AI-Based Optimisation of Incentive Schemes for Sustainable Mobility

The AI-CENTIVE project advances the state of the art in AI research to build and manage a complex mobility data ecosystem as enabler of intelligent applications in the context of ICT for the Future. The core innovations of AI-CENTIVE aim to support and incentivise mobility behaviour towards choosing more sustainable options, thus reducing carbon emissions from the use of private cars and petrol-/diesel-based means of transportation. Actionable datasets on mobility choices and options are currently fragmented across data silos in different organisational networks. The sharing and merging of these datasets via a common data ecosystem and its processing by Intelligent Systems - allowing for data sovereignty, security and privacy - supports the training of AI models to explain how and why citizens make certain mobility choices, and to predict their future choices based on multidimensional context parameters such as the weather, the location and duration of upcoming events or the availability of environmentally friendly options. Customised incentives leveraging AI predictions aim to motivate citizens to adopt those new options and overcome remaining barriers to more sustainable behaviour such as the need to sign up for a new service or the perceived convenience of travelling “as we have always done”. To achieve this, we need AI-based approaches to predict complex mobility behaviour and optimise incentives in a multidimensional manner, beyond currently available solutions. The project’s unique selling proposition stems from concurrently addressing a number of challenges: (i) semantically integrating heterogeneous data from multiple sources into a dynamic mobility data ecosystem; (ii) understanding the evolving data ecosystem by means of a shared mobility knowledge graph; (iii) graph-based AI algorithms to learn from user mobility behaviour and make predictions of future behaviour and propose suitable incentives, and (iv) modelling different user mobility choices based on various incentive models in order to promote the most sustainable mobility behaviour. We will make sure that our predictions are explainable and understandable so that stakeholders can make informed decisions to promote and support more sustainable behaviour in the future, thoroughly testing the results to verify and improve the approach. The results of the project will enable and incentivise Austrian citizens to find more sustainable mobility choices, increasing awareness and affecting public opinion to develop a more positive attitude towards those choices. The deployment of AI-CENTIVE algorithms as part of (i) the existing “ummadum” public mobile application to incentivise sustainable mobility choices as well as (ii) a visual analytics dashboard for professional stakeholders’ decision making will increase the visibility and uptake of project results across different target groups and guide the path to post-project exploitation.