Cutting Edge is the quantitative finance section of Risk.net. It publishes exclusive peer-reviewed papers selected for their originality, relevance and applicability to financial markets. It also publishes podcasts with leading quants on the most topical issues, and comments from practitioners and our editorial team.
No single approach to interpreting a neural network’s outputs is perfect, so it’s better to use them all
Recently developed techniques aimed at answering interpretability issues in neural networks are tested and applied to a retail banking case
Market generator models may aid areas of finance where data is limited or sensitive