Technical paper
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.
Toward a unified implementation of regression Monte Carlo algorithms
The authors put forward a publicly available computational template for machine learning, named mlOSP, which presents a unified numerical implementation of RMC approaches for optimal stopping.
An approach to capital allocation based on mean conditional value-at-risk
The authors put forward a means of Euler capital allocation where the probability level is adjusted such that the total capital is equal to the reference quantile-based capital level.
A robust stochastic volatility model for interest rates
A swaption pricing model based on a single-factor Cheyette model is shown to fit accurately
Throwing green into the mix: how the EU Emissions Trading System impacted the energy mix of French manufacturing firms (2000–16)
This paper investigates links between environmental policy and production decisions, with a focus on firms' energy mixes.
Does the term structure of the at-the-money skew really follow a power law?
A power law can fit the ATM skew, but struggles with short maturities
Using a skewed exponential power mixture for value-at-risk and conditional value-at-risk forecasts to comply with market risk regulation
The authors investigate a method that combines two skewed exponential power distributions and models the conditional forecasting of VaR and CVaR and is in compliance with the recent Basel framework for market risk.
Default forecasting based on a novel group feature selection method for imbalanced data
The authors construct a group feature selection method which combines optimal instance selection with weighted comprehensive precision in an effort to improve the performance of prediction models in relation to defaulting firms.
The realized local volatility surface
The authors put forward a Bayesian nonparametric estimation method which reconstructs a counterfactual generalized Wiener measure from historical price data.
Obtaining arbitrage-free FX implied volatility by variational inference
An ML-based algorithm that provides implied volatilities from bid-ask prices is proposed
A general control variate method for time-changed Lévy processes: an application to options pricing
The authors put forward a novel control variate method for time-changed Lévy models and demonstrate an efficient reduction of the variance of Monte Carlo in numerical experiments.
Sherman ratio optimization: constructing alternative ultrashort sovereign bond portfolios
This paper explores the Sherman ratio and find that it has merit in the optimization of portfolio construction.
Uncovering the hidden impact: noninvestor disagreement and its role in asset pricing
The authors investigate the link between noninvestors and financial returns using data from a social media platform.
The informativeness of risk factor disclosures: estimating the covariance matrix of stock returns using similarity measures
The authors examine 10-K and 10-Q filings for risk factor disclosures and investigate if these disclosures can be used to improve estimations of the covariance matrix of stock returns.
Trading robots and financial markets trading solutions: the role of experimental economics
The authors investigate and summarize experimental studies on automated trading strategies in financial markets.
Modeling the bid and ask prices of options
The authors investigate and partially solve theoretical and empirical problems for the joint modelling of bid and ask prices.
Efficient numerical valuation of European options under the two-asset Kou jump-diffusion model
The authors extend a technique proposed by Toivanen (2008), arriving at an algorithm evaluating the nonlocal double integral appearing in the two-dimensional Kou PIDE and perform several numerical experiments to demonstrate actual convergence behavior…
Sharp L¹-approximation of the log-Heston stochastic differential equation by Euler-type methods
The authors employ Euler-type methods to study the L¹ approximation of the log-Heston stochastic differential equation at equidistant time points.
The factor Heath-Jarrow-Morton term structure
A framework for rates that links real-world and risk-neutral measures is presented
The impact of treasury operations and off-balance-sheet credit business on commercial bank credit risk
Using a vine copula, he authors demonstrate that global systemically important banks face lower credit risk using data from commercial banks based on three risk factors.
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.
Time-varying higher moments, economic policy uncertainty and renminbi exchange rate volatility
The authors investigate how time-varying higher moments and economic policy uncertainty may be used for predicting the renminbi exchange rate volatility.
On capital allocation under information constraints
This paper offers a portfolio optimization framework that uses return data to calculate an optimal capital allocation based on a Cobb–Douglas utility function.
Cyber risk definition and classification for financial risk management
The authors put forward a definition and classification scheme for cyber risk than can be used as a template for data collection by financial institutions.