MGT 2070 Lecture Notes - Exponential Smoothing, Moving Average, Operations Management
Document Summary
Forecast: a statement about the future value of a variable of interest such as demand: cost/profit estimates, cash flow and funding, hiring/recruiting/training, pricing. Plan the use of the system (short/immediate-term: features. Accuracy decreases as time increases: elements of a good forecast. Timely (reach the decision makers in time for them to be relevant) How to chose a forecast technique: consider cost, accuracy, consider availability of historical data, computers, time, forecast horizon. Time series: a time ordered sequence of observations taken at regular intervals of time obtained by observing dependent variable: components. Wavelike variations lasting more than a year. Na ve forecasts: for any period equals the previous period"s actual value: simple, no cost, quick, nonexistent data analysis, can be a standard for accuracy. September 19, 2012: cannot provide high accuracy, stable time series data. Forecast for period t = actual demand or sales for period t-1.