Explore all papers

5,749 papers

The filter tools did not load, so your filters are not applied: the list below is the plain, unfiltered list of papers.

Skip to results

LLM-Generated Counterfactual Stress Scenarios for Portfolio Risk Simulation via Hybrid Prompt-RAG Pipeline

Soleimani

We develop a transparent and fully auditable LLM-based pipeline for macro-financial stress testing, combining structured prompting with optional retrieval of country fundamentals and news. The system generates machine-readable macroeconomic scenarios for the G7, which cover GDP growth, inflation…

Street Traders Math 3.5 Rigor 8.0
Costs: Not applicableOut-of-sample: NoneResolution: Daily Data
More details
Evaluation
Unclear

Portfolio Optimization via Transfer Learning

Wang et al.

Recognizing that asset markets generally exhibit shared informational characteristics, we develop a portfolio strategy based on transfer learning that leverages cross-market information to enhance the investment performance in the market of interest by forward validation. Our strategy…

Holy Grail Math 7.5 Rigor 6.0 capped
Costs: Not modeledOut-of-sample: Walk-forwardResolution: Daily Data
More details
Authors
Kexin Wang, Xiaomeng Zhang, Xinyu Zhang
Evaluation
Trading P&L

Quantum Network of Assets (QNA): A Density-Operator Framework for Market Dependence and Structural Risk Diagnostics

Gong et al.

Classical correlation and rolling PCA summarize market dependence through covariance spectra, but they do not provide a unified operator representation for entropy, purity-based mixing, and standardized structural deviations built from rolling multi-feature trajectories. We propose the Quantum…

Holy Grail Math 6.5 Rigor 7.0
Costs: Not applicableOut-of-sample: NoneResolution: Daily Data
More details
Authors
Hui Gong, Akash Sedai, Francesca Medda
Evaluation
Unclear

Standardized Threat Taxonomy for AI Security, Governance, and Regulatory Compliance

Huwyler

The accelerating deployment of artificial intelligence systems across regulated sectors has exposed critical fragmentation in risk assessment methodologies. A significant "language barrier" currently separates technical security teams, who focus on algorithmic vulnerabilities (e.g., MITRE ATLAS)…

Street Traders Math 2.5 Rigor 6.0 Code

Constrained deep learning for pricing and hedging european options in incomplete markets

Baradel

In incomplete financial markets, pricing and hedging European options lack a unique no-arbitrage solution due to unhedgeable risks. This paper introduces a constrained deep learning approach to determine option prices and hedging strategies that minimize the Profit and Loss (P&L) distribution…

Lab Rats Math 8.0 Rigor 4.0
Costs: UnclearOut-of-sample: HoldoutResolution: Synthetic Data
More details
Evaluation
Pricing / calibration

Efficient Importance Sampling under Heston Model: Short Maturity and Deep Out-of-the-Money Options

Tu et al.

This paper investigates asymptotically optimal importance sampling (IS) schemes for pricing European call options under the Heston stochastic volatility model. We focus on two distinct rare-event regimes where standard Monte Carlo methods suffer from significant variance deterioration: the limit as…

Lab Rats Math 9.0 Rigor 3.0
Costs: Not applicableOut-of-sample: NoneResolution: Synthetic Data
More details
Authors
Yun-Feng Tu, Chuan-Hsiang Han
Evaluation
Pricing / calibration

Carbon-Penalised Portfolio Insurance Strategies in a Stochastic Factor Model with Partial Information

Colaneri et al.

Given the increasing importance of environmental, social and governance (ESG) factors, particularly carbon emissions, we investigate optimal proportional portfolio insurance (PPI) strategies accounting for carbon footprint reduction. PPI strategies enable investors to mitigate downside risk while…

Lab Rats Math 8.5 Rigor 3.0
More details
Authors
Katia Colaneri, Federico D’Amario, Daniele Mancinelli

Diagram-to-Circuit QNLP for Financial Sentiment Analysis

Sakuma

We study a \emph{QDisCoCirc}-inspired, chunked diagram-to-circuit quantum natural language processing (QNLP) model for three-class sentiment classification of financial texts. In our classical simulations, we keep the Hilbert-space dimension manageable by decomposing each sentence into short…

Holy Grail Math 5.5 Rigor 5.0
Costs: Not applicableOut-of-sample: HoldoutResolution: Unclear
More details
Evaluation
Forecast accuracy

Optimal dividend and capital injection under self-exciting claims

Aubert et al.

In this paper, we study an optimal dividend and capital-injection problem in a Cramér–Lundberg model where claim arrivals follow a Hawkes process, capturing clustering effects often observed in insurance portfolios. We establish key analytical properties of the value function and characterise the…

Lab Rats Math 8.5 Rigor 3.0
More details
Authors
Paulin Aubert, Etienne Chevalier, Vathana Ly Vath

A calibrated model of debt recycling with interest costs and tax shields: viability under different fiscal regimes and jurisdictions

Osten et al.

Debt recycling is a leveraged equity management strategy in which homeowners use accumulated home equity to finance investments, applying the resulting returns to accelerate mortgage repayment. We propose a novel framework to model equity and mortgage dynamics in presence of mortgage interest…

Holy Grail Math 6.5 Rigor 6.5
More details
Authors
Carlo von der Osten, Sabrina Aufiero, Pierpaolo Vivo, Fabio Caccioli, Silvia Bartolucci

Re(Visiting) Time Series Foundation Models in Finance

Rahimikia et al.

Financial time series forecasting is central to trading, portfolio optimization, and risk management, yet it remains challenging due to noisy, non-stationary, and heterogeneous data. Recent advances in time series foundation models (TSFMs), inspired by large language models, offer a new paradigm…

Holy Grail Math 6.0 Rigor 8.5
Costs: ModeledOut-of-sample: Walk-forwardResolution: Daily Data
More details
Authors
Eghbal Rahimikia, Hao Ni, Weiguan Wang
More data sources
JKP Global Factor Data
Evaluation
Trading P&L

A multi-view contrastive learning framework for spatial embeddings in risk modelling

Holvoet et al.

Incorporating spatial information, particularly those influenced by climate, weather, and demographic factors, is crucial for improving underwriting precision and enhancing risk management in insurance. However, spatial data are often unstructured, high-dimensional, and difficult to integrate into…

Holy Grail Math 6.0 Rigor 8.0 Code
Costs: Not applicableOut-of-sample: HoldoutResolution: Unclear
More details
Authors
Freek Holvoet, Christopher Blier-Wong, Katrien Antonio
Evaluation
Forecast accuracy

Arbitrage-Free Bond and Yield Curve Forecasting with Neural Filters under HJM Constraints

Gao et al.

We develop an arbitrage-free deep learning framework for yield curve and bond price forecasting based on the Heath-Jarrow-Morton (HJM) term-structure model and a dynamic Nelson-Siegel parameterization of forward rates. Our approach embeds a no-arbitrage drift restriction into a neural state-space…

Holy Grail Math 9.2 Rigor 7.5
Costs: Not applicableOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Xiang Gao, Cody Hyndman
Evaluation
Forecast accuracy

Diffusive Limit of Hawkes Driven Order Book Dynamics With Liquidity Migration

Mahseredjian

This paper develops a theoretical mesoscopic model of the limit order book driven by multivariate Hawkes processes, designed to capture temporal self-excitation and the spatial propagation of order flow across price levels. In contrast to classical zero-intelligence or Poisson based queueing…

Lab Rats Math 8.5 Rigor 1.0

Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization

Kevin et al.

This paper introduces a hybrid framework for portfolio optimization that fuses Long Short-Term Memory (LSTM) forecasting with a Proximal Policy Optimization (PPO) reinforcement learning strategy. The proposed system leverages the predictive power of deep recurrent networks to capture temporal…

Holy Grail Math 8.0 Rigor 7.5
Costs: ModeledOut-of-sample: HoldoutResolution: Weekly-Monthly Data
More details
Authors
Jun Kevin, Pujianto Yugopuspito
Evaluation
Trading P&L

Partial multivariate transformer as a tool for cryptocurrencies time series prediction

Tokajuk et al.

Forecasting cryptocurrency prices is hindered by extreme volatility and a methodological dilemma between information-scarce univariate models and noise-prone full-multivariate models. This paper investigates a partial-multivariate approach to balance this trade-off, hypothesizing that a strategic…

Holy Grail Math 7.0 Rigor 6.0 capped
Costs: Not modeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Andrzej Tokajuk, Jarosław A. Chudziak
Evaluation
Unclear

Random processes for long-term market simulations

Zumbach

For long term investments, model portfolios are defined at the level of indexes, a setup known as Strategic Asset Allocation (SAA). The possible outcomes at a scale of a few decades can be obtained by Monte Carlo simulations, resulting in a probability density for the possible portfolio values at…

Holy Grail Math 7.5 Rigor 6.0

Reinforcement Learning for Portfolio Optimization with a Financial Goal and Defined Time Horizons

Leukam et al.

This research proposes an enhancement to the innovative portfolio optimization approach using the G-Learning algorithm, combined with parametric optimization via the GIRL algorithm (G-learning approach to the setting of Inverse Reinforcement Learning) as presented by. The goal is to maximize…

Lab Rats Math 8.0 Rigor 3.0
Costs: ModeledOut-of-sample: NoneResolution: Unclear
More details
Authors
Fermat Leukam, Rock Stephane Koffi, Prudence Djagba
Evaluation
Trading P&L