, handles, LED taillight

collaborative, planning, forecasting, and replenishment (CPFR)

- Forecasting systems that combine the intelligence of multiple supply-chain partners - Goal is to create significantly more accurate information that can power the supply chain to greater sales and profits - Five step process: 1. Create joint objectives 2. Develop a business plan 3. Create a joint forecast 4. Agree on replenishment strategies 5. Agree on a technology partner to bring CPFR to fruition

long-range forecast

- Generally 3 years or more in time span - Used in planning for new products, capital expenditures, facility location or expansion, and research and development

medium-range forecast (intermediate)

- Generally spans from 3 months to 3 years - It is useful in sales planning, production planning and budgeting, cash budgeting, and analysis of various operating plans

selecting the smoothing constant

- High values of α are chosen when the underlying average is likely to change - Low values of α are used when the underlying average is fairly stable - When α reaches 1.0, the forecast becomes the same as the period's demand - If α is 0, the new forecast would just be equal to the previous period's forecast

questions answered by forecasting

- How much inventory is needed? - Do we need to schedule overtime? - Do we need to hire more people? - Do we need to build another factory?

qualitative forecasts

- Incorporate such factors as the decision maker's intuition, emotions, personal experiences, and value system in reaching a forecast - Based on subjective opinions - Often called judgmental methods

associative models

- Incorporate the variables or factors that might influence the quantity being forecast - Example: Lawn mower sales might use factors such as new housing starts, advertising budget, and competitors' prices

technological forecasts

- Long-term forecasts concerned with the rates of technological progress, which can result in the birth of exciting new products, requiring new plants and equipment

mean absolute deviation (MAD)

- Measure of the overall forecast error for a model - Computed by taking the sum of the absolute values of the individual forecast errors (deviations) and dividing by the number of periods of data

short-range vs. medium/long-range

- Medium/long-range *deal with more comprehensive issues* supporting management decisioning regarding planning and products, plants, and processes - Short-term forecasting usually *employs different methodologies* than longer-term forecasting - Short-range forecasts tend to be more accurate than longer-range forecasts

cycles

- Patterns in the data that occur every several years - Usually tied into the business cycle and are of major importance in short-term business analysis and planning - Also affected by political and economic factors - Multiple years duration - Causal or associative relationships

time-series models

- Predict on the assumption that the future is a function of the past - Look at what happened over a period of uses a series of past data to make a forecast - Future values are predicted ONLY from past values - Example: if we are predicting sales of lawn mowers, we use the past sales of lawn mowers to make the forecast

demand forecasts

- Projects of demand for a company's products or services - Demand-driven forecasts focus on rapidly identifying and tracking consumer desires - May use recent point of sale data, retailer and generated reports of consumer preferences

qualitative forecasting methods

- Qualitative methods are useful when identifying customer buying patterns, expectations, and estimating sales of new products 1. jury of executive opinion 2. delphi method 3. sales force composite 4. market survey

seasonal variations in data

- Regular movements in time series that relate to recurring events such as weather or holidays - May be applied to hourly, daily, weekly, monthly or other recurring patterns

least-squares method

- Results in a straight line that minimizes the sum of the squares of the vertical differences or deviations from the line to each of the actual observations

Multiplicative seasonal model

- Seasonal factors are multiplied by an estimate of average demand to produce a seasonal forecast 1. Find the historical demand each season by summing the demand for that month in each year and dividing by the number of years available 2. Compute the average demand over all months by dividing the total average annual demand by the number of seasons 3. Compute a seasonal index for each season by dividing that month's historical average demand by the average demand over all months 4. Estimate next year's total annual demand 5. Divide this estimate of total annual demand by the number of seasons, then multiply it by the seasonal index for each month. This provides the seasonal forecast

mean squared error (MSE)

- Second way of measuring overall forecast error - The average of the squared differences between the forecasted and observed values

market survey

- Solicits input from customers or potential customers regarding future purchasing plans - Can help in improving product design and planning for new products

forecasting

- The art and science of predicting future events - May involve taking historical data and projecting them into the future with a mathematical model - May be a subjective or intuitive prediction - May be based on demand-driven data - May be influenced by a product's position in its life cycle or demand for a related product

forecasting at Disney

- The forecast team at Disney reports the forecast of the attendance at the park and compares it to the actual attendance, and the error is usually close to zero - The forecasting team also provides daily, weekly, monthly, annual, and 5-year forecasts to the labor management, operations, finance, and park scheduling departments - Forecasters use judgmental models, econometric models, moving-average models and regression analysis - 20% of Walt Disney World's customers come from outside the U.S. so its economic includes GDP, cross-exchange rates, and arrivals into U.S. - Forecast not only attendance but also behavior at each ride - Disney even monitors 3,000 school districts inside and outside the U.S. for holiday/vacation schedules

trend

- The gradual upward or downward movement of data over time - Changes in income, population, age distribution, or cultural views - Typically several years duration

causal forecasting

- Tries to understand and identify the factors affecting or causing a result (for example, sales) • Linear regression models • Multiple regression models • Econometric models • Leading indicators - Some other variable is a leading indicator for the value you want to predict (the dependent variable value) - A good "sample" has many observations and potential "predictor" variables

short-range forecast

- Up to 1 year, generally less than 3 months - Used for planning purchasing, job scheduling, workforce levels, job assignments, production levels

quantitative forecasts

- Use a variety of mathematical models that rely on historical data and/or associative variables to forecast demand - Objective and consistent - Can handle large amount of data and uncover complex relationships

delphi method

- Uses a group process that allows experts to make forecasts - Three types of participants: decision makers, staff personnel, and respondents - Decision makers consists of a group of 5 to 10 experts who will be making the actual forecast - Staff personnel assistant decision makers by preparing, distributing, collecting, and summarizing a series of questionnaires and survey results - The respondents are a group of people, often located in different places, whose judgments are valued - This group provides inputs to the decision makers before the forecast is made

simple moving average

- Uses an average of the n most recent periods of data to forecast the next period - Example: a 4-month moving average is found by simply summing the demand during the past 4 months and dividing by 4 - With each passing month, the most recent month's data are added to the sum of the previous 3 months' data and the earliest month is dropped - Moving averages are useful if we can assume that market demands will stay fairly steady over time

weighted moving average

- Weights can be used to place more emphasis on recent values

supply chain management forecasting

- When a product goes on sale, Apple tracks demand by the hour for each store and adjusts production forecasts daily --> forecasts for supply chain are used as a strategic weapon - Toyota not only looks at forecasts for vehicles, but also for accessories such as navigation systems, wheels etc. - Toyota looks in detail at vehicle forecasts before it makes judgments about the future accessory demand - Walmart collaborare with its suppliers to make sure the right item is available during the right time, especially in times like hurricane seasons

capacity forecasting

- When capacity is inadequate, the resulting shortages can lead to loss of customers and market share - This happened to Nabisco and Nintendo when they the demand for their products exceeded their forecasts - On the other hand, when excess capacity exists, costs can skyrocket

forecasting chapter review

1. Forecasting is the process of attempting to predict future events. Planning is the process of selecting actions in anticipation of the forecast. 2. There are three principles of forecasting: (a) forecasts are rarely perfect; (b) forecasts are more accurate for aggregated items than for individual items; and (c) forecasts are more accurate for shorter than longer time horizons. 3. Data are composed of patterns and randomness. Four of the most common patterns are level, trend, seasonality, and cycle. 4. Forecasting methods can be divided into qualitative and quantitative. Qualitative methods are subjective and based on objectives. Quantitative methods are mathematically based, are objective and consistent. 5. Quantitative forecasting methods can be time series models and causal models. 6. A. Time series models generate the forecast by identifying and analyzing patterns in a "time series" of the data. 6. B. Causal models assume that the variable being forecast is related to other variables. 7. CPFR is a collaborative process of developing joint forecasts and plans with supply chain partners, rather than doing them independently. 8. Sales and Operations Planning (S&OP) is intended to match supply and demand through financial collaboration between marketing, operations, and finance, in order to ensure that supply can meet demand requirements.

demand planning summary

1. Forecasting process choice is influenced by a variety of factors 2. Forecasts are judgment or statistical model based 3. Both accuracy and bias should be considered 4. Demand management involves influencing customer demand 5. Supply chains can be made more responsive to changes in customer demand

principles of forecasting

1. Forecasts are rarely perfect 2. Forecasts are more accurate for groups than for individual items 3. Forecasts are more accurate for short term than long term horizons

problems with moving averages

1. Increasing the size of n (the number of periods averaged) does smooth out fluctuations better, but it makes the method less sensitive to changes in the data 2. Moving averages cannot pick up trends very well 3. Moving averages require extensive records of past data

realities of forecasting

1. Outside factors that we cannot predict or control often impact the forecast 2. Most forecasting techniques assume that there is some underlying stability in the system 3. Both product family and aggregated forecasts are more accurate than individual forecasts

forecast process performance

1. Short term forecasts are more accurate than long term forecasts 2. Aggregate forecasts are more accurate than detailed forecasts 3. Information from more sources yields a more accurate forecast

4 components of time-series models

1. Trend 2. Seasonality 3. Cycles 4. Random variations

bias error

A consistent tendency for forecasts to be greater or less than the actual values

forecasting impact on the organization

Every organizational function relies on forecasting for numerous things • *Marketing* - estimates of demand, future trends • *Finance* - set budgets, predict stock prices • *Operations* - capacity planning, scheduling, inventory levels • *Sourcing* - make purchasing decisions, select suppliers

measuring forecast error

Forecast error = Actual Demand - Forecast Value

focus forecasting

Forecasting that tries a variety of computer models and selects the best one for a particular application

human resources forecasting

Hiring, training, and laying off workers all depend on anticipated demand

exponential smoothing with trend adjustment

Step 1: Compute Ft, the exponentially smoothed forecast average for period t using the first equation Step 2: Compute the smoothed trend Tt, using the second equation Step 3: Calculate the forecast trend, FITt by the formula FITt = Ft + Tt

quantitative forecasting methods

TIME-SERIES MODELS: 1. Naive approach 2. Moving averages 3. Exponential smoothing 4. Trend projection ASSOCIATIVE MODEL: 5. Linear regression

mean absolute percent error (MAPE)

The average of the absolute difference between the forecasted and actual values, expressed as a percentage of the actual values