Is it possible to forecast seasonal products without removing the

Is it possible to forecast seasonal products without removing the seasonal variations? (graded) We calculate a seasonal index in order to remove the seasonal component before creating a forecast. Is it possible to remove this step and create a forecast with the seasonal variation still in place? Why or why not? Explain. Seasonal variations in data are regular up-and-down movements in a time series that relate to recurring events such as weather or holidays. Demand for coal and fuel oil, for example, peaks during cold winter months. The presence of seasonality makes adjustments in trend-line forecasts necessary. Seasonality is expressed in terms of the amount that actual values differ from average values in the time series. Analyzing data in monthly or quarterly terms usually makes it easy for a statistician to spot seasonal patterns. Seasonal relatives are used in deseasonalizing data or incorporating seasonality in a forecast. Deseasonalizing data is accomplished by dividing each data point by its corresponding seasonal relative. If we remove this step and create a forecast with the seasonal variation still in place, it is going to be inflated forecast and the differece between the forecasted value and the actual demand would be large. References: Heizer, Jay H. Operations management - 10th ed.Textbook The presence of seasonality makes adjustments in trend-line forecasts necessary. Seasonality is expressed in terms of the amount that actual values differ from average values in the time series. Analyzing data in monthly or quarterly terms usually makes it easy for a statistician to spot seasonal patterns. Seasonal indices can then be developed by several common methods. In what is called a multiplicative seasonal model, seasonal factors are multiplied by an estimate of average demand to produce a seasonal forecast. Our assumption in this section is that trend has been removed from the data. Otherwise, the magnitude of the seasonal data will be distorted by the trend. Render, Jay Heizer and Barry. Operations Management. 10.

Seasonality is a data pattern that repeats itself after a period of days, weeks, months, or quarters. Seasonality is expressed in amount that actually value differ from average value in the time series. Analyzing data in monthly or quarterly terms usually make it easy for a situation to spot seasonal patterns. According to our text, if you don't remove the seasonal data and you calculate your forcast it will give you a distorted result. Time-series forecasts involve reviewing the trend of data over a series of time periods. The presence of seasonality makes adjustments in trend-line forecasts necessary. Seasonality is expressed in terms of the amount that actual values differ from average values in the time series. Analyzing data in monthly or quarterly terms usually makes it easy for a statistician to spot seasonal patterns. Seasonal indices can then be developed by several common methods.

In what is called a multiplicative seasonal model, seasonal factors are multiplied by an estimate of average demand to produce a seasonal forecast. Our assumption in this section is that trend has been removed from the data. Otherwise, the magnitude of the seasonal data will be distorted by the trend. Ref: Operations Management, Tenth Edition Render, Jay Heizer and Barry. Operations Management, 10th Edition. Pearson Learning Solutions. . Seasonality are weather variations, vacations and holidays. Seasonality is expressed in terms of the amount that actual values deviate from the average value of the series and can be expressed as a percentage of the average amount. If we say that Seasonal relative/Seasonal indices is 1.45 for the quantity of television sold in August at Circuit City, it means that TV sales for that month are 45% above the monthly average. Seasonal factor of 0.60 for the number of notebooks sold at the UTD bookstore in April means that notebook sales are 40% below the monthly average. When we calculate the seasonal index, what is the range of the index that tells us there is not a seasonal component? A seasonal index is used when forecasting products with seasonal demand patterns. When a product experiences a seasonal demand pattern, demand has a repeatable shape during that timeframe. For example, many products linked to school, experience a "back to school" spike in demand. Similarly, products like suntan lotion have a summer seasonality. Seasonality can be experienced over any timeframe. Common timeframes are monthly and weekly. However, some retailers, like restaurants, develop a time of day seasonality. To support the analysis excluding seasonality, the most widespread practice usually consists in breaking up the studied series in distinct components in order to better understand its evolution. These components are: the long-term trend, the cycle, the seasonal component and the irregular component. The series is adjusted for trading days and for variable holidays such as Easter. A series’ deterministic components will be estimated in order to better understand its ups and downs. They will then be able to be rebuilt in order to reconstitute the original series to within about a random component. Seasonal component Part of a time series undergoing specific variations at certain moments during the year which come from these recurring ups and downs. This component is extracted from the series in order to produce the seasonally adjusted series. These seasonal wavings do not give any indication as to what is the current economic trend of the series. Irregular component This component results from statistical errors or from accidental or fortuitous events that is not repetitive. For this given month or quarter, the series presents an unexpected behaviour, its value being raised much more or much more low that usually at that time of the year. This component

belongs to the seasonally adjusted series and can be located while observing graphically the raw series. Trend-cycle This component gathers two parts: a long-term trend from general phenomena of growth or decrease usually linked to population or economic activity and to a rhythmic cycle from an economic variation suitable for economic fluctuations which, traditionally, go from expansion to recession, this cycle's length being unknown but longer than one year. It is the component trend-cycle which should be highlighted when one seasonally adjusts a series. My guess is that the only range of the index that tells us there is not a seasonal component is when there is no range, which would be zero. No upward or downward values, just the one it is and not anything over or under. Seasonal index represents the extent of seasonal influence for a particular segment of the year. The calculation involves a comparison of the expected values of that period to the grand mean. A seasonal index is how much the average for that particular period tends to be above (or below) the grand average. Therefore, to get an accurate estimate for the seasonal index, we compute the average of the first period of the cycle, and the second period, etc, and divide each by the overall average. The formula for computing seasonal factors is: Si = Di/D, where: Si = the seasonal index for ith period, Di = the average values of ith period, D = grand average, i = the ith seasonal period of the cycle. A seasonal index of 1.00 for a particular month indicates that the expected value of that month is 1/12 of the overall average. A seasonal index of 1.25 indicates that the expected value for that month is 25% greater than 1/12 of the overall average. A seasonal index of 80 indicates that the expected value for that month is 20% less than 1/12 of the overall average. 2. Deseasonalizing Process: Deseasonalizing the data, also called Seasonal Adjustment is the process of removing recurrent and periodic variations over a short time frame, e.g., weeks, quarters, months. Therefore, seasonal variations are regularly repeating movements in series values that can be tied to recurring events. The Deseasonalized data is obtained by simply dividing each time series observation by the corresponding seasonal index.

Almost all time series published by the US government are already deseasonalized using the seasonal index to unmasking the underlying trends in the data, which could have been caused by the seasonality factor." Accessed on 1/15/13 from: http://home.ubalt.edu/ntsbarsh/stat-data/forecast.htm Seasonal components are when certain time frames during the year vary. Comparing equivalents time frames (months or quarters) will enable us to see if the trend reoccurs or a pattern that will repeat. The seasonal index is how much of the demand for a particular time frame that is above or below the average demand. There are methods that can be used to reach the seasonal index Average method, linear regression as used in our course project, growth per cycle method and deseasonalizing method. When calculating the seasonal index, the range in the index that tell us there isn't a seasonal component would be when they do not show a range or maybe even when showing a really high decline. Data from seasonality index helps to determine the profitability, lead times, and stock inventory for the holiday. Just like an example, Christmas selections of products are changing every years and based on the product lines, the prices and profit margin are different. Therefore the forecast is sale would be different. Management must goes through product lines review from last year to eliminate the non-sell-able items and replace them with new products. Management would use the forecast of last year and implement the forecast for the next year based on the potential profit margin from which types of products are being offer. If I know the months or quarters where the seasonality occurs, can I just calculate the seasonal index for the month or quarter and not the others? I don't think that we can calculate the seasonality index just for the month or quarter where it occurs. To calculate seasonality index, we first find the average historical demand each month by summing the demand for that month in each year and dividing by the number of years of data available. Then we compute the average demand over all months by dividing the total average annual demand by the number of month. Seasonal index is then calculated for each month by dividing that month’s actual historical demand by the average demand over all months. So, we would need to do this for all months and not just the month or quarter where the seasonality occurs. Seasonal variation is measured in terms of an index, called a seasonal index. It is an average that can be used to compare an actual observation relative to what it would be if there were no seasonal variation. An index value is attached to each period of the time series within a year. This implies that if monthly data are considered there are 12 separate seasonal indices, one for each month. There can also be a further 4 index values for quarterly data. The following methods use seasonal indices to measure seasonal variations of a time-series data. Method of simple averages Ratio to trend method

Ratio-to-moving average method Link relatives method Ref: http://en.wikipedia.org/wiki/Seasonality Post Problem 4.10a Here 4.10a Moving average = sum demand in previous n periods/n YEAR 4 6+4+4/3= 4.7 YEAR 5 6+4+5/3= 5 YEAR 6 4+5+10/3= 6.3 YEAR 7 5+10+8/3 = 7.7 YEAR 8 10+8+7= 8.3 YEAR 9 8+7+9/3 = 8 YEAR 10 7+9+12/3 = 9.3 YEAR 11 9+12+14/3 =11.7 YEAR 12 12+14+15/3 = 13.7 Post Problem 4.10b Here Period Demand Weighed Forecast 1

4000

2

6000

3

4000

4

5000

5

10000 5000

6

8000

7250

7

7000

7750

8

9000

8000

9

12000 8250

4500

10 14000 10000

11 15000 12250 12

14000

Period Demand Weights Forecast 1 4000 1 2 6000 1 3 4000 2 4 5000 4500.00 5 10000 5000.00 6 8000 7250.00 7 7000 7750.00 8 9000 8000.00 9 12000 8250.00 10 14000 10000.00 11 15000 12250.00 12

14000.00

Post Problem 4.26 Here

1000 RADIALS/ YEAR

Y1

Y2

Y3 DEMAND WITH 1200 FORECAST

S

150

165

189

S

300

285

351

F

200

250

270

W

350

300

390

Season Y1 Y2 Y3 Forecast Fall 200 250 270 Winter 350 300 390 Spring 150 165 189 Summer 300 285 351 Total 1000 1000 Forecast 1200 4.26 ((Year 1+Year 2)*1.2)/2 = Forecast Season

Year 3 Forecast

Winter

390

Spring

189

Summer

351

Fall

270 1200