|
on Computational Economics |
| By: | Kelvin J. L. Koa; Filip Orestav; Shengqiong Wu; Michael J. Wooldridge; Ke-Wei Huang |
| Abstract: | While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level reasoning over market context information, and (3) a memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large language models, and SR approaches, while simultaneously producing interpretable equations, which we share with the community. We also make publicly available the distilled learnings across evolution iterations and context-dependent strategy weights, which might offer useful insights for future research on financial fundamental analysis. |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.32746 |
| By: | Wee Ling Tan; Stephen Roberts; Stefan Zohren |
| Abstract: | We present an end-to-end deep learning framework for systematic options trading that directly embeds hedging behavior through explicit control of portfolio-level risk exposures. While neural networks trained to optimize risk-adjusted performance have been shown to outperform traditional rules-based strategies, such approaches remain agnostic to the sensitivities of the resulting portfolios with respect to specific underlying risk factors. We propose a general training objective that combines a performance-driven loss with a differentiable risk-sensitivity penalty, enforcing neutrality to selected risk dimensions. Unlike reinforcement learning methods that approximate optimal hedging policies via simulated market dynamics, our framework operates entirely on historical data and jointly optimizes risk-adjusted returns and targeted risk constraints in a single learning problem. We instantiate the framework on static delta-neutral straddle portfolios with the penalty directed at first-order directional exposure, and evaluate two penalty variants -- an exposure-normalized penalty and a Greek-ratio drift penalty. Empirical results on Nasdaq 100 equity options demonstrate that appropriately calibrated regularization simultaneously improves out-of-sample risk-adjusted performance relative to an unregularized baseline while reducing realized directional exposure. |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.33767 |
| By: | Anna B. Schmidt |
| Abstract: | This work studies how Bayesian machine learning methods can be used for large-scale demand estimation with many product categories. I compare two model classes, a latent factorization model and a mixed logit model and two Bayesian estimation approaches, Markov Chain Monte Carlo (MCMC) and Variational Inference (VI). The analysis combines a simulation study with an application to supermarket scanner data. The results show that the latent factorization model benefits from information across categories and improves its predictive performance as the dimensionality of the choice environment increases, whereas the mixed logit model does not exhibit the same pattern. MCMC delivers the highest predictive accuracy but is computationally intensive. VI achieves slightly lower predictive performance while substantially reducing runtime. In the empirical application, VI also outperforms the mixed logit benchmark. These findings highlight a trade-off between accuracy and computational feasibility in multi-category demand estimation. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.08409 |
| By: | Maya Kodeih; Aliaa Alnaggar; Mucahit Cevik |
| Abstract: | Monetary-policy announcements and central-bank communications play a central role in foreign exchange markets, yet their qualitative, unstructured form makes their forecasting value difficult to quantify. While prior research has largely focused on sentiment extracted from financial news, comparatively little is known about the relative contribution of different dimensions of monetary-policy communication. Existing studies primarily evaluate whether textual information improves overall forecasting performance but provide limited insight into which communication channels drive such improvements. To address this gap, this paper introduces a statistical attribution methodology that decomposes monetary-policy communication into interpretable channels and quantifies their incremental forecasting contribution under false-discovery-rate control. Monetary-policy news is transformed into structured communication signals using large language models (LLMs) and temporal feature engineering. These signals are evaluated using rolling-window experiments with tree-based machine-learning models. The results show that monetary-policy communication contains measurable predictive information. Attribution analysis shows that predictive value is concentrated in a small subset of signals, with communication timing providing the strongest individual feature-level contribution, targeted communication-activity measures also contributing positively, and LLM-derived sentiment providing complementary information at the group level. The findings indicate that communication-based forecasting value extends beyond sentiment alone and that attribution, rather than aggregate accuracy alone, is central to evaluating news-derived signals. |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.32773 |
| By: | Haochen Luo; Yifan Li; Binh Minh An; Xiaolong Luo; Zhengzhao Lai; Yuan Zhang; Chen Liu |
| Abstract: | Large language models (LLMs) and multi-agent systems (MAS) have shown promise in financial decision-making, yet existing evaluations focus on equity trading and primarily assess directional prediction, overlooking the structural complexity of derivative markets. Option trading introduces fundamentally different challenges, including nonlinear payoffs and multi-leg strategy construction, requiring structured decisions rather than simple directional bets. We introduce LiveOption, an evaluation framework for LLM-based agents in option trading. LiveOption formulates the problem as structured sequential decision-making under realistic execution and capital constraints, and provides a reproducible environment with standardized interaction protocols. The framework includes three task suites covering portfolio overlays, event-driven earnings trading, and 0DTE intraday trading. We further propose a hierarchical metric suite that evaluates action validity, decision quality, risk characteristics, and outcome-level performance. Experiments show that current agents often fail to achieve competitive returns in most scenarios. LiveOption offers a principled testbed for evaluating structured decision-making beyond outcome-based metrics. |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.33470 |
| By: | Siyu Wang; Yifan Wang; Yuecheng He |
| Abstract: | Large language models are moving from producing trading signals to writing the code that executes them. The failure mode of the second role is silent: generated code runs, a backtest plots, yet the risk logic that the trader described is not the logic being executed. Existing code benchmarks test functional correctness on unit tests and finance benchmarks test forecasting; neither measures whether an implementation behaves like the strategy that was asked for. We introduce MintEval, a benchmark in which reference strategies are generated programmatically from a library of composable building blocks, back-translated into colloquial trader instructions, and re-implemented by the model under test. Generated and reference programs are executed bar by bar on identical market data and frictions, and compared on their actions rather than on code similarity or profit: alpha is differenced away. MintEval v0 contains 800 tasks on BTCUSDT 15-minute data, stratified by an execution-measured state-span complexity tau that is decoupled from description length. Low-cost models reach a mean ActionMatch of at most 0.544 and reproduce at most 0.087 of tasks exactly; on a stratified subset of 200 tasks a frontier model (Claude Opus 5.5) reaches 0.889 and reproduces 0.575 exactly, yet still fails silently on 0.275 of tasks. Given a menu of building blocks, models identify the strategy almost perfectly, yet 79.2% of the implementations whose specification was read correctly diverge on more than 10% of active bars. The LLM judge of a recent strategy-generation benchmark, applied verbatim, accepts every one of these silent failures. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.03080 |
| By: | Junyi Ye |
| Abstract: | When a data license expires, deleting stored records does not remove influence encoded in a trained forecaster. Machine unlearning seeks to remove this influence without retraining. We benchmark temporal unlearning with 3, 200 paired references trained on all data and oracles retrained without the requested period. The grid covers five architectures, four rolling folds, five deletable years, and three experimental deletion levels on an S&P 500 volatility panel. The 2020 COVID crisis year produces the largest memorization gap for every architecture. Removing it improves all three deployable models in every fold, with the largest improvement in the 2022 bear market, while the two non-deployable models respond inconsistently. The target for approximate unlearning is the oracle, not low predictive accuracy on the deleted period. In one Transformer cell, an oracle that never trained on 2020 still predicts it at an information coefficient of 0.51, compared with 0.55 for the reference; pushing predictions toward noise reduces test skill. Across twelve deployable architecture-method pairs, only TSMixer with the hinge method remains near the oracle in every fold, closing 74-118% of the reference-to-oracle gap without a measurable loss of test skill. Method rankings vary across architectures and rolling windows. Audit separation rises with prior memorization but can remain small after exact deletion. The window-level loss comparison reaches at most 0.69, and treating stock-level windows as independent inflates the absolute t-statistic by a median factor of 1.9. These results call for an explicit deletion scope, oracle validation for the relevant architecture and window, and power-aware auditing. |
| Date: | 2026–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.26242 |
| By: | Xiangyu Li; Fengbin Zhu; Xuan Yao; Siyu Liu; Xiaoluan Liu; Chao Wang; Huanbo Luan; Xiaofen Xing; Xiangmin Xu; Ke-Wei Huang; Richang Hong; Tat-Seng Chua |
| Abstract: | Deep Research (DR) agents have demonstrated strong capabilities in complex, research-oriented tasks through autonomous planning, iterative retrieval, multi-step reasoning, and structured reporting. However, adapting DR agents to finance introduces unique challenges: financial analysis demands the joint completion of heterogeneous sub-tasks spanning diverse data types, tools, and analytical workflows. We identify three key requirements for a professional financial DR agent: integration of authoritative, heterogeneous financial data sources; specialized analytical tools and skills; and dedicated sub-agents for domain-specific sub-tasks. Building on these principles, we propose FinNextAssist, an end-to-end deep research framework designed for professional financial analysis. FinNextAssist decomposes the research process into four stages: Task Planner, Evidence Compiler, Reasoning Engine, and Report Assembler, and introduces two novel lightweight sub-agents: TabAgent, for cross-market financial table understanding, and HeteroAgent, for cross-modality heterogeneous financial data interpretation. Extensive experiments on FinDeepResearch, the Finance Agent Benchmark, and FinTMMBench-Web show that FinNextAssist substantially outperforms both strong proprietary and open-source DR agents, with ablation studies confirming the contribution of each component across diverse markets and languages. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.03174 |
| By: | Kriesch, Lukas (Justus-Liebig-Universität Gießen); Losacker, Sebastian (Justus-Liebig-Universität Gießen) |
| Abstract: | The emergence of large language models and the exponential growth of digitized text data have revolutionized research methodologies across a broad range of social sciences. News articles are an important source of digitized text data in this context. News data is crucial for the social sciences as it provides real-time insights into public discourse and societal trends, helping to understand various social phenomena and dynamics. However, most research involving news data is conducted at the national level, as geographically more granular news data is often unavailable. In this paper, we address this gap by providing insights into how news articles can be geolocated and how the texts can then be further analyzed. More specifically, we collect data from the CommonCrawl News dataset and clean the text data for further analysis. We then use a named-entity recognition model for geocoding, linking news articles to geographic locations. Finally, we transform the news articles into text embeddings using SBERT, enabling semantic searches within the news data corpus. In the paper, we apply this process to all German news articles and make the German location data, as well as the embeddings, available for download. As a result, we compile a dataset containing text embeddings for about 50 million German news articles, of which about 70% include geographic locations. The process can be replicated for news data from other countries, as we provide all code and workflows. |
| Keywords: | News data; Natural language processing; Geography |
| JEL: | C45 O33 R12 |
| Date: | 2026–09–25 |
| URL: | https://d.repec.org/n?u=RePEc:hhs:lucirc:2025_004 |
| By: | Jean-Loup Dupret; Donatien Hainaut; Edouard Motte |
| Abstract: | We introduce a deep kernel hedging framework that combines the flexibility of deep learning with the structural inductive bias of kernel methods. The hedging functional is restricted to a reproducing kernel Hilbert space whose kernel is parameterized through a neural network embedding of the input features. The framework minimizes a regularized empirical risk under convex loss functions and can accommodate path-dependent information through truncated time-augmented signature features. We derive a generalized representer theorem for the joint hedging problem, reducing the empirical optimization to a finite-dimensional problem. To further reduce the computational cost associated with large kernel matrices, we develop a scalable random Fourier feature approximation and establish convergence guarantees. The random Fourier parameters are sampled once and remain fixed throughout training, while the deep kernel adapts to market data through the learned neural representation. We evaluate the performance of the proposed deep kernel approach on both synthetic and real data and compare it with standard kernel methods and classical deep hedging architectures. Numerical results indicate competitive and robust hedging performance, particularly in low-data regimes, which highlights the benefits of combining expressive neural representations with the inductive bias of kernel methods. |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2609.34474 |
| By: | Enang, Imowo; Omeihe, Kingsley Obi |
| Abstract: | This working paper presents a design science research (DSR) investigation into the development and evaluation of an innovative real-time, adaptive AI-driven business simulation platform. Traditional business simulations typically operate with static scenarios and predefined parameters that fail to capture the dynamic complexity of contemporary business environments. Using a rigorous DSR methodology spanning four design cycles over twenty-four months, we developed and refined a prototype system that integrates machine learning algorithms, natural language processing, and knowledge graph technologies to create dynamically evolving simulation scenarios. The platform was evaluated across diverse contexts including MBA education programmes, corporate strategy training, and entrepreneurial incubators, involving 287 participants across multiple evaluation phases. Our findings demonstrate the system's efficacy in enhancing strategic decision-making capabilities, improving knowledge transfer, and fostering adaptive reasoning skills among users. The paper lays the groundwork for next-generation business education and strategy testing environments that more authentically reflect the complex, evolving nature of real-world business ecosystems. |
| Keywords: | adaptive AI; business solutions |
| Date: | 2025–03–01 |
| URL: | https://d.repec.org/n?u=RePEc:gpe:wpaper:54468 |
| By: | Virginie Terraza (MRE - Montpellier Recherche en Economie - UM - Université de Montpellier, uni.lu - Université du Luxembourg = University of Luxembourg = Universität Luxemburg); Aslı Boru İpek (Kütahya Dumlupinar University = Kütahya Dumlupınar Üniversitesi [Kütahya, Turquie]) |
| Abstract: | This study proposes a multi-stage approach to modelling dependencies using Vector Autoregression (VAR), Nonlinear Autoregressive Neural Network (NAR-NN) models, and copulas. This paper aims to assess the dynamic dependency structure between cryptocurrencies and traditional financial assets, considering regime changes and safe-haven properties. The proposed methodology integrates change point detection with copula-based conditional correlation Generalized Autoregressive Conditional Heteroscedasticity (GARCH) models to identify structural breaks and nonlinear dependencies between regimes. A sequential change point procedure based on fast signal segmentation is employed to detect structural changes. According to this study, cryptocurrencies and traditional assets exhibit regimedependent dependence. It was also determined that during periods of market stress, this dependency significantly increases. This paper has significant implications for portfolio diversification, risk management, and the role of digital assets in financial markets. Furthermore, this proposed methodology contributes to the literature by capturing nonlinear, time-dependent, and regime-dependent dependency structures. |
| Keywords: | 62M10, 68T07, neural network MSC: 91G15, DCC-GARCH family models, VAR, copula, change point detection, financial markets, interconnections, interconnections financial markets change point detection copula VAR DCC-GARCH family models neural network MSC: 91G15 62M10 68T07 |
| Date: | 2026–09–15 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-05752791 |
| By: | Kenneth L. Judd; Karl Schmedders |
| Abstract: | Deep learning is increasingly presented in economics as a new paradigm for solving dynamic models, superseding the classical projection methods of numerical economics. We argue that this dichotomy rests on a misclassification. The neural-network solvers emphasized in this literature are least-squares projection methods with an adaptive nonlinear parameterization. Placing deep learning inside the projection family reorients the agenda. The issue is not a contest between paradigms, but suggests a single toolkit using a variety of approximation methods, residual criteria, and evaluation designs to be chosen on the merits for the model at hand. In low and moderate dimensions, linear-basis and sparsegrid methods are often more accurate, faster, and easier to verify than a trained neural network. In high dimensions, an appropriate choice for the space of permissible functions will often avoid the curse of dimensionality. |
| JEL: | C60 |
| Date: | 2026–09 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35806 |
| By: | Lenza, Michele; Marchini, Claudia |
| Abstract: | This study applies a Local Linear Forest (LLF) for wage forecasting in France. The LLF outperforms benchmarks such as Random Walk (RW), Ridge Regressions (RR) and Random Forests (RF). We also show that adding foreign predictors (i.e. measures of real activity, price and wage pressures from Germany and Italy) to French economic variables significantly improves wage predictions in France. The implications of our results are that wage dynamics in France exhibit non-linearity, to a certain extent, and that the better ability of LLFs relative to RFs to fit smooth signals is a valuable feature, especially at times in which wage growth reaches unprecedented levels from an historical perspective. JEL Classification: C45, C55, E37, J30 |
| Keywords: | forecasting, local linear forest, negotiated wages |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20263291 |