- Jan 980 Table 1 Demand Data May June 1500 L3d Feb Mar April 1100 1270 1325 1380 July 1550 2 L3d Aug 1530 2 L3d Sept 1 (14.58 KiB) Viewed 43 times
- Jan 980 Table 1 Demand Data May June 1500 L3d Feb Mar April 1100 1270 1325 1380 July 1550 2 L3d Aug 1530 2 L3d Sept 2 (3.78 KiB) Viewed 43 times
- Jan 980 Table 1 Demand Data May June 1500 L3d Feb Mar April 1100 1270 1325 1380 July 1550 2 L3d Aug 1530 2 L3d Sept 3 (50.32 KiB) Viewed 43 times
- Jan 980 Table 1 Demand Data May June 1500 L3d Feb Mar April 1100 1270 1325 1380 July 1550 2 L3d Aug 1530 2 L3d Sept 4 (41.85 KiB) Viewed 43 times
For this tutorial, use L3D = 178.
(a) Demand data for an interior decoration contractor is recorded in Table 1. Forecast the demand for month of October using the methods described by i-iv. (i) Naive. (1 mark) (ii) 3-period simple moving average. (1 marks) (iii) 4-period weighted moving average with weightage value of 0.4, 0.3 and 0.2 (highest value for the most recent period). It is a common understanding that the summation of weight factors shall equal to 1. (2 marks) (iv) Exponential smoothing with a = 0.3. Assume the forecast for month of July is 1600 + 2(L3D). (3 marks)
(b) As an industrial engineer, you intend to use linear trend (or linear regression) method to solve a forecasting problem. You have decided to use the equation of y = m(x) + c to establish the relationship between the sales (y) and the related month (x). It is known that 8 consecutive months data (Jan to Aug) were used and they resulted to the following parameter values of m = 150 + L3D and c = 1000+ 0.1(L3D). Using the regression technique, estimate the percentage of sales improvement from December this year to June next year. (3 marks)