New articles on Quantitative Finance


[1] 2509.07987

Automated Trading System for Straddle-Option Based on Deep Q-Learning

Straddle Option is a financial trading tool that explores volatility premiums in high-volatility markets without predicting price direction. Although deep reinforcement learning has emerged as a powerful approach to trading automation in financial markets, existing work mostly focused on predicting price trends and making trading decisions by combining multi-dimensional datasets like blogs and videos, which led to high computational costs and unstable performance in high-volatility markets. To tackle this challenge, we develop automated straddle option trading based on reinforcement learning and attention mechanisms to handle unpredictability in high-volatility markets. Firstly, we leverage the attention mechanisms in Transformer-DDQN through both self-attention with time series data and channel attention with multi-cycle information. Secondly, a novel reward function considering excess earnings is designed to focus on long-term profits and neglect short-term losses over a stop line. Thirdly, we identify the resistance levels to provide reference information when great uncertainty in price movements occurs with intensified battle between the buyers and sellers. Through extensive experiments on the Chinese stock, Brent crude oil, and Bitcoin markets, our attention-based Transformer-DDQN model exhibits the lowest maximum drawdown across all markets, and outperforms other models by 92.5\% in terms of the average return excluding the crude oil market due to relatively low fluctuation.


[2] 2509.08096

Joint calibration of the volatility surface and variance term structure

This article proposes a calibration framework for complex option pricing models that jointly fits market option prices and the term structure of variance. Calibrated models under the conventional objective function, the sum of squared errors in Black-Scholes implied volatilities, can produce model-implied variance term structures with large errors relative to those observed in the market and implied by option prices. I show that this can occur even when the model-implied volatility surface closely matches the volatility surface observed in the market. The proposed joint calibration addresses this issue by augmenting the conventional objective function with a penalty term for large deviations from the observed variance term structure. This augmented objective function features a hyperparameter that governs the relative weight placed on the volatility surface and the variance term structure. I test this framework on a jump-diffusion model with stochastic volatility in two calibration exercises: the first using volatility surfaces generated under a Bates model, and the second using a panel of S&P 500 equity index options covering the 1996-2023 period. I demonstrate that the proposed method is able to fit observed option prices well while delivering realistic term structures of variance. Finally, I provide guidance on the choice of hyperparameters based on the results of these numerical exercises.


[3] 2509.08183

Chaotic Bayesian Inference: Strange Attractors as Risk Models for Black Swan Events

We introduce a new risk modeling framework where chaotic attractors shape the geometry of Bayesian inference. By combining heavy-tailed priors with Lorenz and Rossler dynamics, the models naturally generate volatility clustering, fat tails, and extreme events. We compare two complementary approaches: Model A, which emphasizes geometric stability, and Model B, which highlights rare bursts using Fibonacci diagnostics. Together, they provide a dual perspective for systemic risk analysis, linking Black Swan theory to practical tools for stress testing and volatility monitoring.


[4] 2509.08279

Decarbonizing Basic Chemicals Production in North America, Europe, Middle East, and China: a Scenario Modeling Study

The chemicals industry accounts for about 5% of global greenhouse gas emissions today and is among the most difficult industries to abate. We model decarbonization pathways for the most energy-intensive segment of the industry, the production of basic chemicals: olefins, aromatics, methanol, ammonia, and chlor-alkali. Unlike most prior pathways studies, we apply a scenario-analysis approach that recognizes the central role of corporate investment decision making for capital-intensive industries, under highly uncertain long-term future investment environments. We vary the average pace of decarbonization capital allocation allowed under plausible alternative future world contexts and construct least-cost decarbonization timelines by modeling abatement projects individually across more than 2,600 production facilities located in four major producing regions. The timeline for deeply decarbonizing production varies by chemical and region but depends importantly on the investment environment context. In the best-of-all environments, to deeply decarbonize production, annual average capital spending for abatement for the next two to three decades will need to be greater than (and in addition to) historical "business-as-usual" investments, and cumulative investment in abatement projects would exceed $1 trillion. In futures where key drivers constrain investment appetites, timelines for decarbonizing the industry extend well into the second half of the century.


[5] 2509.08450

Environmental Performance, Financial Constraint and Tax Avoidance Practices: Insights from FTSE All-Share Companies

Through its initiative known as the Climate Change Act (2008), the Government of the United Kingdom encourages corporations to enhance their environmental performance with the significant aim of reducing targeted greenhouse gas emissions by the year 2050. Previous research has predominantly assessed this encouragement favourably, suggesting that improved environmental performance bolsters governmental efforts to protect the environment and fosters commendable corporate governance practices among companies. Studies indicate that organisations exhibiting strong corporate social responsibility (CSR), environmental, social, and governance (ESG) criteria, or high levels of environmental performance often engage in lower occurrences of tax avoidance. However, our findings suggest that an increase in environmental performance may paradoxically lead to a rise in tax avoidance activities. Using a sample of 567 firms listed on the FTSE All Share from 2014 to 2022, our study finds that firms associated with higher environmental performance are more likely to avoid taxation. The study further documents that the effect is more pronounced for firms facing financial constraints. Entropy balancing, propensity score matching analysis, the instrumental variable method, and the Heckman test are employed in our study to address potential endogeneity concerns. Collectively, the findings of our study suggest that better environmental performance helps explain the variation in firms tax avoidance practices.


[6] 2509.08742

FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model

Financial time series forecasting is both highly significant and challenging. Previous approaches typically standardized time series data before feeding it into forecasting models, but this encoding process inherently leads to a loss of important information. Moreover, past time series models generally require fixed numbers of variables or lookback window lengths, which further limits the scalability of time series forecasting. Besides, the interpretability and the uncertainty in forecasting remain areas requiring further research, as these factors directly impact the reliability and practical value of predictions. To address these issues, we first construct a diverse financial image-text dataset (FVLDB) and develop the Uncertainty-adjusted Group Relative Policy Optimization (UARPO) method to enable the model not only output predictions but also analyze the uncertainty of those predictions. We then proposed FinZero, a multimodal pre-trained model finetuned by UARPO to perform reasoning, prediction, and analytical understanding on the FVLDB financial time series. Extensive experiments validate that FinZero exhibits strong adaptability and scalability. After fine-tuning with UARPO, FinZero achieves an approximate 13.48\% improvement in prediction accuracy over GPT-4o in the high-confidence group, demonstrating the effectiveness of reinforcement learning fine-tuning in multimodal large model, including in financial time series forecasting tasks.


[7] 2509.08163

Machine Learning with Multitype Protected Attributes: Intersectional Fairness through Regularisation

Ensuring equitable treatment (fairness) across protected attributes (such as gender or ethnicity) is a critical issue in machine learning. Most existing literature focuses on binary classification, but achieving fairness in regression tasks-such as insurance pricing or hiring score assessments-is equally important. Moreover, anti-discrimination laws also apply to continuous attributes, such as age, for which many existing methods are not applicable. In practice, multiple protected attributes can exist simultaneously; however, methods targeting fairness across several attributes often overlook so-called "fairness gerrymandering", thereby ignoring disparities among intersectional subgroups (e.g., African-American women or Hispanic men). In this paper, we propose a distance covariance regularisation framework that mitigates the association between model predictions and protected attributes, in line with the fairness definition of demographic parity, and that captures both linear and nonlinear dependencies. To enhance applicability in the presence of multiple protected attributes, we extend our framework by incorporating two multivariate dependence measures based on distance covariance: the previously proposed joint distance covariance (JdCov) and our novel concatenated distance covariance (CCdCov), which effectively address fairness gerrymandering in both regression and classification tasks involving protected attributes of various types. We discuss and illustrate how to calibrate regularisation strength, including a method based on Jensen-Shannon divergence, which quantifies dissimilarities in prediction distributions across groups. We apply our framework to the COMPAS recidivism dataset and a large motor insurance claims dataset.


[8] 2509.08166

A Linear Pricing Mechanism for Load Management in Day-Ahead Retail Energy Markets

Regulators and utilities have been exploring hourly retail electricity pricing, with several existing programs providing day-ahead hourly pricing schedules. At the same time, customers are deploying distributed energy resources and smart energy management systems that have significant flexibility and can optimally follow price signals. In aggregate, these optimally controlled loads can create congestion management issues for distribution system operators (DSOs). In this paper, we describe a new linear pricing mechanism for day-ahead retail electricity pricing that provides a signal for customers to follow to mitigate over-consumption while still consuming energy at hours that are preferential for system performance. We show that by broadcasting a linear price designed for price-signal control of cost-optimizing loads, we can shape customer load profiles to provide congestion management without the need for bi-directional communication or customer bidding programs.


[9] 2509.08467

An Interpretable Deep Learning Model for General Insurance Pricing

This paper introduces the Actuarial Neural Additive Model, an inherently interpretable deep learning model for general insurance pricing that offers fully transparent and interpretable results while retaining the strong predictive power of neural networks. This model assigns a dedicated neural network (or subnetwork) to each individual covariate and pairwise interaction term to independently learn its impact on the modeled output while implementing various architectural constraints to allow for essential interpretability (e.g. sparsity) and practical requirements (e.g. smoothness, monotonicity) in insurance applications. The development of our model is grounded in a solid foundation, where we establish a concrete definition of interpretability within the insurance context, complemented by a rigorous mathematical framework. Comparisons in terms of prediction accuracy are made with traditional actuarial and state-of-the-art machine learning methods using both synthetic and real insurance datasets. The results show that the proposed model outperforms other methods in most cases while offering complete transparency in its internal logic, underscoring the strong interpretability and predictive capability.


[10] 2504.18788

Elite Formation and Family Structure in Prewar Japan: Evidence from the Who's Who Records

This paper introduces a newly constructed individual-level dataset of prewar Japanese elites using the ``Who's Who'' directories published in 1903-1939. Covering approximately the top 0.1\% of the population, the dataset contains rich information on social origin, education, occupation, and family structure. By reconstructing intergenerational links and family networks, we provide descriptive evidence on elite formation and persistence across geography, social groups, and education during institutional transitions. The dataset provides a foundational empirical resource for studying elite reproduction, intergenerational and intergroup mobility, and institutional development during Japan's transition to a modern society.


[11] 2505.00607

Nonparametric Estimation of Matching Efficiency and Elasticity in a Marriage Agency Platform: 2014--2025

This paper examines monthly matching efficiency in the Japanese marriage market using novel data from IBJ, the country's largest structured matching platform. Unlike administrative or dating app data, IBJ provides full search, dating, and matching logs based on verified profiles and confirmed engagements. Users are highly selected into serious marriage search via costly screening. Covering 3.3% of national marriages annually, the data offer rare behavioral granularity. Using a nonparametric approach, I estimate time-varying matching functions and elasticities. Efficiency rises threefold over time, illustrating how digital intermediation transforms partner search in modern marriage markets.


[12] 2508.12315

Deciphering the global production network from cross-border firm transactions

Critical for policy-making and business operations, the study of global supply chains has been severely hampered by a lack of detailed data. Here we harness global firm-level transaction data covering 20m global firms, and 1 billion cross-border transactions, to infer key inputs for over 1200 products. Transforming this data to a directed network, we find that products are clustered into three large groups including textiles, chemicals and food, and machinery and metals. European industrial nations and China dominate critical intermediate products in the network such as metals, common components and tools, while industrial complexity is correlated with embeddedness in densely connected supply chains. To validate the network, we find structural similarities with two alternative product networks, one generated via LLM queries and the other derived by NAFTA to track product origins. We further detect linkages between products identified in manually mapped single sector supply chains, including electric vehicle batteries and semi-conductors. Finally, metrics derived from network structure capturing both forward and backward linkages are able to predict country-product diversification patterns with high accuracy.


[13] 2509.05080

MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading

The inherent non-stationarity of financial markets and the complexity of multi-modal information pose significant challenges to existing quantitative trading models. Traditional methods relying on fixed structures and unimodal data struggle to adapt to market regime shifts, while large language model (LLM)-driven solutions - despite their multi-modal comprehension - suffer from static strategies and homogeneous expert designs, lacking dynamic adjustment and fine-grained decision mechanisms. To address these limitations, we propose MM-DREX: a Multimodal-driven, Dynamically-Routed EXpert framework based on large language models. MM-DREX explicitly decouples market state perception from strategy execution to enable adaptive sequential decision-making in non-stationary environments. Specifically, it (1) introduces a vision-language model (VLM)-powered dynamic router that jointly analyzes candlestick chart patterns and long-term temporal features to allocate real-time expert weights; (2) designs four heterogeneous trading experts (trend, reversal, breakout, positioning) generating specialized fine-grained sub-strategies; and (3) proposes an SFT-RL hybrid training paradigm to synergistically optimize the router's market classification capability and experts' risk-adjusted decision-making. Extensive experiments on multi-modal datasets spanning stocks, futures, and cryptocurrencies demonstrate that MM-DREX significantly outperforms 15 baselines (including state-of-the-art financial LLMs and deep reinforcement learning models) across key metrics: total return, Sharpe ratio, and maximum drawdown, validating its robustness and generalization. Additionally, an interpretability module traces routing logic and expert behavior in real time, providing an audit trail for strategy transparency.


[14] 2509.07793

Individual utilities of life satisfaction reveal inequality aversion unrelated to political alignment

How should well-being be prioritised in society, and what trade-offs are people willing to make between fairness and personal well-being? We investigate these questions using a stated preference experiment with a nationally representative UK sample (n = 300), in which participants evaluated life satisfaction outcomes for both themselves and others under conditions of uncertainty. Individual-level utility functions were estimated using an Expected Utility Maximisation (EUM) framework and tested for sensitivity to the overweighting of small probabilities, as characterised by Cumulative Prospect Theory (CPT). A majority of participants displayed concave (risk-averse) utility curves and showed stronger aversion to inequality in societal life satisfaction outcomes than to personal risk. These preferences were unrelated to political alignment, suggesting a shared normative stance on fairness in well-being that cuts across ideological boundaries. The results challenge use of average life satisfaction as a policy metric, and support the development of nonlinear utility-based alternatives that more accurately reflect collective human values. Implications for public policy, well-being measurement, and the design of value-aligned AI systems are discussed.


[15] 2506.19958

Introducing RobustiPy: An efficient next generation multiversal library with model selection, averaging, resampling, and explainable artificial intelligence

Scientific inference is often undermined by the vast but rarely explored "multiverse" of defensible modelling choices, which can generate results as variable as the phenomena under study. We introduce RobustiPy, an open-source Python library that systematizes multiverse analysis and model-uncertainty quantification at scale. RobustiPy unifies bootstrap-based inference, combinatorial specification search, model selection and averaging, joint-inference routines, and explainable AI methods within a modular, reproducible framework. Beyond exhaustive specification curves, it supports rigorous out-of-sample validation and quantifies the marginal contribution of each covariate. We demonstrate its utility across five simulation designs and ten empirical case studies spanning economics, sociology, psychology, and medicine, including a re-analysis of widely cited findings with documented discrepancies. Benchmarking on ~672 million simulated regressions shows that RobustiPy delivers state-of-the-art computational efficiency while expanding transparency in empirical research. By standardizing and accelerating robustness analysis, RobustiPy transforms how researchers interrogate sensitivity across the analytical multiverse, offering a practical foundation for more reproducible and interpretable computational science.


[16] 2507.07935

Working with AI: Measuring the Applicability of Generative AI to Occupations

Given the rapid adoption of generative AI and its potential to impact a wide range of tasks, understanding the effects of AI on the economy is one of society's most important questions. In this work, we take a step toward that goal by analyzing the work activities people do with AI, how successfully and broadly those activities are done, and combine that with data on what occupations do those activities. We analyze a dataset of 200k anonymized and privacy-scrubbed conversations between users and Microsoft Bing Copilot, a publicly available generative AI system. We find the most common work activities people seek AI assistance for involve gathering information and writing, while the most common activities that AI itself is performing are providing information and assistance, writing, teaching, and advising. Combining these activity classifications with measurements of task success and scope of impact, we compute an AI applicability score for each occupation. We find the highest AI applicability scores for knowledge work occupation groups such as computer and mathematical, and office and administrative support, as well as occupations such as sales whose work activities involve providing and communicating information. Additionally, we characterize the types of work activities performed most successfully, how wage and education correlate with AI applicability, and how real-world usage compares to predictions of occupational AI impact.