Technical paper/Neural networks
Research on the multifractal volatility of Chinese banks based on the synthetic minority oversampling technique, edited nearest neighbors and long short-term memory
The authors propose the SMOTEENN-LSTM method to predict risk warnings for Chinese banks, demonstrating the improved performance of their model relative to commonly used methods.
Neural stochastic differential equations for conditional time series generation using the Signature-Wasserstein-1 metric
Using conditional neural stochastic differential equations, the authors propose a means to improve the efficiency of generative adversarial networks and test their model against other classical approaches.
An optimal control strategy for execution of large stock orders using long short-term memory networks
Using a general power law in the Almgren and Chriss model and real data, the authors simulate the execution of a large stock order with an appropriately trained LSTM network.
Robust pricing and hedging via neural stochastic differential equations
The authors propose a model called neural SDE and demonstrate how this model can make it possible to find robust bounds for the prices of derivatives and the corresponding hedging strategies.
Alternatives to deep neural networks in finance
Two methods to approximate complex functions in an explainable way are presented
Deep learning for efficient frontier calculation in finance
The author puts forward a means to calculate the efficient frontier in the Mean-Variance and Mean-CVaR portfolio optimization problems using deep neural network algorithms.
Technical indicator selection and trading signal forecasting: varying input window length and forecast horizon for the Pakistan Stock Exchange
This paper investigates how input window length and forecast horizon affect the predictive performance of a trading signal prediction system.
Pricing barrier options with deep backward stochastic differential equation methods
This paper presents a novel and direct approach to solving boundary- and final-value problems, corresponding to barrier options, using forward pathwise deep learning and forward–backward stochastic differential equations.
Predicting financial distress of Chinese listed companies using a novel hybrid model framework with an imbalanced-data perspective
In this paper a novel hybrid model framework is constructed to solve the problem of predicting the financial distress of Chinese listed companies using imbalanced data.
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.
Covariance estimation for risk-based portfolio optimization: an integrated approach
This paper presents a stochastic optimization framework for integrating time-varying factor covariance models in a risk-based portfolio optimization setting.
Multi-horizon forecasting for limit order books
A multi-step path is forecast using deep learning and parallel computing
An artificial neural network representation of the SABR stochastic volatility model
In this paper the universal approximation theorem of artificial neural networks (ANNs) is applied to the stochastic alpha beta rho (SABR) stochastic volatility model in order to construct highly efficient representations.
Deep learning profit and loss
The P&L distribution of a complex derivatives portfolio is computed via deep learning
Comprehensive Capital Analysis and Review consistent yield curve stress testing: from Nelson–Siegel to machine learning
This paper develops different techniques for interpreting yield curve scenarios generated from the FRB’s annual CCAR review.
Axes that matter: PCA with a difference
Differential PCA is introduced to reduce the dimensionality in derivative pricing problems
Deep learning for discrete-time hedging in incomplete markets
This paper presents several algorithms based on machine learning to solve hedging problems in incomplete markets.
An interpretable Comprehensive Capital Analysis and Review (CCAR) neural network model for portfolio loss forecasting and stress testing
This paper proposes an interpretable nonlinear neural network model that translates business regulatory requirements into model constraints.
Generating financial markets with signatures
Signatures can provide the synthetic data to train deep hedging strategies
Nowcasting networks
The authors devise a neural network-based compression/completion methodology for financial nowcasting.
Neural network middle-term probabilistic forecasting of daily power consumption
The authors propose a new modeling approach that incorporates trend, seasonality and weather conditions as explicative variables in a shallow neural network with an autoregressive feature.