causaLens logocausaLens logo alternate

Demand Planning with Causal AI

Plan with confidence, empowered by Causal AI

laptop screen

Demand planning challenges:

  • Point forecasts, not expressing the uncertain, probabilistic nature of outcomes.
  • Process dominated by amalgamating biased forecasts: either those that are human-dominated (e.g. sales/ customer forecasts) or completely devoid of human intelligence (statistical or ML approaches)
  • Largely limited to internally-gathered data – blind to indicators impacting demand found outside the enterprise.
  • Limited understanding of the true causes of demand – impeding counterfactual or what-if analyses that can simulate how external forces or internal actions can impact demand

There’s a better way to understand what is really driving demand:

causaLens’ Demand Planning solution

Strategic planners, meet Causal AI

For the first time, P&L leaders, supply chain strategists, and demand planners can understand what is driving their company’s demand, allowing them to better prepare for shifts in macro conditions while optimizing their own demand-gen activities.

Explainable AI

Understand key drivers of demand.

Probabilistic forecasting

See the uncertainty in your demand forecasts and plan for optimistic and pessimistic market scenarios.

Scenario-based investigation of macro conditions

Simulate discrete scenarios in the macro environment to pressure-test your plans.

Scenario-based investigation of internal levers

Understand the impact that different internal strategies (trade spend, marketing spend, distribution expansion, etc.) have on demand.

Human-guided causal discovery

As underlying conditions change, domain experts can modify causal relationships that shape predicted outcomes.

Early warning system

The detection system identifies when external factors move outside of normal bounds, to notify data scientists to re-calibrate models.

Incorporating external indicators

Relying solely on internally-gathered data is no longer an option for forecasting your company’s demand. causaLen’s signal testing and causal discovery algorithms can search across a vast catalog of public and pay-walled datasets to identify the external data signals that are most relevant for your product portfolio across the different forecasting horizons, whether that be weather, competitive activity, or currency fluctuations in the short term, economic and consumer sentiment indicators in the medium term, or raw material prices and interest rate fluctuations in the long term.

causaLens’ Demand Planning application can then incorporate these external leading indicators into its forecasting engine while also allowing planners to simulate how demand changes when these external indicators shift.

5 steps to prepare for AI regulations

Causality-based Decision Intelligence for Demand Planning Teams

Get a demo

Build robust models with causal discovery

Forecasts based on standard machine learning techniques only extrapolate from historical trends. It is easy for these techniques to build forecasting engines based on historical correlations, as these correlations are found everywhere. However, building models based on these correlative relationships – which tend to be fleeting, continually ebbing and flowing–results in fragile models that don’t perform well when deployed in the real world.

Instead, causaLens uses Causal AI to uncover the true drivers of demand to create predictive causal demand models. These models are robust, autonomously adapting up to three times faster than current state-of-the-art machine learning under regime shifts.

Add domain knowledge to your forecasts

Human + Causal AI

Forecasting should never be left entirely to machines. Yet the backward-looking, black-box ML techniques do not allow for humans to input their knowledge.

Real-life expertise is essential when assessing how the future might deviate from historical patterns. Causal AI explicitly allows for the infusion of such specialized knowledge.

  • Are you planning a large increase in your R&D budget?
  • Have plans with channel partners to increase distribution in certain markets?

Strategic planners can now intervene and model new causal relationships, or simulate what would happen if historical patterns were to change.  

How different teams use decisionOS

Business teams, software developers, and data scientists can work as one team on deploying robust and compliant demand planning models. 


Inspect models to ensure they are aligned with business logic.


Easily connect the app to internal systems


Build powerful, robust, and compliant models

More Solutions