Pricing Engine

To optimize revenues and reduce waste, Wasteless’s pricing engine employs a branch of machine learning called «Reinforcement Learning». This allows our engine to quickly learn how consumers respond to dynamic pricing so it can then find the optimal discounting policy.

Pricing perishables is inherently a dynamic decision.

If a retailer chooses low prices today, inventory will sell faster, but there might not be enough left for future periods. On the other hand, if prices are set high, the retailer sells less now, but carries over more inventory to the next period. Dynamic programming is a mathematical technique developed in order to solve these types of problems.

Wasteless uses state-of-the-art methods to solve high dimensional dynamic programming problems, and automatically map inventory stock and time of day into a series of optimal prices.

However, before it is possible to solve these problems, our statisticians and economists must have knowledge of various parameters.

For example,

How exactly do consumers trade off freshness (expiration date) with discounts?

How do consumers respond when there is little inventory left on the shelf?

When is the next shipment of inventory set to arrive?

How many units does it include, and at what cost?

What are the relations between products, which products are an alternative to one another?

Clearly, the answers to these questions will determine the optimal set of discounts implemented by Wasteless.

Static pricing

Singlee price points

Revenue

Dynamic pricing

Multiple price points

1 2 3 4 5

Profit