ExtremeXP proposes a new paradigm for data analytics

This paradigm consists of experimentation-driven analytics, to provide accurate, precise, fit-for-purpose, and trustworthy data-driven insights via evaluating different complex analytics variants, considering end users’ preferences and feedback in an automated way.


The ambition is to provide capabilities for learning from experimentation to predict user requirements, profiling the user, and proactively generating the accurate analytics workflow towards more precise outcomes and personalized insights for decision making and focusing on the user experience, requirements, and needs and putting him in the center of the decision-making process.


ExtremeXP will integrate cutting-edge research results from the domains of data integration, machine learning, visual analytics, explainable AI, decentralized trust, knowledge engineering, and model-driven engineering into a common framework.

Latest News :

Key Features

A human-centered approach to AI and data driven analytics

A human-centered approach to AI and data driven analytics

ExtremeXP puts the end user, i.e., requirements, preferences, constraints, interpretation, explanations, feedback, and decision making, at the center of the decision-making process

Experimentation is the core concept for generating extremely accurate analytics

Experimentation is the core concept for generating extremely accurate analytics

ExtremeXP will provide capabilities for learning from experimentation to predict user requirements, profiling the user and proactively generating the accurate analytics workflow towards more precise outcomes and personalised insights for decision making.

User-driven Optimization of Complex Analytics

User-driven Optimization of Complex Analytics

The main, overarching idea of the ExtremeXP framework is to optimize the properties of a complex analytics process that the end user cares about (e.g., accuracy, time-to-answer, specificity, recall, precision, and resource consumption) by associating user profiles to computation variants.

The ExtremeXP project is co-funded by the European Union Horizon Program HORIZON-CL4-2022-DATA-01-01, under Grant Agreement No. 101093164
© ExtremeXP 2023. All Rights Reserved – Privacy Policy