So looking at what we have done we have that the model with less MSE is the Winter model with values 0,010822507 so it has more accurate forecast.
The MAD; In our assignment the model with less MAD is the winter model with values 0,255404724 or 0,094942726, that’s mean that the model with less MAD is more accurate forecast.
The MAPE is generally not affected by the magnitude of the demand values, because is expressed as a percentage. But it is not appropriate for very low demand values.
To calculate the MAPE you must take the sum of the ratios between forecast error and actual demand times 100 (to get the percentage) and divide by N.
Focusing on the errors we can say that the winter model is the one with less error so because of that reason we choose the winters model.
2.1) Formulate the single item dynamic lot sizing problem for the Hyundai automobile company using the given data.
Number of order policies X = 5 (i.e. x = 0, 1, 2, 3 and …show more content…
Spreadsheet question 3
3) Consider a Class A item. Describe briefly an appropriate inventory model design for this item.
Class A items (like Spring Valley in our case) are defined to be the most important products in a whole company. That is, the total costs replenishment, carrying stock, and shortages associated with such an item are high enough to justify a more sophisticated and rigorous control system.
The potentially high payoff warrants frequent managerial attention to the replenishment decisions of individual items. However, decision rules, based on mathematical models, do have a place in aiding manager. The art of management is very evident in this type of activity.
Below that, it’s exposed the particular characteristics to design an A class item inventory:
1. Inventory records should be maintained on a transactions recording basis, particulary for the more expensive items. 2. Top management should be kept informed, using frequent reports to senior management for careful review. 3. Demand and supply should be estimated and influenced, providing manual input to forecasts, ascertining the predictability of demand or manipulating a given demand