Chapter 4 - Forecasting PDF

Preview

Summary

IAF716 - Operations Management Chapter 4 - Forecasting October 15, 2018What are the Three Time Horizons and Models to Apply to Each Forecasting - the art and science of predicting future events. ➔ May involve taking historical data and projecting them into the future with some sort of mathematical m...

Description

IAF716 - Operations Management Chapter 4 - Forecasting October 15, 2018 What are the Three Time Horizons and Models to Apply to Each Forecasting - the art and science of predicting future events. ➔ May involve taking historical data and projecting them into the future with some sort of mathematical model. ➔ It may also be a subjective or intuitie prediction ➔ Affects inventory, business strategies ➔ Purpose: accurate estimates to make the optimal decision ➔ Good forecasts = essential part of efficient services and manufacturing operations Forecasting is usually classified by the “Future Time Horizon” -- which time horizons fall into three categories: 1) short-Range Forecast: has a time span up to one year but is generally less than three months a) Used for planning purchasing, job scheduling, workforce levels, job assignments and production levels 2) Medium- Range Forecast:A medium-range, or intermediate, forecast generally spans from three months to three years. It is useful is sales planning, production planning and budgeting, cash budgeting, and analysis of various operating plans 3) Long-range Forecast: usually three years or more in time span. long range forecasts are used in planning for new products, capital expenditures, facility location or expansion, research development Medium- and long- range forecasts are distinguished from short-range forecasts by three features: 1) intermediate and long-run forecasts deal with more comprehensive issues and support management decisions regarding planning and products, plants, and processes. 2) Short-term forecasting usually employs different methodologies than longer-term forecasting. Mathematical techniques are commonly used. 3) Short-range forecasts tend to be more accurate than longer-range forecasts a) Factors that influence demand change everyday -- as the time horizon lengthens = forecast accuracy diminish The Influence of Product Life Cycle

Introduction and growth require longer forecasts than maturity and decline As products passes through life cycle, forecasts are useful in protecting: Staffing Levels | Inventory Levels | Factory Capacity 3 Types of Forecasts: 1) Economic Forecasts - address business cycle - inflation rate, money supply, housing starts, etc 2) Technological Forecasts - predict rate of technological progress a) Impacts development of new products 3) Demand Forecasts - predicts sales of existing products and services Strategic Importance of Forecasting:

1 of 5

➔ Human Resources - Hiring, training, laying off workers ➔ Capacity - capacity shortages can result in dependendable delivery, loss of customers, loss of market share ➔ Supply-Chain Management - good supplier relations and price advantages Seven Steps in Forecasting: 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 6) Make the Forecasts 7) Validate and Implement Results Forecasting is not perfect. Most Techniques assume an underlying stability in the system. Product family and aggregate forecasts are more accurate than individual product forecasts What are the 4 Qualitative Models and When to Use Each? Qualitative Methods -

Quantitative Methods -

used when the situation is vague and little data exist. (i.e. New products and new technology) ➔ Involves intuition and experience (i.e. forecasting sales on internet)

Used when situation is “stable” and historical data exists (i.e. existing products and current technology) ➔ Involves mathematical techniques (i.e. forecasting sales of colour television)

4 Types of Qualitative Methods: 1) Jury of Executive Opinion - pool opinions of High Level Experts, sometimes augment by statistical models 2) Delphi Method - panel of experts, queried iteratively 3) Sales Force Composite - estimates from individual salespersons are reviewed for reasonableness, then aggregated 4) Consumer Market Survey - ask the customer Apply The Naive, Moving-Average, Exponential Smoothing, and Trend Methods 5 Quantitative Approaches: ➔ Time Series Models - is historical/past data collected over regular period time. Forecast is based upon the underlying patterns contained within those data. Time Series analysis is generally presented in graphical form ◆ Set of evenly spaced numerical data ● Obtained by observing response variable at regular time periods ◆ Forecast based only on past values, no other variables ● Assumes that factors influencing past and present will continue influence in future ◆ Trend Series Components:

2 of 6

1) Trend - persistent, overall upward or downwards pattern a) Changes due to population, technology, age, culture. Etc b) Typically several years duration 2) Cyclical - repeating up and down movements a) Affected by business cycle, political and economic factors b) Multiple years duration c) Often causal or associative relationships 3) Seasonal Reason - regular pattern up and down fluctuations a) Due to weather, customs, etc b) Occurs within a single year 4) Random - erratic, unsystematic, “residual” fluctuations a) Due to random variation or unforeseen events b) Short duration and non-repeating 1) Naive Approach - assumes demand in next period is the same as demand in most recent period a) Sometimes cost effective and efficient and can be good starting point 2) Moving averages - Moving Average Method is a series of arithmetic means a) Used if little or no trend. Used often for smoothing i) Provides overall impression of data over time b) Weighted Moving Average - used when some trend might be present i) Older data usually less important ii) Weights based on experience and intuition 3) Exponential Smoothing - increasing “n” smooths the forecast but makes it less sensitive changes a) Does not forecast trends well b) Requires extensive historical data c) Form of weighted moving average i) Weights decline exponentially ii) Most recent data weighted most d) Requires smoothing constant (a) i) Ranges from 0 to 1 ii) Subjectively chosen e) Involves little record keeping of past data f) Exponential smoothing uses past forecasts and past demand data to generate a new forecast ➔ Associative Models - these techniques use variables which are relates to product demand to predict demand ◆ Uses several variables related to the quantity being predicted ◆ More powerful than time-series methods ◆ Most common technique is linear regression analysis 0 forecasting an outcome based on

3 of 6

predictor variables using the least squares 4) Trend Projection - fitting a trend line to historical data points to project into the medium to long-range a) Linear trends can be found using the least-squares technique b) Least-Squares Requirements i) We always plot the data to ensure a linear relationship ii) We do not predict time periods far beyond database iii) Deviations around the least-squares line are assumed to be random c) Seasonal Variations in Data i) The multiplicative seasonal model can adjust trend data for seasonal variations in demand ii) Seasonal Forecast Calculation (1) Steps in the process: (a) Find Average Historical Demand for each season (b) Compute the average demand over all seasons (c) Compute a seasonal index for each season (d) Estimate next year’s total demand (e) Divide this estimate of total demand by the number of seasons, then multiply it by the seasonal index for that season d) Associative Forecasting Methods i) Using several variables related to the quantity being predicted ii) More powerful than time-series methods (1) Regression Analysis (2) Correlation Analysis iii) Most common technique is linear regression analysis 5) Linear Regression - forecasting an outcome based on predictor variables using the least-squares

How to compute the 3 Measures of Forecast Accuracy 1) Mean Absolute Deviation (MAD) 2) Mean Squared Error (MSE)

3) Mean Absolute Percent Error

(MAPE)

4 of 6

➔ ➔ ➔ ➔ ➔

Develop Seasonal Indices? Conduct a Regression & Correlation Analysis How strong is the linear relationship between the variables? Correlation does not necessarily imply causality! Coefficient of correlation, r, measures degree of association Values range from -1 to +1 Perfect Positive | Positive Correlation | No Correlation | Perfect Negative Correlation

Use a Tracking Signal Tracking Signal - measures how well the forecast is predicting actual values ➔ Ratio of cumulative forecasts errors to MAD ◆ Low values = tracking signal ◆ If forecasts are continually high or low, the forecast has a bias error ➔ Used to monitor and control forecasts Forecasting in Service Sector - Presents Unusual Challenges ➔ Presents unusual challenges ◆ Special need for short-term records ◆ Needs differ greatly as function of industry and product ◆ Holidays and other calendar events ◆ Unusual events

5 of 6...