liveBook · Manning

Market demand

As explained in Applied Reinforcement Learning

Customer demand is the quantity of products customers request during a specified period, with stochastic demand varying unpredictably over time.

Market demand is the quantity of products customers request during a period. In production planning, stochastic demand varies unpredictably and affects inventory, backorders, and production decisions. section 2.5

Daily factory demand

A scooter-and-bike factory samples daily demand from Poisson distributions, using rates of 4 scooters and 3 bikes. section 2.5

Listing 2.5 Stochastic demand dynamic (Transition function)
def sample_demand(params: FactoryProblemDefinition): #A
    demand_scooter = np.random.poisson(params.lambda_scooter)    #B
    demand_bike = np.random)poisson)params.lambda_bike)    #B
    return demand_scooter, demand_bike

The demand-sampling function shows how random product requests enter the production-planning model. section 2.5

How Applied Reinforcement Learning covers it

How deep it goes
Defines demand through Poisson sampling with product-specific rates and feeds sampled quantities into state transitions.
Examples
Samples scooter and bike demand with Poisson draws using rates of 4.0 and 3.0.
What you can do after
Build it from scratch by sampling daily product demand and incorporating it into production-state transitions.
How it connects
Connects stochastic demand to Markov decision processes, inventory, production planning, and backorders.

Also explained in

Compare how 2 books explain market demand →

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.