---
title: Demand forecasting with the what-if app
description: Discover the problem framing and data management steps required to successfully model for churn, using a B2C retail example and a B2B example based on a DataRobot’s churn model.

---

# Demand forecasting with the what-if app {: #demand-forecasting-with-the-what-if-app }

[Access this AI accelerator on GitHub <span style="vertical-align: sub">:material-arrow-right-circle:{.lg }</span>](https://github.com/datarobot-community/ai-accelerators/tree/main/use_cases_and_horizontal_approaches/Demand_forecasting4_what_if_app/README.md){ .md-button }

This demand forecasting what-if app allows you to adjust certain known in advance variable values to see how changes in those factors might affect the forecasted demand.

Some examples of factors that might be adjusted include marketing promotions, pricing, seasonality, or competitor activity. By using the app to explore different scenarios and adjust key inputs, you can make more accurate predictions about future demand and plan accordingly.

This app is a third installment of a three-part series on demand forecasting. The [first accelerator](https://github.com/datarobot-community/ai-accelerators/tree/main/use_cases_and_horizontal_approaches/Demand_forecasting1_end_to_end/End_to_end_demand_forecasting.ipynb){ target=_blank } focuses on handling common data and modeling challenges, identifies common pitfalls in real-life time series data, and provides helper functions to scale experimentation. The [second accelerator](https://github.com/datarobot-community/ai-accelerators/tree/main/use_cases_and_horizontal_approaches/Demand_forecasting2_cold_start/End_to_end_demand_forecasting_cold_start.ipynb){ target=_blank } provides the building blocks for cold start modeling workflow on series with limited or no history. They can be used as a starting point to create a model deployment for the app.
