Forecasting Demand Using Time Series Data A time series is a time-ordered sequen
ID: 2761721 • Letter: F
Question
Forecasting Demand Using Time Series Data A time series is a time-ordered sequence of observations taken at regular intervals over a period of time (hourly, daily, weekly, monthly, quarterly, annually, etc.). The data may be measurements of demand, earnings, profits, shipments, accidents, output, precipitation, productivity, CPI, etc. Analysis of time series requires the analyst to identify the underlying behavior of the series. The can often be accomplished by plotting the data and visually examining the plot. One or more patterns might appear: trends, seasonal variations, cycles, irregular variation, and random variations. Typical components of a time series are (1) the trends, (2) seasonal variations, (3) cyclical variation, (4) irregular variations, and (5) random variations of pure noise. 1-(800) flowers is in the business of selling flowers. Briefly describe the components of a time series and explain how these components impact the volume of flower sales.Explanation / Answer
Trend is the steady, long term component of a time series which shows the steady increase or decrease over a period. For a flower business, it is the overall growth in business over time (or decline, if it is a loss-making business).
Seasonal variations are the up and down movement on basis of seasonal demand. For flowers, festive and wedding seasons are the peak season for the business.
Cyclical variations occur with economic business cycle, and these peak during expansion and reach trough during recession. When there is a recession, for example, overall demand for flower, a non-necessity good, will be much lower.
Irregular variations occur infrequently and unpredictably, but these may repeat over the course of the business. For example, a sudden destruction of Tulip floriculture garden caused by a flood will lead to lower supply of tulips, but if the garden is situated in a flood-prone region, it may occur again, though not too frequently.
Random variation is an one-off, unpredictable and sudden disturbance in the time series pattern. Continuing with previous example, a fire in the Tulip floriculture garden is a random noise because it is sudden, unpredictable and extremely unnatural, almost impossible to repeat again.