Business Management Case Study: Snow A Revenue Manager Of The Hamilton Hotel
Index
Cover Page 1
1. Executive Summary 3
2. Background 3
3. Issue Statement 4
4. Analysis of the problem 4-9 1. Moving Average 4-6
2. Holt Winters’ Exponential Smothing 6-7
3. Simple Average 7
3. Exponential Smothing 8-9
5. Recommandations 10
6. References 11
Executive Summary In the given case study, Snow the revenue manager of the Hamilton hotel has to make a decision which is to accept the group of not for 22nd August. As it is a business hotel and generally it is difficult to have a full house on the weekend. She also needs to keep in mind that there is no situation of overbooking in the hotel. It is a situation of the hotel concentrating on the maximization of profit by filling up the rooms but they can …show more content…
The property is managed and operated by the worldwide expanding company of Marriot.
It is really important to have the accuracy of a forecast because a high forecast can lead to excessive inventories and a lower forecast can lead to a situation of out of stock. Thus, error in the forecast can create a situation of overbooking or empty rooms if it is not carried out with precaution. As the process of forecasting is costly, but if there is an error in the forecast it can increase the cost due to the risks involved with it.
There are different techniques and calculations to forecasting the demand each one of having their own drawbacks and issues as they depend on different factors. The propose of a forecast is to estimate the probable booking for the specific day or period.
A key factor for the success of a revenue management system is to use high quality disaggregated forecasts for a long forecasting horizon (up to two months or so) (Weatherford and Kimes, 2003). For this reason, it is crucial that the selected time series forecasting method will be able to produce accurate forecasts for dates farther away (2–8 weeks) because it is expected that the pickup meth- odds will be very accurate for the short forecasting horizon (1–2 …show more content…
This means that we accept the group.
4. Exponential Smoothing
Exponential smoothing is an extension moving average to forecast the demand where you give more wattage to recent data and spread the rest to the other data. This is done to make sure that you consider the recent data scenario for e.g. last 5 days to forecast the following days so that it reflects the appropriate scenarios.
The standard formula for the calculation of exponential smoothing is: -
Where, represents the value of demand for the rooms and alpha represents the parameter to for exponential smoothing.
By applying this formula in the data given in the case study we can find out the MAPE which represents the error in the forecast. The values given to alpha are .1 and .9.
Fig 6
As seen in Fig.6 where the alpha is given the value of .1 the total average of MAPE 5.56% which shows the error in the forecasting process. So in order to calculate the demand for 22nd august we need to apply the following
Actual demand =.955*1839
=1756
=1756+60 = 1816
This shows that 1816 rooms will be used on 22nd of august even if we accept the
Cover Page 1
1. Executive Summary 3
2. Background 3
3. Issue Statement 4
4. Analysis of the problem 4-9 1. Moving Average 4-6
2. Holt Winters’ Exponential Smothing 6-7
3. Simple Average 7
3. Exponential Smothing 8-9
5. Recommandations 10
6. References 11
Executive Summary In the given case study, Snow the revenue manager of the Hamilton hotel has to make a decision which is to accept the group of not for 22nd August. As it is a business hotel and generally it is difficult to have a full house on the weekend. She also needs to keep in mind that there is no situation of overbooking in the hotel. It is a situation of the hotel concentrating on the maximization of profit by filling up the rooms but they can …show more content…
The property is managed and operated by the worldwide expanding company of Marriot.
It is really important to have the accuracy of a forecast because a high forecast can lead to excessive inventories and a lower forecast can lead to a situation of out of stock. Thus, error in the forecast can create a situation of overbooking or empty rooms if it is not carried out with precaution. As the process of forecasting is costly, but if there is an error in the forecast it can increase the cost due to the risks involved with it.
There are different techniques and calculations to forecasting the demand each one of having their own drawbacks and issues as they depend on different factors. The propose of a forecast is to estimate the probable booking for the specific day or period.
A key factor for the success of a revenue management system is to use high quality disaggregated forecasts for a long forecasting horizon (up to two months or so) (Weatherford and Kimes, 2003). For this reason, it is crucial that the selected time series forecasting method will be able to produce accurate forecasts for dates farther away (2–8 weeks) because it is expected that the pickup meth- odds will be very accurate for the short forecasting horizon (1–2 …show more content…
This means that we accept the group.
4. Exponential Smoothing
Exponential smoothing is an extension moving average to forecast the demand where you give more wattage to recent data and spread the rest to the other data. This is done to make sure that you consider the recent data scenario for e.g. last 5 days to forecast the following days so that it reflects the appropriate scenarios.
The standard formula for the calculation of exponential smoothing is: -
Where, represents the value of demand for the rooms and alpha represents the parameter to for exponential smoothing.
By applying this formula in the data given in the case study we can find out the MAPE which represents the error in the forecast. The values given to alpha are .1 and .9.
Fig 6
As seen in Fig.6 where the alpha is given the value of .1 the total average of MAPE 5.56% which shows the error in the forecasting process. So in order to calculate the demand for 22nd august we need to apply the following
Actual demand =.955*1839
=1756
=1756+60 = 1816
This shows that 1816 rooms will be used on 22nd of august even if we accept the