Broadband activation forecasting.
A predictive model to estimate broadband activations one year ahead, supporting a nationwide service launch across 8,000 municipalities.
Anticipate demand, municipality by municipality.
Launching a broadband service nationwide means deciding where to focus investment and commercial activity before demand materialises. An aggregate forecast is not enough: municipalities have different demographics, market conditions and responses to campaigns. The project addressed this complexity with activation estimates at municipal level over a one-year horizon.
- Forecasting
- Multivariable models
- Commercial planning
What we designed.
The challenge calls for commercial signals, demographics and advertising activity to be combined in a dedicated predictive model. Local detail makes the estimates useful for launch decisions and investment allocation.
Connect territories and channels
The model combines demographic and market data with signals from web, retail and call-centre channels. Reading these variables together represents potential demand in the context of each municipality.
Model future activations
A multivariable forecasting system estimates future activations, considering local characteristics and the impact of TV campaigns and local advertising. Forecasting brings national launch planning down to municipal detail.
Inform commercial decisions
The estimates provide a quantitative basis for setting territorial priorities and planning marketing and sales activity. Expected demand distribution helps assess where to invest and where to limit the risk of over- or under-investment.
Territory, channel and campaign data
One-year multivariable forecasting
Activation estimates by municipality
What it makespossible.
- Municipal forecasts supporting a launch across 8,000 municipalities.
- A quantitative basis for planning marketing and sales one year ahead.
- Support for assessing the risk of investing too much or too little across territories.
Want to forecast demand before deciding where to invest?
Let’s start with your context, available data and the first useful outcome.
Tell us about your project
PPE and procedure checks with computer vision.
Deep-learning video analysis to support safety checks in electrical substations: protective equipment and observable steps in operating procedures.