|
on Computational Economics |
| By: | Cristina Rossetti; Nicola Caravaggio; Giovanni Lamura; Giuliano Resce |
| Abstract: | The study of the factors driving the dynamics of healthcare spending is of paramount importance to guide policymakers in the allocation of resources and to measure the effectiveness of the healthcare system under consideration. The identification of these drivers can be supported by the use of machine learning techniques, which enable the discovery of hidden patterns within vast amounts of data. In contrast to black-box methods, Symbolic Regression (SR) is an approach that allows for the identification of analytical models that explicitly capture the functional relationships within the data, thus enhancing interpretability. In this paper, we present the use of SR for identifying the drivers of healthcare expenditure in Italian regions. Given the dynamic and complex nature of this phenomenon, we generated several models based on distinct temporal windows, enabling us to analyze the drivers across different time horizons. In addition to identifying the main drivers based on variable frequency in the generated models, we also conducted a study on recurring substructures. The results show that SR was able to generate models with a good level of predictive accuracy for private healthcare expenditure, enabling a reliable analysis of its driving factors, but failed to do so for public healthcare expenditure. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.04439 |
| By: | Zhuohan Wang; Carmine Ventre |
| Abstract: | Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents. Yet it remains unclear whether advances across these paradigms yield more generalizable, distinct, and economically useful financial signals. We introduce FactorBench, a portfolio-aware benchmark comparing roughly five thousand mined factors from nine automated mining methods across five equity markets. A shared data and evaluation contract supports both symbolic expressions and executable Python factors, connecting heterogeneous discovery algorithms to common signal combination and portfolio construction procedures. FactorBench traces the outputs of mining systems across three levels: factor validity, temporal generalization, and predictiveness beyond measured risk and style exposures; within- and across-method pool distinctness, including similarity to the benchmark Alpha101; and composite-signal quality and after-cost long-only and long--short portfolio performance. After systematically assessing whether advances in factor mining translate into signal quality and portfolio performance, FactorBench finds that no paradigm consistently dominates. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.06947 |
| By: | Mateusz Buczy\'nski; Micha{\l} Wo\'zniak; Konrad Kaczy\'nski; Anna Wr\'oblewska; Sebastian Kuk |
| Abstract: | Forecasting resale prices of used electronics is critical for subscription-based platforms where pricing errors translate directly into risk. Unlike structured financial markets, second-hand electronics exhibit high volatility, sparse listing histories, and non-normal price dynamics - yet no systematic time-series benchmark exists for this domain. This paper presents the first multi-horizon benchmark of statistical and deep learning forecasting models for used electronics price prediction. We use a large-scale dataset of daily price listings from Polish online marketplaces (January 2022 to March 2025, 100+ smartphone and laptop models) and evaluate eleven models across six horizons from 1 to 365 days, covering classical methods (ARIMA, ETS, Theta), recurrent and convolutional networks (LSTM, TCN), and modern deep architectures (N-BEATS, N-HiTS, TFT, PatchTST, Informer). Three complementary evaluation protocols assess trajectory fitness, one-shot endpoint accuracy, and cross-horizon transfer. N-BEATS achieves the lowest MAPE beyond 30 days, reaching 8.51% at 365 days versus 14.94% for the best statistical baseline - a 43% reduction. At short horizons (1-7 days), all models converge near 0.72% MAPE and the naive baseline remains competitive. A single N-BEATS model trained at 365 days generalizes to all shorter horizons, eliminating the need for horizon-specific models. N-BEATS and N-HiTS also demonstrate superior hyperparameter stability. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.10727 |
| By: | Ricardo Alonzo Fern\'andez-Salguero |
| Abstract: | This study develops a survey-calibrated, path-dependent agent-based microsimulation for evaluating crime and violence reduction policies in Bolivia. A synthetic population is constructed from the 2025 Household Survey and the fourth-quarter 2025 Continuous Employment Survey using official expansion weights and cross-survey donor matching. The model combines heterogeneous agents, place-based risk, criminal adaptation, institutional capacity, community organization, and multiple policy channels. Uncertainty is propagated through adaptive Gaussian-process and tree-ensemble emulators, global sensitivity analysis, tempered ensemble MCMC, and predictive meta-calibration. Simulated portfolios include focused policing, community control, Guardabosques-type incentives, social prevention, environmental interventions, justice reforms, investigation, rehabilitation, and financial-network disruption. Results are interpreted as structural policy scenarios rather than causal forecasts, with explicit attention to displacement, distributional effects, implementation capacity, and multi-objective trade-offs. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.03895 |
| By: | OECD |
| Abstract: | Timely and accurate distributional income data are essential for monitoring inequality, assessing the adequacy of tax-benefit systems, and designing policy responses during periods of rapid economic change. However, income and inequality statistics derived from EU-SILC are typically published with a lag of 12 to 18 months, limiting their usefulness during fast-moving shocks such as the COVID-19 pandemic, the 2022 energy price shock, or a severe recession. This paper presents results from a new nowcasting framework designed to reduce this information gap for EU Member States. By combining machine-learning (ML) forecasts of market income with EUROMOD microsimulation under the latest available tax-benefit rules, the framework produces timely estimates and forecasts of income inequality. |
| Keywords: | inequality, machine learning, microsimulation, nowcasting, poverty rate |
| JEL: | D31 C53 |
| Date: | 2026–10–13 |
| URL: | https://d.repec.org/n?u=RePEc:oec:wiseaa:41-en |
| By: | Raša Karapandža; Yaw Nyarko |
| Abstract: | Large language models (LLMs) increasingly provide economic and financial advice. We develop a microeconomic framework for understanding this role. We prove that an LLM acts like a voting rule: each input text is an election, possible continuations are candidates, and output probabilities are vote shares derived from the training corpus. Such rules can generate Condorcet cycles, implying intransitive pairwise recommendations and potential money-pump exploitation. Using ChatGPT-4o, we identify millions of cycles in pairwise investment choices among S&P 100 firms. Our theorems establish the voting interpretation on the training data and support its use off-sample. We also show that correcting cycles ex post is generally infeasible. Finally, temperature changes the voting rule: at T = 1, outputs are sampled in proportion to vote shares; lower temperatures favor the plurality winner, whereas higher temperatures flatten probabilities toward uniformity. |
| JEL: | D81 D83 D91 G41 |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35839 |
| By: | Yizhen Xie; Mengyang Liu |
| Abstract: | As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news, but option trading presents a particularly challenging decision problem: a single stock can have thousands of contracts, and the agent must decide both which contracts to trade and how to combine them. Existing approaches often sidestep this complexity by restricting the policy to a fixed strategy structure, such as a straddle, limiting their ability to switch strategies as market conditions change. We present SOTA (Stock Options Trading Agents), an agentic trading framework for structured option-strategy selection. SOTA abstracts the large option universe into strategy-level decisions while deterministic resolvers handle portfolio implementation. We develop SOTA by post-training Qwen3.8-27B with supervised fine-tuning followed by reinforcement learning. SOTA is evaluated on options on nine large-cap U.S. equities and SPY against rule-based and machine-learning strategy selectors in the same trading environment. Over a six-month out-of-sample period, SOTA earns an 18.3% total return with a Sharpe ratio of 1.60 and a maximum drawdown of 8.96%. We also document an asymmetric role of news: news improves frontier-teacher trajectories, but retaining news during reinforcement learning reduces out-of-sample return from 18.3% to -2.7%. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.10407 |
| By: | Yanzheng Jin; Pengyang Shao; Yunshan Ma; Haowen Pan; Naixin Zhai; Chen-Hui Song; Fei Shen; Kenji Kawaguchi |
| Abstract: | Formulaic alpha discovery seeks symbolic expressions that predict cross-sectional asset returns. In deployment, multiple formulas are combined into an alpha pool, where each formula is valued through the complementary information it contributes to joint predictive performance. While Reinforcement Learning and Generative Flow Networks have emerged as promising paradigms for generating formulaic alphas, existing frameworks face three related challenges. First, generating formulas individually leaves pool context and inter-formula complementarity outside the generative state. Second, formula-wise generation lacks a unified mechanism for preserving and revising structures at different levels. Third, pool-level rewards jointly reflect predictive performance and redundancy but cannot be differentiated directly through symbolic evaluation to train the generator. To overcome these challenges, we introduce AlphaPADI (Formulaic Alpha Discovery via Pool-Aware Hierarchical Discrete Diffusion), a novel framework built around three components: (1) grammar-constrained buffer initialization that constructs syntactically valid pool candidates, (2) pool-aware hierarchical diffusion that reconstructs complete pools at multiple structural scales under the current pool context, and (3) reward-guided pool refinement that evaluates joint predictive performance and inner diversity, updates the elite buffer, and trains the reverse model through reconstruction and preference learning. Empirical results on the Chinese and U.S. stock markets demonstrate that AlphaPADI outperforms the evaluated baselines in both predictive and portfolio performance, thereby validating pool-aware generation as an effective framework for automated alpha discovery. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.04959 |
| By: | Daniel Robert Kling Alexander; Catherine Louise Kling |
| Abstract: | Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem for decades. It judges survey responses without knowing the true value, through a framework of validity and related concepts: content, construct, and criterion validity, reliability, incentive compatibility, and consequentiality. We argue that this framework is a general method for evaluating language models, and we set out what each concept means for LLM evaluation. We demonstrate the approach using a published water-quality stated preference economic valuation survey (Vossler et al. 2023) administered to six models. In this economic application, the validity tests take the form of predictions from economic theory: demand should slope down, and willingness to pay should respond to the scope of the good and to income. The tests separate the models sharply. Two older models fail the most basic test at a household income level of \$75, 000, and the two newest pass every test of theoretical validity we can score, but diverge on convergent validity. Passing validity tests shows that a model's answers are coherent, not that they are correct. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.10506 |
| By: | Dexin Peng; Xiaoyu Wang |
| Abstract: | Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We show that model depth is a source of additional economic value in asset pricing. Residual learning can be used to deepen other neural-network-based asset pricing models if they contain intermediate layers. Our design also provides one way to scale asset pricing models, making native "large asset pricing models" more feasible. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.09613 |
| By: | E.F. Haghish (University of Bergen) |
| Abstract: | Missing data are common in empirical research. Standard imputation tools require users to specify model forms and tuning parameters before it is clear which model best fits each incomplete variable. As data become more complex, for example because of nested structures, mixed variable types, or low-prevalence categories, imputation becomes more difficult. mlim is a new Stata package that uses automated machine learning for single and multiple imputation in mixed datasets. For each incomplete variable, mlim builds and tunes a separate prediction model, rather than applying one predefined model to all variables. The default method is elastic net, with optional random forest, gradient boosting, and stacked ensemble models for more computationally demanding applications. The package supports large datasets with continuous, binary, multinomial, and ordinal variables and includes automatic balancing procedures to reduce bias when categorical variables contain rare levels. This presentation introduces mlim to the Stata community as a competent open-source software for single and multiple imputation. It discusses the motivation, workflow, strengths, limitations, and examples of how Stata users can apply mlim to impute missing data. |
| Date: | 2026–10–03 |
| URL: | https://d.repec.org/n?u=RePEc:boc:usug26:24 |