liveBook · Manning

Perishable product

As explained in Applied Reinforcement Learning

A perishable product is a product whose value declines substantially or becomes zero after a limited shelf life or deadline.

A perishable product loses value or becomes worthless after a limited selling window. Fresh bread, flight tickets, hotel rooms for a particular night, and seasonal clothing all face a deadline. section 3.3

Pricing such products means balancing price against uncertain demand and finite inventory: prices that are too high can leave stock unsold, while prices that are too low can sell it out prematurely. section 3.3

Table 3.2 Elements of Markov decision process for perishable dynamic pricing
Markov decision process elements
Definitions
State
How many sales periods are left.
How many items are left to sell.
Action
The agent chooses a price from a predefined list, e.g., [8, 10, 12, 15, 18].
Reward
Calculated as the revenue from sales in that period.
Penalty if items remain unsold after the last period.
Transition Dynamics
Demand drops as the price increases (price sensitivity).
Demand slightly increases over time due to urgency (people rush to buy near the end).
Random noise is added to simulate uncertainty.

The Markov decision process table maps the pricing problem to time and inventory states, price actions, sales rewards, and uncertain demand. section 3.3

Fresh bread

A bakery must sell its daily bread before it goes stale. It can adjust prices over the day as demand unfolds, aiming to earn revenue while avoiding unsold stock. section 3.3

How Applied Reinforcement Learning covers it

How deep it goes
Models pricing with time and inventory states, price actions, sales rewards, and stochastic demand, while abstracting away domain-specific complexities.
Examples
Uses fresh bread, flight tickets, hotel rooms, seasonal fashion, strawberries, and tacos to illustrate perishability and demand.
What you can do after
Build a simplified dynamic pricing environment with finite inventory, selling periods, price choices, and uncertain demand.
How it connects
Connects dynamic pricing and reinforcement learning with Markov decision processes, demand, and inventory.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Applied Reinforcement Learning. The section links point to the parts of the book it draws on.