1. How does L.L. Bean use past demand data and a specific item forecast to decide how many units of that item to stock?

Based on the book forecast and past demand data, L.L. Bean calculates a point forecast for the item in the future period. Then, actual demand / forecast ratio is calculated to forecast the range of inventory of the item. The last step in forecasting demand is finding the service level based on a profit margin calculation. Since L.L. Bean wants to compare the probability of each unit of item bought and the loss generated from liquidating, L.L. Bean calculates a fractile for the items since the fractile calculation indicates what point is optimal to hold the stock in order to balance overstocking and understocking costs, which then determines the number of units to stock.

2. What item costs and revenues are relevant to the decision of how many units of that item to stock?

The cost of the item for L.L. Bean and the price at which they can sell the item are the two factors that are relevant in determining how many units of an item should be stocked. L.L. Bean can, then, calculate the profit margin by subtracting item’s costs from the selling price. The profit margin relates to the cost of understocking. Thus, subtracting liquidation value from the original cost of the item gives the loss for failing to sell that item, which also means overstocking an item. Additional cost associated with overstocking is the annual holding time of their facility when they keep inventory for the next year.

3. What information should Scott Sklar has available to help him arrive at a demand forecast for a particular style of men’s shirts that is a new catalog item?

Since Scott Sklar is unable to look at historical data for this particular item, he needs all the past data related to new items along with forecasted demand and the actual demand to discover any possible trends. Additionally, he needs the data for the whole industry and the demand for when they offer similar products. For example, Scott Sklar would need the data from when the competitors released the similar item to expect the demand for that new item. The data from L.L. Bean and it’s competitors will help Scott to have an idea of what the demand will be and how to react upon the change. Moreover, Scott would need to do profit margin analysis and liquidation value of the item to calculate the overstocking and understocking costs.

4. How would you address Mark Fasold’s concern that the number of items purchased usually exceeds the number forecast?

I think the example in the case study would help in this situation. Let us say that the profit margin on an item is $15, which is the understocking cost. The overstocking cost, which we calculate by subtracting the liquidation value from the cost of item, is $5. If the forecasted demand is 1,000 items and they order 1,300, the cost of making $4,500 is greater than the risk of losing $1,500 on the additional items bought. Consequently, it costs less for L.L. Bean to liquidate an item.

5. What should L.L. Bean do to improve its forecasting process?

L.L. Bean should hire someone who can just analyze the demand because Scott Sklar does not seem to suit well for forecasting demand. However, forecasting is a huge issue within the company because L.L. Bean’s lead time is eight to twelve weeks. Having a long lead time, more accurate forecast would make the company more profitable. Consequently, L.L. Bean should make their suppliers have facilities close to them to support L.L. Bean’s whole supply chain by adding some make-to-order components into their make-to-stock business model.