Forecasting_Assignment_ProblemSet - α for exponential...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
HA301: Forecasting Assignment Due Date: September 21 Please refer to forecasting.xls file posted on Blackboard site (under course documents folder – excel file sub-folder). I. Use the following methods to forecast demand for room-nights for the month of September 2007 . a. Naïve method b. Moving average with 4 time periods c. Weighted moving average with two time periods with weights: 0.7, 0.3 d. Weighted moving average with three time periods with weights: 0.5, 0.3, 0.2 e. Exponential smoothing with α = 0.65 II. Error analysis (for methods used in section I) a. If bias is used as the error measure, which is the best forecasting method? b. If MAD is used as the error measure which is the best forecasting method? c. If MSE is used as the error measure which is the best forecasting method? III. Finding best weights a. Find best
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: α for exponential smoothing method if MAD is used as the evaluation criteria. b. Find best weights for three period weighted moving average if Bias is used as the evaluation criteria. IV. Regression analysis Assuming that revenue is a function of Room-nights sold, develop a linear regression model. How good is this model? Using this model predict revenue if room-nights sold is 675. NOTE : ♦ This is an individual assignment – but student groups can work together if they so desire. However each student should complete the final version of the analysis themselves. ♦ You can upload the assignment directly to Blackboard – Digital Dropbox . ♦ Use different worksheet for each analysis. ♦ Create a summary worksheet which includes answers to all questions listed above....
View Full Document

This homework help was uploaded on 02/20/2009 for the course H ADM 243 taught by Professor Rkwortnik during the Fall '06 term at Cornell.

Ask a homework question - tutors are online