Our AI-generated summary
Our AI-generated summary
In a rapidly electrifying mobility landscape, Charge Point Operators (CPOs) are racing to meet surging demand for EV infrastructure. For one European CPO, this meant deploying over 7,000 public Electric Vehicle Charging Stations (EVCS) across three countries by 2028—a bold target hindered by a highly manual and fragmented site selection process.
The challenge was clear: despite the commercial team's deep market knowledge and on-the-ground scouting, the existing workflows lacked automation, scalability, and consistent data-driven rigor. Location scouting occurred via three disconnected channels: proactive screening of new areas, field-driven insights from commercial agents, and batch evaluations for public tenders—each relying on empirical judgment and siloed data.
“The real blocker wasn’t lack of experience—it was lack of integration. Disconnected scouting channels and scattered data turned every location assessment into a time-consuming gamble.”
Site assessments depended heavily on heuristics, with scattered data sources such as maps of the electric grid and road network, and evidence from site visits. The criteria used to score potential sites were often subjective, limiting comparability, while the heuristic demand projections lacked temporal granularity, preventing optimized charger-type placement or accurate peak-time forecasting.
To achieve its growth ambitions, the CPO needed a scalable, analytical, and centralized solution to evaluate new charging sites based on hard data and predictive insights—streamlining decisions while maximizing return on infrastructure investments.
We partnered with the CPO to design and implement a Location Intelligence platform that transforms how expansion decisions are made. At its core, the solution consolidates diverse datasets into a single, intuitive, map-based interface—enabling the business development team to explore, compare, and score locations with precision, all while being able to share results within and outside the team in a standard format.
The platform ingests data from multiple sources:
- Socio-demographic indicators (population density, income levels, education)
- Vehicle characteristics (fleet size, fuel type, vehicle age)
- Buildings data (building types, height, residential vs. commercial)
- POIs and mobility drivers (retail areas, workplaces, amenities)
- Grid connectivity (proximity to substations)
- Zoning and land-use data
“From scattered spreadsheets to a single sourceof truth: the new platform empowered teams to simulate, score, and select locations in one unified interface.”
The solution supports three core use cases tailored to the CPO’s operating model:
- A. Region Characterization – Compare geographies across key metrics to identify high-potential regions for future deployment.
- B. Location Attractiveness Scoring – Rank sites with a multi-criteria scoring model defined based on the team’s business knowledge, balancing infrastructure costs, the competition landscape, and key drivers of demand.
- C. Occupancy Prediction – Estimate charger usage and energy sales (kWh) with Machine Learning predictive models, enabling granular economic viability analysis.
Each use case is powered by robust analytics and customizable inputs. Commercial teams can simulate various charger configurations and predict sales by site—aligning operational decisions with financial targets.
We delivered a custom web application with a responsive, user-friendly interface that democratizes data access and insights across the organization. Key features include:
- A centralized platform replacing fragmented workflows
- Visual heatmaps for opportunity spotting
- Dynamic filters to tailor site comparisons
- Integration with predictive models for occupancy and sales forecasting
- Exportable reports for fast decision-making and stakeholder alignment
Importantly, the platform accommodates all three scouting workflows—screening, field scouting, and public tender assessments—ensuring it supports both proactive and reactive strategies.
Our solution is built on a robust and secure infrastructure designed to ensure seamless operations at scale. The system features a high-performance GIS data base that securely stores and manages all relevant data. The backend serves as an intermediary between the frontend and the database through API requests, enhancing security by isolating the two components and optimizing performance by separating data processing from visualization. With the integration of AIR (LTP’s orchestrator), the backend processes user inputs from the frontend to trigger the analytical models, enabling on-demand testing of new locations. This setup guarantees fast performance and enterprise-level security, allowing the team to make data-driven decisions with confidence and without delay.
The Location Intelligence tool became a core asset in the CPO’s growth engine, greatly increasing their capacity to evaluate new locations while dramatically reducing time spent on manual analysis. At the same time, the performance of the new sales forecasts presented a significant improvement relative to the previous method, increasing confidence to move for new investments.
“With better forecasting, faster decisions, and standardized scoring, the CPO unlocked not just speed—but smarter, more profitable growth.”
By automating previously empirical and siloed tasks, the solution unlocked:
- A standardized process for location scoring and benchmarking
- Faster decision cycles for both organic growth and competitive bids
- Improved forecasting accuracy, optimizing charger mix per location
- Greater scalability, supporting long-term expansion into new markets
With a strategic, data-driven approach now embedded in their operations, the CPO is better positioned to lead the EV transition—ensuring infrastructure investments are not only faster to deploy but smarter, more efficient, and better aligned with real-world demand.