liveBook · Manning

Demand function

As explained in Delivering Machine Learning Projects: From design to deployment

A demand model predicts the quantity or likelihood of demand for a product, service, or activity under specified conditions.

A demand function estimates how much demand a product, service, or activity will receive under specified conditions. In practice, demand models turn available signals into a prediction that supports a business decision. section 6.6.1

Frame a demand-modeling task by:

  • Selecting conditions that may change demand, such as forecast weather. section 6.6.1
  • Placing the forecast before the prediction so the result can guide an anticipated customer response. section 6.6.1
  • Connecting the predicted behavior to an operational question, such as whether customers will cycle or take buses. section 6.6.1

Weather-sensitive travel demand

Use a weather forecast to estimate whether customers will want to cycle or shelter from rain by taking buses. This turns a forecast into a demand-prediction requirement. section 6.6.1

How Delivering Machine Learning Projects: From design to deployment covers it

How deep it goes
Connects forecast timing and customer behavior to model requirements but specifies no algorithm, formula, or evaluation metric.
Examples
Uses forecast weather to distinguish cycling demand from bus travel.
What you can do after
Apply it by converting forecast conditions into a concrete demand-prediction requirement.
How it connects
Connects weather forecasts, customer behavior, demand prediction, and sales prediction.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Delivering Machine Learning Projects: From design to deployment. The section links point to the parts of the book it draws on.