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

Beyond Anonymous Order Flow: Wallet Identity as a Feature for Short-Horizon Return Prediction

Ding et al.

Conventional public order-book data summarize trading without identifying the accounts behind it. Hyperliquid's Level-4 record also exposes persistent pseudonymous wallet addresses. We reconstruct full-depth books from consensus-ordered messages and evaluate wallet identity as a feature for…

Holy Grail Math 6.5 Rigor 8.0
Costs: Not applicableOut-of-sample: HoldoutResolution: L2 Order Book
More details
Authors
Jingqiu Ding, Daojing Zhai
Evaluation
Forecast accuracy

CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining

Wang et al.

Discovering predictive alpha factors from noisy financial data is a fundamental yet challenging problem in quantitative finance. LLM-driven formulaic alpha mining offers an attractive paradigm by combining interpretable symbolic expressions with iterative generation and refinement guided by…

Holy Grail Math 7.5 Rigor 6.0 capped Code
Costs: Not modeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Zhan-He Wang, Zi-Yang Lang, Yi-Yang Li, Qing-Yu Lan, Yun-Song Piao
Evaluation
Trading P&L

Decomposing Rank Reversals under Temporal Nonstationarity: Alignment, Aggressiveness, and Instability

Song et al.

Under temporal nonstationarity, model performance rankings reverse across training horizons due to heterogeneous sensitivities to memory. While existing literature addresses adaptive lookbacks, effective model complexity, and empirical forecast evaluation in isolation, no unified framework explains…

Holy Grail Math 9.0 Rigor 8.0
Costs: Not applicableOut-of-sample: Walk-forwardResolution: Daily Data
More details
Authors
Deying Song, Xueying Ding
Evaluation
Forecast accuracy

FinTech Adoption, Bank Profitability, and Stability: The Mediating Role of Operational Cost Efficiency in Bangladesh's Commercial Banking Sector

Sabiq et al.

While financial technology (FinTech) is seen as a contributor to bank performance, the empirical evidence of digitization's ability to translate into improved profit and stability outcomes and efficiency gains, within emerging systems dominated by banks is not conclusive. The direct impact of a…

Holy Grail Math 5.0 Rigor 7.0
More details
Authors
Shabab Sabiq, Progga Biswas Parama

How market volatility responds to a preceding price trend: a lag-resolved measurement in cryptocurrencies and equities

Bicki et al.

We quantify the response of market volatility to a preceding price trend as a function of lag at minute resolution. The asymmetry of the response is investigated. The sample consists of trades in three of the largest cryptocurrencies on a single exchange and in three large US stocks and the S&P 500…

Holy Grail Math 6.5 Rigor 8.0
More details
Authors
Gulsah Bicki, Taylan Akdogan

Mitigating Return Drag and Regime Whipsaws in Sector Rotation: An Asymmetric Downside-Aware Nested Clustered Optimization Framework

Supriadi

Hierarchical clustering and Nested Clustered Optimization (NCO) mitigate the mathematical ill-conditioning of classical Markowitz covariance matrices. However, two structural vulnerabilities persist in equity markets: (1) symmetric variance penalizes upside and downside return dispersion…

Holy Grail Math 7.5 Rigor 8.0 Code
Costs: Partially modeledOut-of-sample: Walk-forwardResolution: Weekly-Monthly Data
More details
Evaluation
Trading P&L

Multidimensional Views Behind Target-Price Revisions: An LLM-Based Representation of Analyst Outlooks

Kim et al.

A target price compresses an analyst's multidimensional views into a single number. We propose an LLM-based text representation that extracts these views from research reports as question-based outlook scores with supporting evidence. The questions organize reported views on earnings, valuation…

Street Traders Math 4.0 Rigor 8.0
Costs: Not applicableOut-of-sample: Walk-forwardResolution: Weekly-Monthly Data
More details
Authors
Kiyoun Kim, Sung-Yeon Nathan Lim
Evaluation
Forecast accuracy

Safe Portfolio Learning from Untrusted Predictions: Signed Trust, Abstention, and Cross-Universe Polarity Failure

MohammadpourAzari et al.

Portfolio use of machine predictions must often proceed while the predictions' economic direction, reliability, and timing remain untrusted, and while feedback from overlapping multi-period positions arrives with delay. A controller chooses among Safe, Follow, and Reverse portfolio actions, so…

Holy Grail Math 7.0 Rigor 7.0
Costs: Partially modeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Amirhossein MohammadpourAzari, Mohammad Zarei, MohammadAmin Fazli
Evaluation
Trading P&L

Are LLM Research Agents Reliable Judges of Predictability? Evidence from Planted-Signal Worlds

Liu

Researchers ask large language model (LLM) research agents whether a forecasting model beats a static benchmark, a verdict that real data cannot check. We treat the agent as a statistical test and score pre-specified runs of three frontier models and one open-weight model in simulated worlds with a…

Holy Grail Math 7.5 Rigor 9.0
Costs: Not applicableOut-of-sample: UnclearResolution: Weekly-Monthly Data
More details
Evaluation
Unclear

Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents

Benhamou et al.

Financial research agents can generate and monitor trading rules faster than a human can document the resulting selection process. Candidates appear at data-dependent times, weak rules are abandoned, and promising ones are watched until they cross a reporting threshold. We introduce PROMOTE, a…

Holy Grail Math 7.5 Rigor 8.0
Costs: ModeledOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Eric Benhamou, Jean-Jacques Ohana, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot
Evaluation
Unclear

EventGPT: Next-Event Pretraining on Banking Customer Histories

Burakov

A model pretrained to predict a customer's next event can estimate the probability of future events without training on their labels and provide a reusable representation for supervised downstream banking tasks. We pretrain EventGPT, a hierarchical causal transformer, by next-token maximum…

Holy Grail Math 6.5 Rigor 8.0 Code
Costs: Not applicableOut-of-sample: UnclearResolution: Unclear
More details
Evaluation
Forecast accuracy

Finite-horizon Optimal Consumption and Investment with Costly Income Adjustment

Ha et al.

We study optimal consumption and investment for an investor who receives labor income until a fixed retirement date, can raise the income rate irreversibly at a constant price per unit of income flow, and cannot borrow against future income. A pathwise argument shows that no income is purchased…

Lab Rats Math 9.5 Rigor 3.0
More details
Authors
Gugyum Ha, Junkee Jeon

Hardware-Aware Design and Layout Selection in Quantum Reservoir Computing for Insurance Claims Forecasting

Rusnáková et al.

Quantum reservoir computing (QRC) processes temporal information through quantum dynamics, but it remains unclear whether small QRC models can forecast real data competitively with classical models and whether their predictions survive the transfer from ideal simulation to noisy hardware. We…

Holy Grail Math 6.5 Rigor 8.0 Code
Costs: Not applicableOut-of-sample: HoldoutResolution: Daily Data
More details
Authors
Renáta Rusnáková, Eugen Šlapak, Gaurav K. Pandey, Juraj Gazda
Evaluation
Forecast accuracy

Herding or Racing? Decomposing Cross-Account Order-Flow Persistence in On-Chain Markets

Bai et al.

Most of the autocorrelation in trade signs on decentralized exchanges comes from pairs of trades sent by different wallets. For Uniswap v3, this has been read as herding dominating order splitting – the reverse of what equity markets show. We show that this herding share mixes two quantities: the…

Holy Grail Math 6.5 Rigor 8.0
Costs: UnclearOut-of-sample: UnclearResolution: Unclear
More details
Authors
Yichong Bai, Dingyue Kan
Evaluation
Unclear

Honest Small Decision Models for Finance: Scale, Specialization Collapse, and Mixed-Corpus Remediation

Kumar

Financial workflows need fast, calibrated, auditable decisions, not just generated text. We train System-1 decision models, small language models fine-tuned to answer typed questions (choice/score/noul) with a probability in a single forward pass, across two model families (K2-Horizon and…

Holy Grail Math 6.5 Rigor 8.0
Costs: Not applicableOut-of-sample: Walk-forwardResolution: Daily Data
More details
Evaluation
Forecast accuracy

Interpretable Allocation and Model-Predictive Rebalancing of Equity Portfolios, Tested on Real and Synthetic Markets

Varner

A live equity portfolio poses three problems: which stocks to hold, when to trade, and whether the strategy holds up beyond the observed market. We built one system for all three and tested it on 373 US equities, calibrated on 2014-2024 and traded from January 2025 to September 2026. A selection…

Holy Grail Math 6.5 Rigor 8.0 Code
Costs: ModeledOut-of-sample: HoldoutResolution: Daily Data
More details
Evaluation
Trading P&L

Optimal Annuitization, Consumption, and Investment with Costly Capital Injections

Huang et al.

We study a joint optimal decision of portfolio, consumption, and annuitization for a pension-plan manager who balances retirement consumption benefits against the cost of maintaining the solvency of pension account. The pension sponsor provides costly capital injection to prevent negative wealth.…

Holy Grail Math 9.0 Rigor 6.0
More details
Authors
Yijie Huang, Xiaoqing Liang, Jie Xiong, Xiang Yu

PanelGP: A Probabilistic Factor Model for Asset-Return Panels

Ruglioni et al.

We develop PanelGP, a conditional factor model for large panels of stock returns in which firm characteristics determine the factor loadings and economic conditions determine the expected factors. Both relations are estimated nonparametrically with Gaussian-process priors. The kernel choice nests…

Holy Grail Math 8.5 Rigor 8.0 Code
Costs: ModeledOut-of-sample: Walk-forwardResolution: Weekly-Monthly Data
More details
Authors
Andrea Ruglioni, Damir Filipovic
Evaluation
Trading P&L

Penalize the Common Trade: A Collision-Aware Layer for Learned Portfolios

Benhamou et al.

Different learning systems can make nearly the same trade when they share data, objectives, or representations. The market then sees decision concentration even if the models look diverse. We call exposure to this shared direction a signal collision. A linear-impact game shows the basic…

Holy Grail Math 7.5 Rigor 6.0 capped
Costs: ModeledOut-of-sample: UnclearResolution: Weekly-Monthly Data
More details
Authors
Eric Benhamou, Jean-Jacques Ohana, Beatrice Guez, Ethan Setrouk, Chamyl Saadi, Thomas Jacquot
Evaluation
Trading P&L

Robust distortion riskmetrics over Bregman--Wasserstein balls and their intersections

Liu et al.

We study the worst-case values of distortion riskmetrics over Bregman–Wasserstein balls around a reference distribution. Unlike the squared 2-Wasserstein distance, Bregman–Wasserstein divergences can penalize upward and downward deviations differently. Our main result applies to generalized…

Lab Rats Math 9.0 Rigor 4.0
More details
Authors
Peng Liu, Steven Vanduffel, Carole Bernard