Module 3 Section E: Quantitative Forecasting

Trend

A change in _____ occurs if it is sustained over multiple periods. Lower alpha values increase lags in _____.

one less than one greater than one

A seasonal index ____ means that the period's demand is equal to average demand A seasonal index _____ means that the period's demand is less than the average A seasonal index ____ means that the period's demand is greater than average

Upward

A time-series forecast done during a seasonal upswing would predict the swing to keep going _____. Seasonal swings will need to be removed, or the results will be of little use.

Life Cycle Analysis

Another quantitative forecasting technique, ________ is based on applying past patterns of demand data covering introduction, growth, maturity, saturation, and decline of similar products to a new product family. This is a comparative technique that analyzes and adapts existing data and patterns and extrapolates them to create a forecast based on historical information.

Positive correlation Negative correlation

As the leading indicator rises, so does demand. This is _____ As the leading indicator rises, demand falls. This is _____

Actual demand / Trend sum of same period ratios / # of periods

Calculations for step 2: actual demand to trend ratio = trend adjusted seasonal index =

Time Series Analysis X2 Time Series

Decomposition is a type of ______: analysis of any variable classified by time in which the values of the variable are functions of the time periods. ___ is used in forecasting. A ____ consists of seasonal, cyclical, trend, and random components

(alpha x last period's demand) + [(1-alpha) last period's forecast]

Exponential smoothing new forecast =

Simple moving average = sum of demand from most recent periods/ # of periods Weighted moving average = (w1Xn1) + (w2Xn2) + (wn X nn) / sum of weights

Formulas for Simple moving average: Weighted moving average:

Forecast

How does one choose the best method? The choice of _____ method should consider 1. Degree to which the available data are complete vs incomplete 2. Degree of stability in the data (stable vs unstable data)

Seasonality

If ______ exists, it must be removed prior to forecasting and then added back prior to interpreting the results

Alpha

If alpha is .3, it puts 30% of the weight on the last period's demand and 70% on the last period's forecast. The ____ the alpha is (less weight put on actual demand) the more exponential smoothing will smooth out random variation, but will also lag a trend more. When the alpha is ______, exponential smoothing will lag a trend less but will smooth out random variation less

Forecast Management

It is important to avoid falling into the trap of using the same forecast methods across all products; this can lead to erratic and unreliable information. _______: the process of making, checking, correcting, and using forecasts. It also includes the determination of the forecast horizon.

Forecasting

Key ____ principles: 1. Forecasts are wrong most of the time 2. Be sure there is an estimate of forecast reliability or error rates for each forecast 3. Forecasts are more accurate for product families than for individual items 4. Forecasting is more accurate in the near term than in the long term

Correlation Causation Correlation

Note that ______ is not _____. ____ is an observation that the change in an independent variable has a measurable effect on a dependent variable.

Period avg demand = sum all like periods in series / # periods Avg. Demand all periods = sum period avg. demands / # periods Seasonal Index = Period avg. demand / avg. demand all periods Deseasonalized Demand = actual seasonal demand / seasonal index

Period average demand = Avg. Demand all periods = Seasonal Index = Deseasonalized Demand =

Forecasting Wrong Forecast Reliability Product Families Near Long

Principles of ____: 1. Forecasts are ____ most of the time 2. Always be sure there is an estimate of ______ or error rates for each forecast 3. Forecasts are more accurate for _______ than for individual items 4. Forecasting is more accurate in the ________ term than in the _____ term

Roofing sales is the predicted variable Housing starts is the predictor

Roofing sales = (m x prior month's housing starts) + b Roofing sales is the Housing starts is the

Least Squares Method

Simple regression (linear regression) uses the ______: method of curve fitting that selects a line of best fit through a plot of data to minimize the sum of squares of the deviations of the given points from the line. The ____ is used to make an association between the dependent variable, y (the thing you are trying to predict), and the independent variable x (the predictor). y = mx+b

Trend adjusted seasonal forecast Trend

Step 3: Calculate the _____________ * for each quarter of the forecasted year, use the formula: Trend x Seasonal Index to get the trend adjusted seasonal forecast for the period * To determine the annual trend adjusted forecast, sum the quarterly forecast results *Compare the aggregate forecast to the actual demand of the preceding year and determine the difference. This figure indicates the effect of the ___ on the aggregate forecast

Deseasonalize Demand

Steps to ________: 1. Determine Period Average Demand : sum of all like periods in the series / # of periods 2. Determine average demand all periods: sum of period avg. demands / # of periods 3. Determine seasonal index: Period avg. demand / avg. demand all periods 4. Apply seasonal index to the raw data: Actual seasonal demand / seasonal index (do for each period)

Decomposition

The ____ of time series data seeks to understand the patterns of demand in a given sequence of historical data. ________: a method of forecasting where time series data is separated into up to three components: Trend, Seasonal, and Cyclical.. A fourth component, Random, is data with no pattern. The new forecast is made by projecting the patterns individually determined and then combining them

Predictor Dependent variable

The ______ variable is called the independent variable The element being predicted is called the ____.

Plot the seasonal data and calculate the trend line

The first step is to _____________ Use the regression analysis formula y = mx+b y = 50x_+ 161 50x = slope is 50 units per quarter 161 units is the intercept where the trend line starts

1. Seasonality 2. Trend 3. Cycle 4. Random Variation

The main components of _________ that can be observed as patterns when plotted visually are: 1. 2. 3. 4.

Period average demand = Avg. Demand all periods = Seasonal Index = Deseasonalized Demand =

The order to perform the calculations required to deseasonalize demand: 1 2 3 4

Correlation

The relationship between two sets of data such that when one changes, the other is likely to make a corresponding change. If the changes are in the same direction, there is positive correlation. When changes tend to occur in opposite directions, there is negative correlation. When there is little correspondence or changes are random, there is no correlation.

Demand Filtering Demand Filter

The removal of outliers from demand data in order to provide a reasonable historical base from which to forecast is called _________. It is a method of controlling variations by providing a check that limits the amount of the variation from one period to the next. A ______ typically is a ratio of the new demand to the average of the old demand.

Calculate the trend adjusted seasonal factor seasonal forecast

The second step is to ______ This step requires two calculations: 1. Determine the actual to trend ratio by dividing actual demand/trend for each quarter of the two years 2. Calculate the trend adjusted seasonal indexes based on averaging same quarter ratios for quarters 1-4 for the two years Use the trend-adjusted seasonal indexes to generate the ______ for the following year.

Time Series Decomposition

The steps for using ______ to create a forecast 1. Plot the Seasonal Data and calculate the trend line 2. Calculate the trend adjusted seasonal factor 3. Calculated the trend adjusted seasonal forecast

Reapply Seasonality Seasonalized Forecast

To _______ to a forecast, apply the proper seasonal index to the deseasonalized data. ________ = Seasonal Index X Deseasonalized period forecast The ____ is the actual forecast values for each period of the forecast.

Trend X seasonal index = trend adjusted seasonal forecast per period sum of trend adjusted seasonal forecast per period = annual trend adjusted forecast

To determine the trend adjusted seasonal forecast: Trend adjusted seasonal forecast per period = Annual trend adjusted forecast =

Higher

To follow a trend more closely but smooth random variation less, a _____ alpha is used.

Deseasonalize

Why _____ data? 1. To identify straight line trends 2. To review trends while developing new forecasts into the future 3. Seasonality factors will then be applied back to a new forecast

Multiplicative Seasonal Variation

With __________: the trend is multiplied by the seasonal factors. The highs and lows would both increase in this method, and the seasonality would appear to be more volatile.

Econometric Model

____: a set of equations intended to be used simultaneously to capture the way in which dependent and independent variables are interrelated. An ____ could be used to explain the demand for housing starts by looking at the consumer base, internet interest rates, personal incomes, and land availability

Moving Average

____: an arithmetic average of a certain number (n) of the most recent observations. As each new observation is added, the oldest observation is dropped. The value of n (the number of periods to use for the average) reflects responsiveness versus stability in the same way that the choice of the smoothing constant does in exponential smoothing. There are two types of ___: 1. Simple 2. Weighted Selecting the amount of Periods is important: ¤Longer periods provide more smoothing. ¤Shorter periods react to trends more quickly.

Trend Seasonal Cyclical Random

_____ component: general horizontal upward or downward movement over time. ______ component: recurring demand pattern such as day, of the week, weekly, monthly, or quarterly. There are two types of ___ variation: additive and multiplicative. ______ component: includes any repeating, nonseasonal pattern. Repetitive activity other than annual recurrent periods, such as the economic cycle of growth and recession ____: Data with no pattern

Exponential Smoothing

_____ does not average multiple periods, but it does involve weighting. It uses three inputs: last periods forecast, last periods demand, and a smoothing constant, alpha, a number between 0 and 1 that is a percentage weighting where 1 = 100%.

Trend

_____: A general upward or downward movement of a variable over time. They can also be flat. ___ can be influenced to varying degrees internally by things like promotions and externally by things outside of one's control like the economic cycle.

Base Series

_____: A standard succession of values of demand-over-time data used in forecasting seasonal items. This series of factors is usually based on the relative level of demand during the corresponding period of previous years. The average value of the base series over a seasonal cycle is 1.0. A figure higher than 1.0 indicates that demand for that period is higher than average; a figure less than 1.0 indicates less-than-average demand. For forecasting purposes, the base series is superimposed upon the average demand and trend in demand for the item in question.

Regression Analysis

_____: A statistical technique for determining the best mathematical expression describing the functional relationship between one response and one or more independent variables

Causal Forecasting

_____: A type of forecasting that uses cause-and-effect associations to predict and explain relationships between the independent and dependent variables. Also known as associative correlation or extrinsic forecasting, use cause and effect associations to predict and explain relationships or correlation between variables.

Deseasonalized Data

_____: Data from which seasonality has been removed using annual moving averages. You must do this prior to forecasting. Forecast _____ demand, not seasonal demand

Second Order Smoothing

_____: a method of exponential smoothing for trend situations that employs two previously computed averages, the singly and doubly smoothed values to extrapolate into the future. This method accounts for trends, which would be applicable during a growth phase

Extrinsic Forecasting Techniques Extrinsic

_____: forecast method using a correlated leading indicator; for example, estimating furniture sales based on housing starts. _____ forecasts tend to be more useful for large aggregations, such as total company sales, than for individual product sales. This technique is best for long-term forecasting at the aggregate level. It is often the best way to detect changes in a trend. Ex: Simple Regression Analysis, Multiple regression analysis, Econometrics

Cycle

_____: refer to the wavelike patterns observed in the growth and recession trends of teh economy over years. Unlike seasonality, economic cycles do not repeat over a predictable period of time.

Stable Data Unstable Data

______ data have a distinct pattern such as seasonality or trends. ____ data there is randomness and no distinct pattern

Seasonality

______: A predictable repetitive pattern of demand measured within a year where demand grows and declines. These are calendar-related patterns that can appear annually, quarterly, monthly, weekly, daily and/or hourly. _____ repeats over the analysis period and can be isolated from other sources of variation and removed temporarily so that it will not influence forecasting.

Simple Moving Average

______: It is recalculated using the most recent set of periods, dropping the oldest period and adding the just-ended period. Typically, 3-6 periods are in use. It can be useful when demand is relatively constant from period to period. The method can be used to prevent an overreaction to a random or irregular spike or dip in a given month because it smooths out these variations. Drawback: if there is a change in trend, this method would be slow to respond. It would lag the trend _____ = sum of demand from most recent periods / # periods

Intrinsic Forecast Method

______: a forecast based on internal factors, such as an average of past sales. ____, or time series, forecasting uses internal info such as the firm's historical data on demand for a product family or individual products. These techniques assume that the near-term past is a good guide to the near-term future.

Time Series Forecasting

______: a forecasting method that projects historical data patterns into the future. It involves the assumption that the near term future will be like the recent past. ____ methods assume that the factors that influenced the past will continue on into the future. When that trend is unlikely to be stable, causal/associative forecasting may be needed. Ex: Naive Moving Averages exponential smoothing time series decomposition

Weighted Moving Average

______: an averaging technique in which the data to be averaged is not uniformly weighted but is given values according to its importance. It places weights on the periods being averaged, usually to put greater emphasis on the more recent periods and relatively less on the more distant periods. When calculating the _____, you divide by the sum of the weights rather than the number of periods. _____ = (w1Xn1) + (w2Xn2) + (w3Xn3) etc/ (sum of weights) - assumes that weights are whole numbers and not fractions of one)

Random Variation

______: any variation left over after after seasonality and trends have been acounted for. It reflects that customers vary when where and in what quantities they buy products; the level of variation can differ greatly. If _____ is small, forecasting will be fairly accurate. If its large, errors will be high

Additive seasonal varition

______: assumes that there is a constant seasonal amount regardless of what the trend or average amount is. The seasonality is overlaid on the trend; this is what is happening in this example.

Exponential Smoothing Forecast

_______ = (alpha x last periods demand) + [(1-alpha) x last periods forecast]

Focus Forecasting

_______: A system that allows the user to simulate the effectiveness of numerous forecasting techniques, enabling selection of the most effective one.

Curve Fitting

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

Smoothing Constant, alpha

_______: the weighting factor that is applied to the most recent demand, observation, or error. In this case, the error is the difference between actual demand and the forecast for the most recent period. The _____ smooths out the random spikes or dips in actual demand by placing more weight on the prior forecast. The value is selected by experience, trial and error, and testing against historical data

First order smoothing

________: A single exponential smoothing; a weighted moving average approach that is applied to forecasting problems where the data does not exhibit significant trend or seasonal patterns.

Adaptive Smoothing

________: a form of exponential smoothing in which the smoothing constant is automatically adjusted as a function of forecast error measurement.

Exponential Smoothing Forecast

________: a type of weighted moving average forecasting technique in which past observations are geometrically discounted according to their age. The heaviest weight is assigned to the most recent data. The technique makes use of a smoothing constant to apply to the difference between the most recent forecast and the critical sales data, thus avoiding the need of carrying historical sales data. The approach can be used for data that exhibits no trend or seasonal patterns.

Quantitative Forecasting Techniques

________: an approach to forecasting where historical demand data is used to project future demand. Extrinsic and Intrinsic Techniques are typically used.

Complete Incomplete

________: if all required sales data for a particular item as well as the causal variables are available, then the data are ________ _______ data would have limited or even an absence of sales data for a particular product or would not have the causal variables identified.

Leading indicator

_________ a specific business activity index that indicates future trends. For example, housing starts is a _____ for the industry that supplies builders' hardware. These economic or demographic ______ tend to be among the first types of data that can show a change in a trend. Ex: housing starts, orders for durable goods and capital equipment Ex: Demographic info on birth rates, age distribution, income, education levels

Forecast

_________: An estimate of future demand. A ____ can be constructed using quantitative methods, qualitative methods, or a combination of methods, and it can be based on extrinsic (external) or intrinsic (internal) factors. Various ______ techniques attempt to predict one or more of the four components of demand: cyclical, random, seasonal, and trend

Multiple Regression Models

___________: a form of regression analysis where the model involves more than one independent variable. There are multiple predictive variables rather than just one. ex: one could add marketing spend to the roofing sales analysis to determine if this increases or decreases the predictive value of the equation

Seasonal Index

____________: a number used to adjust data to seasonal demand. It provides information on how much each seasonal period's demand has varied from the average demand in the past, and it is used to estimate how much seasonal demand will vary from average demand in a future seasonal period.

Least Squares Method

two other elements are used in the ____ formula 1. The slope, rise/run denoted with an "m" 2. The y-intercept - the fixed starting point denoted with a "b" - the intercept is where the slope intercepts zero on a chart 3. y-hat is the predicted value of y y-hat= mx+b