Skip to main content
WeiMindWeiMind
ChineseView Course
Quant Radar

Research Directions

Risk Management Latest Activity

Methods for position sizing, drawdowns, tail risk, and stress testing.

49 related activitiesLast 30 days 35 itemsFeatured among them 0 items

Updated

Risk Managementrelated activities

20 OctTueIssue 1–20 items
  1. arXiv q-fin31

    Optimal Loss Allocation and Reflected Free Boundaries in Systemic Risk

    This study focuses on the allocation of bank default losses without external capital injection, proving that for all non-decreasing concave terminal payoffs, the "tax the richest" truncation rule is optimal. The study constructs a continuous-time optimal solution through time discretization, characterizes the optimal flow as a novel reflected free boundary problem, and proves the positive time smoothness of the free boundary and the density of surviving banks.

    Read original
  2. arXiv q-fin67

    Conformal Kelly: Why Economic Performance Fails to Materialize When Marginal Coverage Targets Are Met

    The paper proposes using the half-width of conformal prediction intervals as a scaling measure for fractional Kelly position sizing with a leverage cap, and tests this rule under a pre-registered protocol. During the development phase, an autonomous LLM agent searched approximately 200 configurations on a 2016-2021 sample of 8 U.S. equity ETFs, with subsequent data sealed before the search, and the final configuration, 9 comparison portfolios, and conclusion mapping all registered before unsealing.

    Read original
  3. arXiv q-fin34

    Coherent Risk Research under Finite Models

    This research in quantitative financial risk management proves that when estimates remain unchanged after replicating all scenarios, binary estimators can accurately describe the same population risk and recover the population dual set from finite models. The study derives Wasserstein, Kolmogorov, and total variation norms under bounded support based on Bernoulli loss risk, characterizes uniform estimability, provides impossibility bounds for arbitrary stochastic estimators, and further derives uniform regret bounds for data-driven risk-averse optimization, with applications in stop-loss retention scenarios.

    Read original
  4. arXiv q-fin33

    On the Utility Problem in Markets with Instantaneous Price Impact

    For a discrete-time financial market model with trades having instantaneous price impact, the existence of a solution to the corresponding utility maximization problem is proven. This study removes the unnatural restrictions on market depth and resilience processes present in earlier work, with the non-standard feature of this problem being that the set of attainable portfolio values may not satisfy convexity.

    Read original
  5. arXiv q-fin53

    Exact Risk Calculation for Candidate Scoring Decision Models: Analysis of the Impact of Teacher Supervision, Fixed Representations, and Calibration

    A new arXiv paper uses Gaussian surrogate models to precisely calculate the finite-sample risk of candidate scoring decision models, analyzing the boundaries of the role of three training elements: teacher soft targets, frozen pre-trained backbones, and temperature calibration. The paper points out that after a student model inherits teacher bias, more student data cannot eliminate that bias; fixed representations only reduce risk below an explicit sample size threshold; under the probit model, exact recalibration maps to temperature scaling, and can only eliminate all excess risk when the direction of the teacher's coefficients is correct.

    Read original
  6. arXiv q-fin64

    arXiv Paper: The Control Layer Behind Rule-Following Trading Agents Across Cross-Market Quotes

    This arXiv paper tests the degree to which 4 AI trading agents adhere to their own strategies and risk rules, based on 2627 closed trades from February 12 to August 27, 2026. 18% of the trades were live orders on Hyperliquid, while the rest were simulated at real-time prices, with a uniform round-trip fee of 0.09%.

    Read original
  7. arXiv q-fin57

    Conditional Weight of Evidence for Gradient Boosting Credit Models: Estimation Methods, Additivity, and Their Relationship with Adverse Behavior Causes

    This arXiv paper proposes a conditional weight of evidence method to measure the marginal impact of a single credit feature on the log odds of default, given the rest of an applicant's credit information. The same feature value can yield different evaluations for applicants with different credit backgrounds.

    Read original
  8. arXiv q-fin38

    A Dynamic Programming Approach for Value-at-Risk Markov Decision Processes in Continuous Spaces

    This study is the first to prove the validity of dynamic programming equations for Value-at-Risk Markov Decision Processes (VaR MDPs) in continuous spaces, covering both finite-horizon and infinite-horizon scenarios. Previously, related dynamic programming equations had only been derived and verified in finite state and action spaces, leaving the continuous-space problem unresolved for a long time. This framework can be used to characterize optimal dynamic strategies for optimal execution problems with VaR objectives, solving an open problem in the field.

    Read original
  9. arXiv q-fin55

    Probability Weighting Functions for Normal Tempered-Stable Distributions: Orthogonal Channels and Information-Theoretic Indices

    This arXiv paper proposes constructing probability weighting functions from changes in return distributions rather than parameter families, with the formula w(p)=F_post(F_prior^{-1}(p)). Both the prior and posterior are normal tempered-stable distributions, and the posterior differs from the prior along three independent channels—scale, skewness, and tail thickness—under the premise of fixed variance.

    Read original
  10. arXiv q-fin55

    Amortized Neural Filtering for Calibrating Posteriors in Statistical Arbitrage

    The paper proposes a Neural Filter Estimator (NFE), trained on simulated paths of mean-reverting processes, that outputs the posterior distribution of the implied state for each spread in the cross-section in a single forward pass, incorporating estimation uncertainty into trading decisions. On simulated paths with known ground truth, the method achieves accuracy comparable to other practical estimators, with its advantage lying in correctly characterizing its own uncertainty.

    Read original
  11. arXiv q-fin45

    No-Arbitrage Implied Volatility Surface Reconstruction via Additive Martingales

    This paper proposes AddMart, a few-shot implied volatility surface reconstruction framework that embeds no-arbitrage structure into the architecture to achieve global static no-arbitrage, enabling continuous and valid surface generation from a small number of option quotes. Experiments on 10 real-world option datasets show that the framework delivers competitive reconstruction accuracy with no significant static arbitrage violations, and can be directly applied to VaR, CVaR and crash probability estimation.

    Read original
  12. arXiv q-fin37

    The value of optimal trading filters and predictive signals

    This paper addresses the stationary quadratic trading problem with transient price impact, deriving optimal trading strategies using predictive theory tools, expressed as a combination of conditional predictions and explicit causal linear filters. The paper recovers the Gârleanu-Pedersen target portfolio under the exponential elasticity assumption, derives fractional trading filters under power-law impact decay, and clarifies the mechanisms determining the net realizable value of predictive signals under different trading cost scenarios.

    Read original
  13. 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. CFA Institute Research and Policy Center: Publications54

    A veteran former fund manager used AI to test his lifelong investment strategy

    A former equity strategy partner and independent investment firm operator used AI in retirement to backtest his long-standing personal strategy, which combined Peter Lynch's growth stock selection, Hilary Kramer's undervalued obscure stock selection, and earnings revision discipline. He corrected for survivorship bias, used point-in-time data, calculated pre-fee returns, and compared it against random stock selection from the same investment pool. The results showed that the strategy did not outperform random selection, with ordinary index funds performing better than the strategy.

    Read original
  2. 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
  3. 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
16 OctFri
15 OctThu
  1. Hong Kong Monetary Authority: Press Releases35

    HKMA launches "ART" framework to promote responsible AI adoption in the banking sector

    The HKMA launched the "ART" framework on October 15, centered on the core principles of Accountability, Resilience, and Trust, to support the banking sector in responsibly adopting artificial intelligence. The framework includes the release of the latest regulatory guidelines on responsible AI adoption, the joint establishment of an AI training data sharing platform, and the advancement of agentic AI application testing. Concurrently, the HKMA and Cyberport co-hosted a two-day "Finance + AI Forum," marking the successful completion of the second phase of the Generative AI Sandbox technical testing.

    Read original