Instead of using broad national trends, the platform uses synthetic populations to simulate individual household behaviors. By analyzing micro-demographics—such as housing type (off-street parking availability), income levels, and typical commuting patterns—the AI identifies which specific streets or boroughs are most likely to switch to electric vehicles first.

The forecasting model considers a variety of correlated attributes, including:

• Infrastructure Access: Proximity to existing charging points and the ability to install home chargers.

• Economic Factors: Household income and the impact of government tax benefits or subsidies.

• Environmental Sentiment: The likelihood of a demographic to prioritize sustainability based on behavioral data.

• Vehicle Segments: Preferences for specific EV types (e.g., SUVs vs. compact city cars) based on family size and location.

The data helps stakeholders optimize the placement of charging stations by highlighting "demand hotspots." By knowing where adoption will be highest, energy providers and local councils can allocate resources to upgrade the electrical grid and install chargers exactly where they will be needed, preventing future bottlenecks.

Yes. One of the primary uses of the forecasting tool is "What-If" scenario testing. Users can adjust variables—such as an increase in EV subsidies or a new low-emission zone (like the ULEZ)—to see how these interventions would accelerate or change the adoption timeline within a specific London borough.

Traditional forecasting often relies on static surveys or past sales data, which can be outdated or biased. Synthetic Gen’s approach uses Dynamic Synthetic Generation, which constantly evolves based on changing micro-demographics. This creates a "live" replica of the population that reacts to real-time changes in technology costs and infrastructure development, providing a more robust prediction of future demand.