EV charging Location-Based Price Optimisation
This challenge is about building a pricing engine that sets optimised prices for charging sessions at each location. The goal is to maximise short-term profit. The price should capture local demand as effectively as possible, while still offering fair prices to encourage EV adoption and shifting consumption to off-peak times.
Challenge Owner
Postdate 28.07.2026
Energy
Data
Description
On the cost side, grid and electricity prices per kWh matter most, and these vary depending on location and grid operator. The price should be adjustable dynamically, both by location and by day.
It's up to the participants themselves to figure out which factors really drive the optimal price (utilisation, time of day, weather, electricity price, and location characteristics are just a few examples) and how often an adjustment actually makes sense.
The end result should be a solution that increases short-term profit per location through dynamic price optimisation by weighing cost factors (grid and electricity prices) against local demand behaviour.
Specifically, we expect a model or pricing engine that calculates an optimised, dynamic price for each location and provides a clear rationale for it, for example through a dashboard or a visualisation of the pricing logic.
Impact
Location-specific, dynamic price optimisation helps manage the trade-off between price and demand (price elasticity) in a targeted way, increasing profit per location. This creates a data-driven basis for pricing decisions and enables flexible responses to local differences in cost structures and demand behaviour.
At the same time, we still want to offer fair prices to encourage EV adoption, and encourage consumption at off-peak times, avoiding congestion and helping stabilize the grid.
Data Set
Needed Skills
- Price modelling/optimisation
- Data analysis
- Statistics/machine learning (demand forecasting)
- Visualisation/dashboard development
- Basic understanding of energy markets and cost structures is a plus