--- title: Quant Letter No. 134: October 2026, Week 2 url: https://www.ml-quant.com/issues/2026-10-09/ site: ML-Quant (https://www.ml-quant.com) updated: 2026-10-09 license: Summaries CC BY 4.0; links go to the original sources index: https://www.ml-quant.com/llms.txt issue_date: 2026-10-09 --- # Quant Letter: October 2026, Week 2: Weekly quantitative finance newsletter *This week centers on AI systemic risk, factor discovery limits, and monetary transmission channels. Agentic AI systems create non-diversifiable contagion floors despite fleet size; automated factor mining shows no paradigm dominates; and Fed policy transmits primarily through risk appetite shifts rather than rates. See "Agentic AI and Systemic Risk," "FactorBench," and "Risk Appetite and Monetary Transmission."* ## Top picks ### 1. [Agentic AI and Systemic Financial Risk](https://arxiv.org/abs/2610.08806) · arXiv ### 2. [Quantitative Equity Evolution: Constraints and Alpha Decay](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7566701) · SSRN ### 3. [Risk Appetite and Monetary Transmission](https://econpapers.repec.org/RePEc:fip:fedfwp:103796) · RePEc ### 4. [FactorBench: Benchmarking Automated Factor Mining](https://arxiv.org/abs/2610.06947) · arXiv ### 5. [LLM Factor Discovery and Evidence Scarcity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7555699) · SSRN ## What's rising ### Housing: 36 papers this week, 1.8× the usual 20 ### ETFs and funds: 34 papers this week, 1.6× the usual 21.9 ### Volatility forecasting: 20 papers this week, 1.5× the usual 13.7 ## GitHub radar ### Quant repos rising #### [jarrodwatts/jev-trader](https://github.com/jarrodwatts/jev-trader): AI trading agent executing trades on Monad blockchain. (3 quants, 2,912 stars, +167 this week, new repo) #### [Yijia-Xiao/FinanceHarness](https://github.com/Yijia-Xiao/FinanceHarness): Autonomous financial deep research framework. (2 quants, 196 stars, +8 this week, new repo) #### [TNT-Likely/PanWatch](https://github.com/TNT-Likely/PanWatch): AI stock monitoring for A-shares, HK and US markets. (2 quants, 2,047 stars, +104 this week) ### What quants are playing with #### [morluto/rea](https://github.com/morluto/rea): Reverse engineer apps and binaries using AI agents. (35 quants, 37.0k stars, +36.6k this week) #### [storytold/photocraft](https://github.com/storytold/photocraft): Open-source Rust reimplementation of Adobe Photoshop. (22 quants, 32.1k stars, +32.0k this week, new repo) #### [openai/math](https://github.com/openai/math): Mathematics library in Lean. (21 quants, 12.8k stars, +12.8k this week, new repo) #### [Niko1221/Strata](https://github.com/Niko1221/Strata): Run Qwen3.8-Flash on consumer hardware with local APIs. (13 quants, 19.2k stars, +12.3k this week, new repo) #### [tester-army/e2e](https://github.com/tester-army/e2e): End-to-end testing framework for web and mobile apps. (7 quants, 8,332 stars, +6,418 this week, new repo) #### [boykopovar/AnyPS5](https://github.com/boykopovar/AnyPS5): Tool for porting PS5 executables to Linux and Windows. (7 quants, 19.6k stars, +16.6k this week, new repo) ## We called it ### [Dynamic resource allocation with karma: An experimental study](http://arxiv.org/abs/2404.02687v2): now published in Journal of Economic Behavior & Organization (featured 8 Jan 2025; 4 citations) ### [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://arxiv.org/abs/2402.00299): passed 50 citations (featured 7 Feb 2024, 6 days after release) ### [A comparison of cryptocurrency volatility-benchmarking new and mature asset classes](https://arxiv.org/abs/2404.04962?utm_source=dlvr.it&utm_medium=twitter): passed 25 citations (featured 10 Apr 2024, 3 days after release) ## arXiv __[Agentic AI and Systemic Financial Risk](https://arxiv.org/abs/2610.08806)__: The study shows that agentic AI systems sharing a foundation model create non-diversifiable common exposure whose systemic risk floor does not shrink as the fleet grows, shifting concern from individual model risk to population-level contagion. (2026-10-08, fanfare: 4) ![2: The set-valued risk measure \rho(X) . The acceptable set of containment configurations (green), coloured elsewhere](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-01-44530988.png) __[FactorBench: Benchmarking Automated Factor Mining](https://arxiv.org/abs/2610.06947)__: A portfolio-aware benchmark comparing five thousand factors from nine automated mining methods across five equity markets finds that no discovery paradigm consistently dominates in signal quality or portfolio performance. (2026-10-07, fanfare: 4) ![Overview of FactorBench](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-02-5c0da455.png) __[Financial World Modeling with Market-1T](https://arxiv.org/abs/2610.09048)__: The study introduces a trillion-observation U.S. equity dataset and systematically evaluates 18 representation-learning methods across nearly two decades, finding that encoders with similar predictive performance organize market state very differently. (2026-10-08, fanfare: 4) ![Paper overview](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-03-d2723b48.png) __[How LLMs Fill Missing Financial Information](https://arxiv.org/abs/2610.07798)__: When financial facts are withdrawn from prompts, identity attributes explain 96% of variation in equity allocation advice from a language model, replacing missing evidence. (2026-10-07, fanfare: 4) ![Mean identity swing in equity allocation versus evidence level with 95% confidence interval band.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-04-8b80af07.png) __[AlphaPADI: Pool-Aware Formulaic Alpha Discovery](https://arxiv.org/abs/2610.04959)__: Introduces a hierarchical discrete diffusion framework that generates pools of formulaic alphas by reconstructing complete candidate pools under current context and maximizing joint predictive performance and inner diversity. (2026-10-06, fanfare: 3) ![Cumulative returns comparison of AlphaPADI against baseline methods on CSI300 from 2023-2025.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-05-9577d8ca.png) __[VIX Decomposition: Probability and Severity](https://arxiv.org/abs/2610.03849)__: Separating risk-neutral shortfall probability from conditional severity in option prices shows that severity accounts for 91.5 percent of recession log premium movements, supplying joint empirical restrictions on uncertainty and economic activity. (2026-10-06, fanfare: 3) ![Monthly 30-day downside protection premium and VIX. Panel (a) compares the VIX with the fixed benchmark](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-06-373eddc5.png) __[Stock-JEPA: Prior-Anchored Representation Learning](https://arxiv.org/abs/2610.07006)__: A joint-embedding framework learns predictable incremental revisions from market data relative to a financial prior, combining interpretability from classic models with the pattern-capture strength of deep learning. (2026-10-07, fanfare: 3) ![Predictive utility across market states](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-07-b72a51b8.png) __[Compact Transformers for Limit Order Forecasting](https://arxiv.org/abs/2610.02917)__: MBOFormer and MBOFusion, two causal transformers with under 70 kilobyte serialized state, predict limit order book price trends with sub-millisecond latency across three markets and four prediction horizons. (2026-10-05, fanfare: 3) ![Architectures of our two L3-based models](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-08-8ad95c68.png) __[Neuroevolution for Stock Return Prediction](https://arxiv.org/abs/2610.07825)__: Tiny neuroevolved recurrent networks rank first on both forecast accuracy and daily long-short returns across four portfolios, outperforming larger transformers and proving that forecast accuracy does not guarantee trading profit. (2026-10-07, fanfare: 3) ![Rank IC as a function of scoring horizon Plot showing Rank IC as a function of scoring horizon](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-09-e68f5369.png) __[Admission Gates for Strategy Research](https://arxiv.org/abs/2610.07701)__: An injected-truth protocol reveals that statistical admission gates eliminate false discoveries in weak-signal regimes but cut adoption rates to 1–7 percent, while criteria computed on absolute rather than excess returns reject all candidates. (2026-10-07, fanfare: 3) ![Panel I (400 repetitions)](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-10-6ce485cd.png) __[Earnings Disclosure Alignment via Optimal Transport](https://arxiv.org/abs/2610.04094)__: Decomposing earnings press releases and conference calls into shared and unique textual components shows that unique call content predicts returns better than repeated material. (2026-10-06, fanfare: 3) ![Average Returns (%) Sorted by Surprise and Soft Average return heatmap, sorted by soft and surprise](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-11-63c15178.png) __[LiveMACE: Process-Aware LLM Agent Evaluation](https://arxiv.org/abs/2610.09872)__: A benchmark evaluates frontier LLMs as live trading agents and finds that realized returns often diverge from capability-specific measurements, revealing outcome-capability gaps through decision traces. (2026-10-08, fanfare: 3) ![LiveMACEBench overview](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-12-39288c40.png) __[Agentic ETFs as Emerging Asset Class](https://arxiv.org/abs/2610.06856)__: Proposes that large-language-model-driven trading agents delegated to autonomous execution define a nascent asset class, mapping infrastructure layers and projecting potential trillions in assets by 2030. (2026-10-07, fanfare: 3) ![Actively managed ETF assets under management, actuals and industry projection](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-13-94d3062c.png) __[MintEval: Behavioral Testing for Trading Code](https://arxiv.org/abs/2610.03080)__: Introduces a benchmark that compares LLM-generated trading code to reference strategies bar by bar on identical data, revealing silent failures in implementation despite passing functional tests. (2026-10-05, fanfare: 3) ![Closed setting: SpecMatch vs ActionMatch per task](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-14-4f740cdb.png) __[TradeGrad: Textual Gradient Strategy Optimization](https://arxiv.org/abs/2610.03128)__: Proposes an LLM-guided framework for trading strategy refinement using accumulated experience and cross-period robustness, achieving 27.99% annualized return on Chinese equities with 1.63 Sharpe ratio. (2026-10-05, fanfare: 3) ![Evolution of a final strategy along its ancestral lineage](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-15-9b5f31d2.png) __[Latent Continuum of Limit Order Book Regimes](https://arxiv.org/abs/2610.05740)__: Analysis of high-frequency limit-order-book geometry finds market states form a continuous structure with a dominant latent coordinate capturing between 83.66% and 85.27% of covariance variation. (2026-10-06, fanfare: 3) ![Time series of stress-dial dynamics across three covariance windows, 2022-2025.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-16-b7432ccc.png) __[Algorithmic Greenwashing Detection in ESG](https://arxiv.org/abs/2610.02225)__: Fuses SEC financials with EPA emissions data and conformal machine learning to quantify divergence between self-reported and physical emissions, finding algorithmic divergence predicts lower valuation and profitability. (2026-10-05, fanfare: 3) ![Uncertainty Quantification via Mondrian Conformal Prediction (Discrete Bounds)](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-17-fb889fb1.png) __[Expected Utility Regret Rule for Portfolio Choice](https://arxiv.org/abs/2610.02290)__: Proposes a portfolio rule that simultaneously selects class and estimates weights to minimize expected utility regret, attaining both minimax and Bayes lower bounds without requiring prior information. (2026-10-05, fanfare: 3) ![Moment separation: worst-case expected utility regret over the two orderings of return distributions with identical](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-18-48b891ea.png) __[Adversarial Training for Deep Hedging](https://arxiv.org/abs/2610.07162)__: WRAP combines Wasserstein reweighting and optimal-transport perturbations in a distributionally robust framework to make deep hedging policies robust to nonstationarity and distributional drift in market conditions. (2026-10-07, fanfare: 3) ![Loss landscapes across deep-hedging training schemes from Table 1 : (A) ERM-W , (B) \phi -W , (C) OT-W , and (D) WRAP-W](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-19-5c03f47c.png) __[When LLM Agents Should Trust Memory](https://arxiv.org/abs/2610.11732)__: MemTrial uses factorial design to isolate what each memory contributes to portfolio decisions by crediting experiences with their marginal effect rather than shared market moves. (2026-10-09, fanfare: 3) ![Comparison of existing agent approach versus MemTrial's memory trust mechanism with factorial design](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-20-e6c9f2c4.png) __[Ranking Prior Alignment for Credit Risk](https://arxiv.org/abs/2610.11146)__: A model-agnostic framework distills ranking priors from experts or teacher models into credit scorers via KL divergence, improving cold-start performance with scarce labeled data. (2026-10-09, fanfare: 3) ![Robustness checks and ablation studies](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-21-115679c0.png) __[Execution Assumptions in LLM Trading Benchmarks](https://arxiv.org/abs/2610.05077)__: Varying execution realism from ideal fills to latency and impact reshuffles rankings of LLM and classical trading policies, showing how backtest conventions affect headline results. (2026-10-06, fanfare: 3) ![Kendall \tau\_{b} between the E0 ranking and each stressed ranking](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-22-92c85ddc.png) __[Credal Machine Learning for Risk-Averse Decisions](https://arxiv.org/abs/2610.12115)__: A method represents epistemic uncertainty with credal sets and combines them with a decision rule that avoids catastrophic predictions under conditional value-at-risk minimization. (2026-10-09, fanfare: 3) ![Set size and accuracy versus corruption severity, showing CreWare adapting set size with degraded accuracy.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-23-8c4c6f36.png) __[Robust CVaR Portfolio Selection with Penalties](https://arxiv.org/abs/2610.09246)__: Derives a closed-form expression for worst-case conditional value-at-risk under reward-penalty mechanisms and distribution uncertainty, enabling optimal portfolio allocations that balance losses with downside risk. (2026-10-08, fanfare: 2) ![Cumulative wealth comparison of six portfolio models from 2010-2025 with clear legend and time series.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-24-23778d6b.png) __[HAN-Mamba: Multi-Scale Volatility Forecasting](https://arxiv.org/abs/2610.10323)__: Replaces transformers with selective state space encoders in a hierarchical architecture for realized volatility forecasting, reducing error to 0.1927 on the Optiver benchmark with 33 percent fewer parameters than the attention variant. (2026-10-08, fanfare: 2) ![Context-length scaling](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-25-49b3c3ef.png) __[StaFIR: Learned Stationarity-Aware Filters](https://arxiv.org/abs/2610.07430)__: A convex method learns causal filters that balance stationarity and input preservation for financial time series, adapting filtering strength to persistence while preserving signal similarity. (2026-10-07, fanfare: 2) ![Per-series forecast performance on the log five-day realized-variance series](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-26-4cf8b5c3.png) __[Regime-Aware Equity Correlation Matrices](https://arxiv.org/abs/2610.12166)__: Fitting separate dependence matrices to lower-tail, central, and upper-tail regimes reveals tail-driven co-movements that single Gaussian-copula structures systematically miss. (2026-10-09, fanfare: 2) ![Three regime-specific correlation matrices: lower-tail, middle-regime, and upper-tail heatmaps.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-27-6f3b5c5c.png) __[State-Dependent Hawkes Models in Electricity](https://arxiv.org/abs/2610.08169)__: A regime-switching Hawkes process models intraday electricity order flow across liquidity conditions, showing that stress mainly strengthens self-excitation rather than reshaping cross-side dynamics. (2026-10-07, fanfare: 2) ![Intraday electricity market evolution: mid-price, bid-ask spread, and trading volume over time.](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-28-5ac1b503.png) __[Stochastic Control for Goal-Based Investing](https://arxiv.org/abs/2610.10046)__: A framework characterizes optimal investment policies for reaching financial goals by deadline, revealing that policies can decrease in asset drift and need not converge to risk-free allocation. (2026-10-08, fanfare: 2) ![Goal reaching time distributions comparing hyperbolic and exponential discounting with different parameters](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-29-9b583a75.png) __[Robust Enhanced Index Tracking Under Uncertainty](https://arxiv.org/abs/2610.04221)__: Robust optimization models minimize worst-case loss and downside risk for enhanced indexing under distributional uncertainty, beating benchmarks and standard robust approaches in out-of-sample wealth. (2026-10-06, fanfare: 2) ![Cumulative wealth and Sharpe ratios of portfolios based on the M-ER, M-TSV, and M-V models under the uncertainty set](https://www.ml-quant.com/issues/2026-10-09/figures/arxiv-30-b31b0dba.png) ## SSRN __[Quantitative Equity Evolution: Constraints and Alpha Decay](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7566701)__: Surveys fifty years of quantitative investing as a history of changing implementation boundaries from diversification through machine learning, emphasizing alpha decay and the gap between research and production systems. (2026-10-08, fanfare: 4) __[LLM Factor Discovery and Evidence Scarcity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7555699)__: An autonomous agent evolved 940 factors over 17 days and finds that reusing backtest data inflates edge by a quarter to a third and in-sample improvement predicts worse performance. (2026-10-05, fanfare: 4) __[Fed Surprises: Rate-Path, Information, and Tone](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7560218)__: The study decomposes Federal Reserve announcements into three orthogonal shocks and traces each through the equity cross-section, finding rate-path surprises dominate while standard balance-sheet characteristics carry no additional power beyond beta and size. (2026-10-06, fanfare: 4) __[Firm-Level AI Exposure Predicts Returns Post-Launch](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7575518)__: A natural-language analysis of 13,757 firms finds AI exposure surged after ChatGPT and predicts 1.37 percent higher annual returns, though the effect is concentrated after the launch and driven by firm-specific factors. (2026-10-08, fanfare: 4) __[Monetary Policy Risk and Asset Prices](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7585438)__: Asset prices respond to monetary policy uncertainty around FOMC announcements; a New Keynesian model shows policy risk accounts for much of equity and inflation-bond risk premia and weakens activity when elevated. (2026-10-08, fanfare: 4) __[Volatility Targeting Over a Century](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7585278)__: Analyzing 100 years of daily data, the study finds volatility scaling harmed returns before 1985 but improved them after, a shift attributed to derivatives markets and deregulation, with walk-forward Sharpe ratio of 1.01. (2026-10-08, fanfare: 4) __[Multi-Strategy Quantitative Portfolio](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7561158)__: Eleven systematic strategies across equities, futures, and currencies achieve a 1.91 Sharpe ratio net of costs from January 2012 to June 2026, with 23.6% compound annual return. (2026-10-07, fanfare: 4) __[Demographics, Debt, and Equity Risk Premia](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7570178)__: A two-country model attributes 251 basis points of U.S. equity premium gains and 71 basis points of global rate decline since 1980 to demographic aging. (2026-10-07, fanfare: 4) __[Pre-registered Testing of Trading Signals](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7553278)__: Applies a strict pre-registered protocol to eleven trading signals across equity and futures markets, finding only trend survives development and hold-out periods with borderline significance after multiple-testing adjustment. (2026-10-03, fanfare: 3) __[Cross-Sectional Risk and Corporate Bond Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7566162)__: Constructs a characteristics-based systematic risk measure using rate jumps that predicts out-of-sample corporate bond returns, with high-minus-low decile portfolio earning 9.12% annually and 7.80% alpha. (2026-10-05, fanfare: 3) __[The Price of Conviction in Asset Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7571098)__: The study shows that high-conviction beliefs exert outsized influence on prices, with a long-short portfolio exploiting conviction-weighted disagreement earning 13.2 percent annualized six-factor alpha. (2026-10-07, fanfare: 3) __[LLM Agents Build Auditable Equity Alpha Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7568638)__: An autonomous research loop in which agents propose factor candidates and code verifies them builds multi-factor alpha models, screening 212 predictors and admitting 14 that raise baseline information coefficient out-of-sample. (2026-10-07, fanfare: 3) __[White-Box Alpha Mining with Quality-Control Loops](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7576913)__: GFlowAlpha uses neuro-symbolic search and internalizes econometric quality control as online rewards to mine white-box factors, delivering mean out-of-sample daily ICIR of 0.485 with Fama-MacBeth t-statistics of 4.99 on Chinese stocks. (2026-10-07, fanfare: 3) __[Deflated Sharpe Ratios Fail Under Adaptive Search](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7557458)__: The research proves that query-counted Deflated Sharpe Ratios certify noise in adaptive research and proposes sealed-holdout verification, where validity depends on bits revealed rather than strategy count. (2026-10-05, fanfare: 3) __[Long-Horizon Credit Spreads Test Pricing Kernels](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7570200)__: The study shows that Baa-Aaa spreads at 27-year maturity test pricing kernels better than shorter maturities, with a structural refinancing model matching observed spreads while prior kernels overpredict by 27 to 68 basis points. (2026-10-07, fanfare: 3) __[LLMs Reduce Information Frictions in Bonds](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7577906)__: Shows that large-language-model scores of default risk from earnings calls predict bond rating migration one year ahead where analysts disagreed, capturing information not yet priced in spreads. (2026-10-07, fanfare: 2) __[DeFi Token Revenue Surprises Predict Short-Term Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7566845)__: Revenue surprises on 95 DeFi protocols predict abnormal token returns, with one-standard-deviation surprises associated with 28.8 basis points higher returns over three days when tokens have direct revenue claims. (2026-10-06, fanfare: 3) __[Machine Learning Predicts Cryptocurrency Contagion](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7578304)__: The study forecasts time-varying return spillovers among cryptocurrencies using machine learning, finding monetary policy and funding rates drive connectedness and classifying events that shift spillover composition into contagion types. (2026-10-07, fanfare: 3) __[Bitcoin ETFs Tighten Spillovers from Equities](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7566372)__: The research shows that after U.S. Bitcoin ETF approval in January 2024, return and volatility linkages between Bitcoin and equities strengthened substantially, with volatility spillovers becoming markedly asymmetric from stocks to crypto. (2026-10-05, fanfare: 3) __[AI Exposure and Financial Stability Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7577948)__: The study measures AI exposure across 284 U.S. firms and finds that an AI-factor explains only 18% variance alongside conventional factors, suggesting AI is a distinct cross-industry risk lens separate from traditional spillovers. (2026-10-07, fanfare: 3) __[Causal Uplift Modeling for Credit Restructuring](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7556744)__: A causal framework compares six estimators of treatment effect to optimally assign debt restructuring interventions, revealing that targeting borrowers by predicted effect generates substantially positive value where blanket treatment fails. (2026-10-03, fanfare: 3) __[Exchange Rate Regimes and Term Premium Spillovers](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7588778)__: U.S. monetary tightening raises term premia sharply in pegged economies but not floating ones; a DSGE model shows pegs force adjustment through domestic rates, tightening leverage constraints and amplifying spillovers. (2026-10-09, fanfare: 3) __[Geopolitical Skewness Risk and Bond Premia](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7570538)__: A measure of cross-country geopolitical risk skewness predicts U.S. Treasury risk premia out-of-sample and forecasts weaker activity, adding incremental value beyond yield curves and standard macroeconomic predictors. (2026-10-07, fanfare: 3) __[Geoeconomic Fear and Sovereign Spreads](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7580558)__: The study constructs a geoeconomic fear index from news articles and finds that higher fear predicts wider emerging-market sovereign spreads, especially for speculative-grade issuers. (2026-10-09, fanfare: 3) __[Debt Maturity and Corporate Investment](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7589333)__: A global study of 357,630 firm-years shows firms with more short-term debt cut capital expenditure by 2.156 percentage points, mainly due to refinancing availability constraints. (2026-10-09, fanfare: 3) __[Common Banks Limit Supply-Chain Shocks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7588198)__: Using Portuguese wildfire data, the research finds firms whose banks also lend to suppliers experience 10 percentage points smaller credit declines and face attenuated real losses. (2026-10-09, fanfare: 3) __[Delta-Guided RL for Derivative Hedging](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7585078)__: A reinforcement learning method embedding Black-Scholes delta guidance cuts hedging error by 19-38% across simulated and real options data with robust statistical significance. (2026-10-08, fanfare: 3) __[Hybrid Graph Neural Network for RV Forecasting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7576359)__: A graph neural network combining temporal and cross-asset volatility patterns reduces mean squared error and quasi-likelihood loss by approximately 9.9% and 3.4% on Dow stocks. (2026-10-07, fanfare: 3) __[Expectations and Monetary Policy Transmission](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7588262)__: Optimal rate-setting creates time-inconsistency: market expectations become too sensitive to policy surprises, amplifying real effects of central bank forecast errors; less aggressive rules cut output volatility. (2026-10-09, fanfare: 3) __[Anomalies in Indian Equities and Real Costs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7551520)__: Well-documented Indian equity anomalies replicate strongly in-sample but all fail to survive 12 to 32 basis point retail transaction costs; required directional accuracy reaches 72% at hourly horizons. (2026-10-03, fanfare: 3) ## RePEc __[Risk Appetite and Monetary Transmission](https://econpapers.repec.org/RePEc:fip:fedfwp:103796)__: The research shows Fed policy affects risk asset prices primarily through risk appetite shifts, not interest rates; transmission via risk appetite dwarfs rate-channel effects. (2026-10-05, fanfare: 4) ![Rolling regression of RISK on MPS](https://www.ml-quant.com/issues/2026-10-09/figures/repec-01-7c1065f0.png) __[Treasury Yield Effects of Supply Demand](https://econpapers.repec.org/RePEc:fip:fedgif:103792)__: A demand-system framework quantifies that $100 billion in Treasury supply raises five-year yields by roughly 3 basis points, with effects driven by changing foreign and hedge-fund participation. (2026-10-05, fanfare: 3) ![Stacked area chart decomposing five-year yield changes into standard factors, market multiplier, and investor purchases](https://www.ml-quant.com/issues/2026-10-09/figures/repec-02-e09dc4cc.png) __[Dollar Collateral and Global Capital Flows](https://econpapers.repec.org/RePEc:ces:ceswps:_13008)__: A model shows U.S. Treasury collateral advantage drives dollar appreciation during stress and reconciles exorbitant privilege, financial intermediation, and convenience yield perspectives. (2026-10-05, fanfare: 3) ![US external dynamics during crises: NFA trends, exchange rates, capital inflows, and regression relationships.](https://www.ml-quant.com/issues/2026-10-09/figures/repec-03-34444440.png) __[Monetary Policy and Wealth Distribution](https://econpapers.repec.org/RePEc:bfr:banfra:1064)__: Rate cuts initially reduce wealth inequality but increase it medium-term; housing drives effects at the bottom while equities drive them at the top. (2026-10-05, fanfare: 3) ![Wealth share changes across distribution after interest rate shock over time](https://www.ml-quant.com/issues/2026-10-09/figures/repec-04-ddce3881.png) __[Financial Vulnerability Index for U.S. System](https://econpapers.repec.org/RePEc:fip:fedgfe:103791)__: An index capturing structural financial weaknesses displays gradual buildup before crises, predicts shock amplification, and reveals delayed monetary policy transmission effects. (2026-10-05, fanfare: 3) ![Fitted skewed-t distributional forecasts of GDP growth conditional on lagged GDP growth and FVI or NFCI. The fitted](https://www.ml-quant.com/issues/2026-10-09/figures/repec-05-1a035ab3.png) __[Credit Frictions and Aggregate Economic Output](https://econpapers.repec.org/RePEc:nbr:nberwo:35552)__: UK firm-level data shows relaxing credit frictions raises output by 25% and wages by 23%, with most gains from capital accumulation rather than reallocation. (2026-10-07, fanfare: 3) ![Output change comparing SME and large firms under low friction scenario, 2004 vs 2019.](https://www.ml-quant.com/issues/2026-10-09/figures/repec-06-cdd4f487.png) __[AI Intensity and Economic Shock Responses](https://econpapers.repec.org/RePEc:ces:ceswps:_13000)__: Industries with higher AI intensity show significantly higher returns and valuations when hit by supply and technology shocks but not demand shocks. (2026-10-08, fanfare: 3) ![Returns, valuations and volatility following a technology shock, excluding 2020](https://www.ml-quant.com/issues/2026-10-09/figures/repec-07-850b0734.png) __[A Currency Premium Puzzle](https://econpapers.repec.org/RePEc:nbr:nberwo:35572)__: The paper proves that asset pricing models solving equity and risk-free rate puzzles fail to generate observed interest-rate differentials between risky and safe currencies. (2026-09-26, fanfare: 3) ![Currency Premium in SDF Space](https://www.ml-quant.com/issues/2026-10-09/figures/repec-08-c0dad59b.png) __[The Implied Equity Term Structure](https://econpapers.repec.org/RePEc:fip:fednsr:103730)__: Inferring expected returns from stock prices and cash flows reveals an upward-sloping equity term structure, but value and speculative-grade firms show flat or downward slopes. (2026-10-09, fanfare: 3) ![Implied equity term structure showing return premia across maturity horizons in good and bad times.](https://www.ml-quant.com/issues/2026-10-09/figures/repec-09-71e432d8.png) __[Volatility Disagreement in Options Market](https://econpapers.repec.org/RePEc:nbr:nberwo:35500)__: Cross-sectional dispersion in volatility forecasts predicts delta-hedged straddle losses of 5.14% per month, consistent with mispricing rather than risk compensation. (2026-10-07, fanfare: 3) ![High-Minus-Low Decile Portfolios Based on VDIS conditional on Stock and Option Characteristics](https://www.ml-quant.com/issues/2026-10-09/figures/repec-10-0342c16d.png) __[ECB's Whatever It Takes and Bank Risk-Taking](https://econpapers.repec.org/RePEc:bdm:wpaper:2026-01)__: The ECB's "whatever it takes" announcement reversed euro area banks' risk appetite, reducing loan growth and credit risk, showing capitalization can curb lending during crises. (2026-10-05, fanfare: 3) ![Coefficient trend showing reversal in euro bank risk-taking post-announcement](https://www.ml-quant.com/issues/2026-10-09/figures/repec-11-af128d56.png) __[Global Firms and Capital Allocation](https://econpapers.repec.org/RePEc:nbr:nberwo:35652)__: A quantified general-equilibrium model of 23,000 firms across 48 countries shows financial and trade liberalization concentrate activity in largest firms with larger gains for emerging economies. (2026-09-26, fanfare: 3) __[Banker Outside Options and Credit Risk](https://econpapers.repec.org/RePEc:ajk:ajkdps:429)__: Improved job opportunities for bankers increase non-investment-grade lending and borrower risk without compensating spreads, raising systemic risk through weakened workplace discipline. (2026-10-09, fanfare: 3) ![Dynamic effects of risky loan volume growth and financial risk with confidence bands](https://www.ml-quant.com/issues/2026-10-09/figures/repec-13-8a4e0789.png) __[Policy Beliefs Drive Returns in Chinese Funds](https://econpapers.repec.org/RePEc:nbr:nberwo:35528)__: The study shows that mutual fund managers' policy beliefs predict market returns and explain positive alphas, while sentiment beliefs attract flows but lack predictive power. (2026-10-09, fanfare: 3) __[Distinguishing FX Shocks from Fundamentals in EMDEs](https://econpapers.repec.org/RePEc:imf:imfsdn:2026/003)__: A framework using deviations from interest-rate parity identifies when exchange-rate movements stem from financial shocks rather than fundamentals, aiding intervention decisions. (2026-10-05, fanfare: 3) __[Sentiment Arc Shape in Monetary Policy Communication](https://econpapers.repec.org/RePEc:onb:oenbwp:281)__: The sequencing and emphasis of sentiment within central bank statements predict rate decisions and inflation expectations beyond average tone alone. (2026-10-05, fanfare: 3) __[The Terra Luna Blockchain Run Dynamics](https://econpapers.repec.org/RePEc:ehl:lserod:137575)__: Granular blockchain data reveals the Terra crash resulted from subsidized money creation, real-time transaction visibility, and investor concentration amplifying financial fragility. (2026-10-07, fanfare: 3) ![Anchor's daily cash flow decomposition and balance decline through Terra collapse](https://www.ml-quant.com/issues/2026-10-09/figures/repec-17-d961ee1a.png) __[Continuous Time Models Beat HAR for Volatility](https://econpapers.repec.org/RePEc:boa:wpaper:202648)__: Fractional processes outperform discrete models like HAR for forecasting realized volatility at longer horizons by better balancing recent levels against long-run persistence. (2026-10-05, fanfare: 2) __[Asymmetric Inflation Risk and Monetary Policy](https://econpapers.repec.org/RePEc:bde:wpaper:2626)__: A model with time-varying skewness in cost-push shocks generates persistent stagflationary effects; optimal policy leans against the balance of inflation risks. (2026-10-02, fanfare: 2) ![Distribution shifts and responses to one-month shocks with asymmetric skewness distributions](https://www.ml-quant.com/issues/2026-10-09/figures/repec-19-bfb8d6fa.png) __[Energy Shocks and Euro Area Monetary Policy](https://econpapers.repec.org/RePEc:adl:wpaper:2026-07)__: A DSGE model reveals energy and exchange-rate shocks drive euro inflation volatility, and optimal policy can exploit the exchange-rate channel rather than looking through energy shocks. (2026-10-05, fanfare: 2) ![Drivers of headline inflation and GDP growth: a historical decomposition](https://www.ml-quant.com/issues/2026-10-09/figures/repec-20-f5678d00.png) __[Classifying Macro News from Asset Co-movements](https://econpapers.repec.org/RePEc:bca:bocsap:26-7)__: CLONE decomposes daily price moves into demand, productivity, inflation, and policy news using stocks, bonds, and inflation swaps; aggregate demand dominated until 2021. (2026-09-30, fanfare: 2) ![Variance Ratios The figure shows the variance ratios from equation 5 for the S&P 500 Index, 2-year U.S. Treasury yield,](https://www.ml-quant.com/issues/2026-10-09/figures/repec-21-d6c6a815.png) __[Term Spread Volatility Predicts Economic Activity](https://econpapers.repec.org/RePEc:hal:journl:hal-05740995)__: Treasury yield curve slope volatility forecasts industrial production and employment growth at medium and long horizons, outperforming term spread alone after the 2008 crisis. (2026-10-05, fanfare: 2) ![Estimated R2 when forecasting economic activity 6 months ahead using TS](https://www.ml-quant.com/issues/2026-10-09/figures/repec-22-4929ec80.png) __[Bayesian Shrinkage in High-Dimensional Panel VARs](https://econpapers.repec.org/RePEc:adl:wpaper:2026-05)__: A Bayesian spike-and-slab method improves high-dimensional panel VAR forecasting and reveals heterogeneous spillover structures in sovereign bonds and macro data. (2026-10-05, fanfare: 2) ![Posterior Dynamic Interdependencies Across the Euro Area](https://www.ml-quant.com/issues/2026-10-09/figures/repec-23-001f422a.png) __[Eurodollars and Bretton Woods Monetary Transmission](https://econpapers.repec.org/RePEc:aim:wpaimx:2625)__: US monetary tightening attracted capital through Eurodollar borrowing but did not transmit to foreign output, revealing continued financial segmentation despite offshore growth. (2026-10-05, fanfare: 2) ![Fed discount rate, fed funds rate, T-Bills rate, and Eurodollar rate from 1947-1973.](https://www.ml-quant.com/issues/2026-10-09/figures/repec-24-f7501234.png) __[Interest Rate Pass-Through in DeFi](https://econpapers.repec.org/RePEc:abo:neswpt:sp0003)__: The study finds that US risk-free rates predict stablecoin lending rates in decentralized finance, though transmission operates mainly through crypto-native factors like utilization. (2026-10-05, fanfare: 2) __[Optimal Currency Strategies Under CIP Violations](https://econpapers.repec.org/RePEc:nbr:nberwo:35498)__: Extending Campbell et al., the analysis shows empirically measured deviations from interest parity reverse optimal currency demands for emerging-market investors. (2026-09-26, fanfare: 2) __[Dollar Safe Asset Convenience Yields Persist](https://econpapers.repec.org/RePEc:nbr:nberwo:35742)__: Dollar safe asset convenience yields remain stable domestically since 2019 but decline globally relative to other currencies, with repo markets leading. (2026-09-28, fanfare: 2) __[Housing Volatility Spillovers and Policy Networks](https://econpapers.repec.org/RePEc:pre:wpaper:202630)__: A time-varying VAR network reveals supply-inelastic coastal markets absorb largest regulatory shocks and spillovers persist to monetary conditions and inflation expectations. (2026-10-05, fanfare: 2) ![Macroeconomic Policy and Financial Indicators](https://www.ml-quant.com/issues/2026-10-09/figures/repec-28-6f1edacb.png) __[Volatility-Based ID of April 2025 Tariff Shocks](https://econpapers.repec.org/RePEc:bde:wpaper:2629e)__: Volatility and kurtosis reveal that dollar depreciation and rising Treasury yields reflect multiple distinct shocks rather than a single tariff announcement shock. (2026-10-05, fanfare: 2) ![Impulse response functions](https://www.ml-quant.com/issues/2026-10-09/figures/repec-29-fe0ebc16.png) __[Professional Forecasters' Perceived Policy Rules](https://econpapers.repec.org/RePEc:adl:wpaper:2026-02)__: Time-varying beliefs about the central bank's reaction function collapsed at the zero bound and rose only after observed tightening, not from guidance alone. (2026-10-05, fanfare: 2) ![Cash rate and headline CPI forecasts](https://www.ml-quant.com/issues/2026-10-09/figures/repec-30-efde0a4b.png)