Our work demonstrates the limitations of Big Data in the field of customer knowledge. It has paved the way for new research avenues on Machine Learning, especially Preference Learning. Applied to target marketing, this analytical technique makes it possible to characterize profit-generating customers and can be extended to other fields (health, etc.).
Our research work is focusing on developing solutions to improve the evaluation metrics of interpretability models in terms of plausibility and fidelity. The design of robust substitution models against adversarial attacks. The generation of adversarial attacks and suitable counterfactuals, which are especially difficult for NLP applications, to eventually optimize the interpretability of AI algorithms.
Our research work aims to develop innovative statistical and mathematical models contributing the modelling of the impact of climate and transition risks on the solvency of banks and on the calculation of their capital needs to cover the risks induced by climate change.
