Technical paper/Machine learning
Interpretability of neural networks: a credit card default model example
Recently developed techniques aimed at answering interpretability issues in neural networks are tested and applied to a retail banking case
An advanced hybrid classification technique for credit risk evaluation
In this paper, the authors employ a hybrid approach to design a practical and effective CRE model based on a deep belief network (DBN) and the K-means method.
Optimal posting of collateral with recurrent neural networks
Pierre Henry-Labordère applies neural networks to a control problem approach for managing collateral
CVA and IM: welcome to the machine
Henry-Labordere proposes a neural networks-based technique to price counterparty risk and initial margin
Global perspectives on operational risk management and practice: a survey by the Institute of Operational Risk (IOR) and the Center for Financial Professionals (CeFPro)
This paper presents survey results which represent comprehensive perspectives on operational risk practice, obtained from practitioners in a wide range of countries and sectors.
Predictive fraud analytics: B-tests
In this paper, the authors look at B-tests: methods by which it is possible to identify internal fraud among employees and partners of the bank at an early stage.
Curve dynamics with artificial neural networks
Artificial neural networks can replace PCA for yield curves analysis
Evolutionary algos for optimising MVA
Alexei Kondratyev and George Giorgidze apply two evolutionary algos to MVA optimisation
Machine learning for trading
Gordon Ritter applies reinforcement learning to dynamic trading strategies with market impact
Model calibration with neural networks
Andres Hernandez presents a neural network approach to speed up model calibration