Avoiding markdowns

Avoiding markdowns is one of the five fulfillment objectives that Fulfillment Optimizer considers when optimizing orders. When this objective is prioritized, fulfillment decisions are based primarily on preventing markdowns at nodes while still meeting customer expectations. Fulfillment Optimizer analyzes the possibility of a potential future markdown at each node and favors options with the highest probability of one to fulfill the order.

Overview

Fulfillment Optimizer considers the following factors when optimizing orders with a priority of avoiding markdowns:
  • In-store and online sales
  • Future replenishments
  • Markdown plans
  • Inventory availability

The inventory model analyzes the possibility of a markdown at a node, balances the inventory of a SKU at the network level, and selects ship nodes with high probabilities of a markdown. This model is based on the probability and predicted demand of an item. It is calculated for the SKU-ship node combination by using a proprietary algorithm based on feeds of inventory, markdown, TLOG, order, replenishment, and SKU data. The system uses demand predictions to calculate the markdown avoidance cost at the SKU-ship node level.

The markdown avoidance cost represents the amount of money that is gained (a negative cost) by sourcing an order from a ship node. This cost is multiplied by the optimization weight set for the Avoiding markdowns objective before it is factored during optimization. By predicting and ultimately avoiding a markdown, you can obtain markdown avoidance benefits, which are reported in Benefits report.

To avoid markdowns, Fulfillment Optimizer performs the following actions:
  • Learns sell-through patterns by using inventory and sales data to assess the risk of a markdown.
  • Assigns a value to the risk of markdown based on the product's lifecycle stage.
  • Sources SKUs nearing markdown in advance to avoid selling at a low markdown price in the future.
  • Trades off markdown savings against fulfillment costs while it is sourcing orders.

Idle assets or orphaned returns in a store can be modeled as artificial markdowns in your markdown plan.

Example

In a scenario where an order can be shipped from multiple nodes and the Avoiding markdowns objective is prioritized, Fulfillment Optimizer considers a potential markdown to select a ship node. It then optimizes the order so that the initial investment results in larger savings from markdown avoidance.

Table 1. Example of optimizing an order to avoid markdowns
Shipping node Distance between node and destination Shipping cost Processing cost Load-balancing cost Distance penalty Stockout avoidance cost Markdown avoidance cost Total cost of optimization with inventory model Total cost of optimization without inventory model
Node A 891 miles $4.90 $3.50 $.012 $.0032 $0 $42.65 -$34.2379 $8.4154
Node B 221 miles $4.33 $3.25 $.056 $.0009 $0 $.59 $7.0480 $7.6367
  • Total cost of optimization with inventory model = Shipping cost + Processing cost + Load-balancing cost + Distance penalty + Stockout avoidance cost - Markdown avoidance cost
  • Total cost of optimization without inventory model = Shipping cost + Processing cost + Load-balancing cost + Distance penalty

If the inventory model was not used in this example, node B would likely be selected to fulfill the order since it is closer to the destination. However, the inventory model predicts a high possibility of a markdown at node A in the future. The predicted loss due to a markdown at node B is $0.59 compared to $42.65 at node A. To minimize the loss due to a predicted future markdown, node A is selected for shipping. As a result, the total cost of optimization at node A is -$34.2379 as compared with $7.0480 at node B.