FORECASTING:INCORPORATING SEASONAL EFFECTS INTO FORECASTING METHODS

By -

INCORPORATING SEASONAL EFFECTS INTO FORECASTING METHODS

It is fairly common for a time series to have a seasonal pattern with higher values at certain times of the year than others. For example, this occurs for the sales of a product that is a popular choice for Christmas gifts. Such a time series violates the basic assumption of a constant-level model, so the forecasting methods presented in the preceding section should not be applied directly.

Fortunately, it is relatively straightforward to make seasonal adjustments in such a time series so that these forecasting methods based on a constant-level model can still be applied. We will illustrate the procedure with the following example.

Example. The COMPUTER CLUB WAREHOUSE (commonly referred to as CCW) sells various computer products at bargain prices by taking telephone orders directly from customers at its call center. Figure 27.3 shows the average number of calls received per day in each of the four quarters of the past three years. Note how the call volume jumps up sharply in each Quarter 4 because of Christmas sales. There also is a tendency for the call volume to be a little higher in Quarter 3 than in Quarter 1 or 2 because of back-to-school sales.

To quantify these seasonal effects, the second column of Table 27.1 shows the average daily call volume for each quarter over the past three years. Underneath this column, the overall average over all four quarters is calculated to be 7,529. Dividing the average for each quarter by this overall average gives the seasonal factor shown in the third column.

In general, the seasonal factor for any period of a year (a quarter, a month, etc.) measures how that period compares to the overall average for an entire year. Specifically, using historical data, the seasonal factor is calculated to be

INTRODUCTION TO OPERATIONS RESEARCH-0649

Your OR Courseware includes an Excel template for calculating these seasonal factors.

The Seasonally Adjusted Time Series

It is much easier to analyze a time series and detect new trends if the data are first adjusted to remove the effect of seasonal patterns. To remove the seasonal effects from the time series shown in Fig. 27.3, each of these average daily call volumes needs to be divided by the corresponding seasonal factor given in Table 27.1. Thus, the formula is

INTRODUCTION TO OPERATIONS RESEARCH-0650

Applying this formula to all 12 call volumes in Fig. 27.3 gives the seasonally adjusted call volumes shown in column F of the spreadsheet in Fig. 27.4.

INTRODUCTION TO OPERATIONS RESEARCH-0651

In effect, these seasonally adjusted call volumes show what the call volumes would have been if the calls that occur because of the time of the year (Christmas shopping, back- to-school shopping, etc.) had been spread evenly throughout the year instead. Compare the plots in Figs. 27.4 and 27.3. After considering the smaller vertical scale in Fig. 27.4, note how much less fluctuation this figure has than Fig. 27.3 because of removing seasonal ef- fects. However, this figure still is far from completely flat because fluctuations in call volume occur for other reasons beside just seasonal effects. For example, hot new products attract a flurry of calls. A jump also occurs just after the mailing of a catalog. Some random fluctuations occur without any apparent explanation. Figure 27.4 enables seeing and analyzing these fluctuations in sales volumes that are not caused by seasonal effects.

INTRODUCTION TO OPERATIONS RESEARCH-0652

The General Procedure

After seasonally adjusting a time series, any of the forecasting methods presented in the preceding section (or the next section) can then be applied. Here is an outline of the gen- eral procedure.

1. Use the following formula to seasonally adjust each value in the time series: actual value

Seasonally adjusted value = --.

seasonal factor

2. Select a time series forecasting method.

3. Apply this method to the seasonally adjusted time series to obtain a forecast of the next seasonally adjusted value (or values).

4. Multiply this forecast by the corresponding seasonal factor to obtain a forecast of the next actual value (without seasonal adjustment).

As mentioned at the end of the preceding section, an Excel template that incorporates seasonal effects is available in your OR Courseware for each of the forecasting methods to assist you with combining the method with this procedure.

Comments

Post a Comment

Popular posts from this blog

DUALITY THEORY:THE ESSENCE OF DUALITY THEORY

By -
Image
THE ESSENCE OF DUALITY THEORY Given our standard form for the primal problem at the left (perhaps after conversion from another form), its dual problem has the form shown to the right. Thus, with the primal problem in maximizatio n form, the dual problem is in minimization form instead. Furthermore, the dual problem uses exactly the same pa r amete r s as the primal problem, but in different locations, as summarized below. 1. The coefficients in the objective function of the primal problem are the right-hand sides of the functional constraints in the dual problem. 2. The right-hand sides of the functional constraints in the primal problem are the coef- ficients in the objective function of the dual problem. 3. The coefficients of a variable in the functional constraints of the primal problem are the coefficients in a functional constraint of the dual problem. To highlight the comparison, now look at these same two problems in matrix notation (as introduced at the beginn...
Read more

NETWORK OPTIMIZATION MODELS:THE MINIMUM SPANNING TREE PROBLEM

By -
Image
THE MINIMUM SPANNING TREE PROBLEM The minimum spanning tree problem bears some similarities to the main version of the shortest-path problem presented in the preceding section. In both cases, an undi r ecte d and connected network is being considered, where the given information includes some mea- sure of the positive length (distance, cost, time, etc.) associated with each link. Both problems also involve choosing a set of links that have the shortest total length among all sets of links that satisfy a certain property. For the shortest-path problem, this property is that the chosen links must provide a path between the origin and the destination. For the minimum spanning tree problem, the required property is that the chosen links must provide a path between ea c h pair of nodes. The minimum spanning tree problem can be summarized as follows: 1. You are given the nodes of a network but not the links. Instead, you are given the po- tential links and the positive length for each ...
Read more

INTEGER PROGRAMMING:THE BRANCH-AND-CUT APPROACH TO SOLVING BIP PROBLEMS

By -
TH E BRANCH-AND-CUT APPROACH TO SOLVING BIP PROBLEMS Integer programming has been an especially exciting area of OR since the mid-1980s be- cause of the dramatic progress being made in its solution methodology. Background To place this progress into perspective, consider the historical background. One big break- through had come in the 1960s and early 1970s with the development and refinement of the branch-and-bound approach. But then the state of the art seemed to hit a plateau. Rel- atively small problems (well under 100 variables) could be solved very efficiently, but even a modest increase in problem size might cause an explosion in computation time be- yond feasible limits. Little progress was being made in overcoming this exponential growth in computation time as the problem size was increased. Many important problems arising in practice could not be solved. Then came the next breakthrough in the mid-1980s, with the introduction of the b r an c h- and-cu t approach to sol...
Read more