Skip to main content
WeiMindWeiMind
ChineseView Course
Quant Radar

Content Formats

Paper Research Latest Activity

Research from arXiv, SSRN, and large funds: prioritize papers that provide data, code, and out-of-sample tests.

124 related activitiesLast 30 days 97 itemsFeatured among them 1 items

Updated

Activity Archive · Page 3 页

20 OctTueIssue 41–60 items
  1. arXiv q-fin46

    TRACE: Governing AI-Assisted Research Through Computer Science Principles

    Researchers have distilled five principles from established practices in software engineering and security research to form the TRACE framework for governing AI-assisted research, covering five dimensions: record tracking, source verification, independent acceptance, process control, and correction evaluation. The framework is accompanied by the open-source operating system TRACE-OS, which can adapt to researchers' existing workflows, helping teams maintain control over their research work when adopting AI and promoting the establishment of trust standards for AI-assisted research.

    Read original
  2. arXiv q-fin38

    How to Distinguish Liquidity-Constrained Default from Strategic Default Using Deep Learning

    Researchers used proprietary panel data of commercial mortgages from 1998 to 2021 and adopted deep neural networks (DNN) to distinguish liquidity-constrained default from strategic default. The study found that, under delinquency conditions, property net operating income (NOI) has a more significant impact on default rates than loan-to-value ratio (LTV), and the threshold for dividing the two types of defaults remained stable during the 2008 financial crisis and the 2020-2021 COVID-19 commercial real estate shock.

    Read original
  5. arXiv q-fin53

    Research on Inferring Implied Risk-Neutral Density from Irregular Option Quotes

    Published at ICAIF 2026, this study finds that accurate option prices do not necessarily mean accurate recovery of the underlying risk-neutral density. By comparing synthetic simulation benchmarks with out-of-sample NIFTY option benchmarks, the research reveals that the two-component lognormal mixture model demonstrates overall pricing performance on synthetic benchmarks.

    Read original
  6. arXiv q-fin34

    Certifiable Neural Operators for Simultaneously Solving Infinitely Many Convex Programs: Logarithmic Rank and Linear Complexity

    This arXiv paper proposes proximal equilibrium operators (PEOs), constructed via finite-dimensional deep equilibrium layers, that can solve a family of convex optimization problems on separable Hilbert spaces. The paper proves that when input loss functions lie in a suitable infinite-dimensional set, PEOs can uniformly approximate corresponding solutions to arbitrary precision, with rank and width growing only logarithmically with the inverse of approximation error, and depth growing linearly. The related theory and trainability have been validated across three application domains: nonlinear PDEs, stochastic optimal control, and financial portfolio optimization and hedging.

    Read original
19 OctMon
  1. Quantpedia64

    Study Finds Classic Bitcoin Price Cycle Indicators Gradually Losing Effectiveness, While Halving Clock Remains Stable

    Quantpedia analyzes a paper by Josh Molnar published on SSRN, noting that classic Bitcoin cycle signals such as MVRV, Mayer Multiple, and Pi Cycle Top are gradually losing effectiveness as price volatility narrows. The three mature cycle peaks occurred 525, 546, and 534 days after their respective halvings.

    Read original
  2. English translation is being prepared.22

    Hang Seng Index Quarterly Review Preview: CICC Expects Zijin Gold International and Others to Join Blue Chips, Hang Seng Tech Index to Add 20 Constituents

    CICC released a preview forecast for the Hang Seng Index quarterly review, expecting Zijin Gold International and other companies to be included in the Hang Seng Index blue-chip constituents. The Hang Seng Tech Index is expected to see a significant expansion, with 20 new constituents added.

    Read original
  3. Quantocracy31

    Quantocracy's Latest Quant Research Link Roundup as of October 18, 2026

    Quantocracy has compiled the latest quant research-related links as of October 18, 2026, covering topics including trend following, futures continuous contract construction, in-sample to out-of-sample Sharpe ratio decay, the impact of liquidity on stock returns and option pricing, and cryptocurrency cross-sectional trend factors. One study based on 12 commodity futures found that the expected retention ratio of in-sample Sharpe ratios from a 10-year backtest on new data is 30%.

    Read original
  4. arXiv q-fin23

    Board Gender Diversity and Emissions Performance: Findings from Panel Regression, Machine Learning, and Explainable AI

    A study of European firms from 2016 to 2022, combining panel regression, machine learning, and explainable AI methods, finds a nonlinear relationship between board gender diversity and emissions performance: emissions performance begins to improve significantly when female director representation reaches a minimum threshold of approximately 22%, and further increases in female representation beyond an optimal level of approximately 35% do not yield additional emissions performance gains.

    Read original
  5. arXiv q-fin33

    Power-Law Relationship Between Skew and Curvature in Stochastic Volatility Models with Infinite Variation Lévy Jumps

    This paper focuses on the impact of hybrid dynamics (rough volatility and infinite variation Lévy processes) on the implied volatility skew and curvature of at-the-money options. By analyzing the leading terms of their short-time expansions, the origin mechanism of the power-law behavior of skew and curvature can be determined from the hybrid dynamics model. The paper confirms that hybrid models also produce power-law relationships, and the relevant conclusions are crucial for model design and calibration. Numerical evidence for the rough Heston model with CGMY Lévy jumps is also provided.

    Read original
  6. arXiv q-fin49

    How Language Model Agents Are Reshaping Price Competition

    Research shows that large language model pricing agents can deviate from the repeated Bertrand competition benchmark where prices converge to marginal costs in homogeneous goods markets, with their performance depending on deployment decisions. Whether LLM pricing agents can maintain prices above marginal costs in self-play is directly related to deployment choices: whether they set prices period-by-period based directly on raw market history including competitor prices, or periodically output probability distributions based on summaries of their own profit history.

    Read original
  7. arXiv q-fin47

    AI Agents in Automated Markets

    The research team built behavioral models for three types of trading agents—rational arbitrageurs, manipulators, and retail momentum followers—based on reinforcement learning, and conducted a pilot study on hourly cryptocurrency data (AAVE, ETC, SUI). The results show that the behavioral characteristics of different agents have differentiated impacts on market pressure, liquidity, volatility, and risk-adjusted returns. The research conclusions support formulating differentiated regulatory rules for different behavioral types, rather than uniformly restricting volatility or turnover rates.

    Read original
  8. arXiv q-fin44

    OrderFlowDiT: A Transport-Regularized Diffusion Transformer for Probabilistic Limit Order Supply Prediction

    Researchers propose OrderFlowDiT, a conditional diffusion Transformer trained with an unbalanced optimal transport (UOT) auxiliary loss, to predict the conditional distribution of limit order submissions over the next five minutes. Across 1,950 validation conditions covering 30 U.S. stocks, adding UOT reduces the full-field transport cost by 45.8% and the transport energy score by 26.1% compared with training using only mean squared error, with improvements in both metrics for every stock.

    Read original
  9. arXiv q-fin43

    From Alpha to Execution: Trading Horizon, Market Regimes, and Execution Schedules under Concave Impact and Hurst Scaling

    This study analyzes trade execution under concave power-law impact and Hurst-scaled price fluctuations. It determines the optimal execution horizon by maximizing the Sharpe ratio of realized trading P&L and identifies conditions for an interior optimum. The derived execution schedule can reduce envelope costs by 10-17% compared to a TWAP schedule over the same duration. The results are published on arXiv.

    Read original
  10. arXiv q-fin47

    Study on the Impact of Shared Action Ordering on Executed Credit for LLM Borrowers in a Simulated Lending Market

    An experiment on a simulated collateralized lending market shows that shared action ordering significantly affects the scale of executed credit for LLM borrowers. The experiment set up 12 ordinary order markets and 12 balanced order markets, using an exact randomization test to obtain a two-sided p-value of 2/8100, with a credit difference of 1.12 units of initial unused reference borrowing capacity between leverage-prioritized and deleveraging-prioritized ordinary order markets. No liquidations or actual bad debts occurred in all 24 markets; under the fixed-price 30% shock benchmark, most write-offs came from collateral consumed by liquidation bonuses.

    Read original
  11. arXiv q-fin37

    Merton Consumption-Investment Problem under Different Stochastic Integral Conventions

    This study examines the Merton consumption-investment problem under the Itô, Stratonovich, and Hänggi-Klimontovich conventions, corresponding to stochastic integral convention parameter α = 0, 1/2, and 1, respectively. The study finds that if the drift term is transformed synchronously, the optimal investment strategy is unaffected by the choice of convention; if the drift coefficient value is fixed, the investor's opportunity set will change. Under logarithmic utility, consumption decisions are unaffected, but the optimal portfolio weights shift, and the stochastic integral convention cannot be identified using return data alone.

    Read original
  13. arXiv q-fin46

    Cross-Product Modeling in Continuous Intraday Electricity Markets Based on Hawkes Processes

    This paper proposes a multivariate state-dependent Hawkes process (SDHP) to model cross-product liquidity dynamics between quarter-hourly and hourly contracts in the Dutch EPEX SPOT continuous intraday market. The model is calibrated using Level 3 order book data from the first month of each quarter in 2024, dividing trading sessions into normal and stress states. The study finds that approximately 95% of orders are driven by their own order flow, with cross-excitation primarily flowing from quarter-hourly contracts to hourly contracts, and this dominance significantly weakens in stress states.

    Read original