Technical paper/Machine learning
Shapley values as an interpretability technique in credit scoring
The authors analyze the usefulness of the Shapley value as a machine learning interpretability technique in credit scoring.
Obtaining arbitrage-free FX implied volatility by variational inference
An ML-based algorithm that provides implied volatilities from bid-ask prices is proposed
Benchmarking machine learning models to predict corporate bankruptcy
Based on a comprehensive sample, the authors benchmark machine learning models in the prediction of financial distress of publicly traded US firms, with gradient-boosted tress outperforming other models in one-year-ahead forecasts.
Sovereign credit risk modeling using machine learning: a novel approach to sovereign credit risk incorporating private sector and sustainability risks
The authors investigate the effect of spillover effects from private sector risks on sovereign debt risk and the impact of rising sustainability risks on sovereign credit risk using the XGBoost classification algorithm and model interpretability…
Momentum transformer: an interpretable deep learning trading model
An attention-based deep learning model for trading is presented
Machine learning for categorization of operational risk events using textual description
The authors summarise ways that machine learning can help categorize textual descriptions of operational loss events into Basel II event types.
Forecasting the loss given default of bank loans with a hybrid multilayer LGD model by extending multidimensional signals
The authors employ signaling theory and machine learning methods to investigate loss given default predictions of commercial banks and propose a method to improve the accuracy of these predictions.
Asset allocation with inverse reinforcement learning
Using reinforcement learning to help replicate asset managers' allocation strategy
Imbalanced data issues in machine learning classifiers: a case study
The author outlines characteristics of machine learning classifiers, compares methods for dealing with imbalanced data issues, and proposes terms of best practice in model development, evaluation, and validation.
Explainable artificial intelligence for credit scoring in banking
The authors put forward an explainable machine learning model predicting credit default using a real-world data set provided by a Norwegian bank.
Alternatives to deep neural networks in finance
Two methods to approximate complex functions in an explainable way are presented
An effective credit rating method for corporate entities using machine learning
The authors propose a new method to design credit risk rating models for corporate entities using a meta-algorithm which exploits information embedded in expert-assigned credit ratings to rank customers.
Exploring the equity–bond relationship in a low-rate environment with unsupervised learning
The authors apply k-means clustering to low interest rate periods in order to analyze the equity hedging property of government bonds.
An end-to-end deep learning approach to credit scoring using CNN + XGBoost on transaction data
The authors find that machine learning methods can generate satisfactorily performing credit score models based on data from the 90-days prior to the score date, where traditional models can perform poorly.
Semi-analytic conditional expectations
A data-driven approach to computing expectations for the pricing and hedging of exotics
Dynamically controlled kernel estimation
An accurate data-driven and model-agnostic method to compute conditional expectations is presented
Customer churn prediction for commercial banks using customer-value-weighted machine learning models
In this paper the authors propose a framework to address the issue of customer churn prediction, and they quantify customer values with the use of an improved customer value model.
Probabilistic machine learning for local volatility
In this paper, the authors propose to approach the calibration problem of local volatility with Bayesian statistics to infer a conditional distribution over functions given observed data.
Multi-horizon forecasting for limit order books
A multi-step path is forecast using deep learning and parallel computing
Forecasting natural gas price trends using random forest and support vector machine classifiers
In this paper, different machine learning approaches are applied to forecasting future yearly price trends in the natural gas Title Transfer Facility market in the Netherlands.
Forecasting consumer credit recovery failure: classification approaches
This study proposes an advanced credit evaluation method for nonperforming consumer loans, which may serve as a new investment opportunity in the post-pandemic era.