---
title: Quant Letter No. 138: November 2026, Week 1
url: https://www.ml-quant.com/issues/2026-11-06/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-11-06
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2026-11-06
---

# Quant Letter: November 2026, Week 1: Weekly quantitative finance newsletter

*This week spotlights credibility gaps in quantitative finance: LLMs lose predictive power in live trading despite strong backtests, knowledge cutoffs and future-look bias inflate strategy alphas, and reproducibility remains fragile. Standouts: LLM Stock-News Signals Under Scrutiny, LLM Knowledge Cutoffs and Backtests, and Bounded LLM Research Loop for Trading.*

## Top picks

### 1. [LLM Stock-News Signals Under Scrutiny](https://arxiv.org/abs/2611.03985) · arXiv

### 2. [The Hidden Sharpe Ratio](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679420) · SSRN

### 3. [Newspaper Reasons Explain Returns](https://econpapers.repec.org/RePEc:nbr:nberwo:35885) · RePEc

### 4. [LLM Knowledge Cutoffs and Backtests](https://arxiv.org/abs/2611.06808) · arXiv

### 5. [AI Bias Toward ESG in Analysis](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679880) · SSRN

## What's rising

### Yield curve: 9 papers this week, 2.6× the usual 3.4

### Regime switching: 9 papers this week, 1.8× the usual 5

### Earnings and analysts: 21 papers this week, 1.4× the usual 14.6

## GitHub radar

### Quant repos rising

#### [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill): Claude skills for day trading with backtesting and timing. (4 quants, 5,704 stars, +2,004 this week, new repo)

#### [finic-ai/kairos](https://github.com/finic-ai/kairos): Real-time event intelligence and fraud detection for finance. (3 quants, 231 stars, +233 this week, new repo)

#### [QuantJourneyOrg/quantjourney-bt](https://github.com/QuantJourneyOrg/quantjourney-bt): QuantJourney backtester for testing trading strategies. (3 quants, 597 stars, +426 this week)

#### [microprediction/regimelib](https://github.com/microprediction/regimelib): QuantLib models with hidden Markov regime switching. (2 quants, 11 stars, +3 this week, new repo)

#### [BruceLanLan/augur](https://github.com/BruceLanLan/augur): Local-first investment research system with 18 investor personas. (2 quants, 681 stars, +32 this week)

#### [gloom-sh/gloomberb](https://github.com/gloom-sh/gloomberb): Finance terminal for Bloomberg-style market data tracking. (2 quants, 2,654 stars, +70 this week)

#### [shiyu-coder/Kronos](https://github.com/shiyu-coder/Kronos): Foundation model for the language of financial markets. (2 quants, 47.0k stars, +2,827 this week)

#### [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents): Multi-agent LLM framework for financial trading. (2 quants, 121k stars, +2,276 this week)

### What quants are playing with

#### [NVIDIA/auto-ontology](https://github.com/NVIDIA/auto-ontology): Framework for building semantic graph-based reasoning layers over data. (28 quants, 8,496 stars, +7,839 this week)

#### [vercel-labs/agent-desktop](https://github.com/vercel-labs/agent-desktop): CLI for AI agents to use computers. (24 quants, 17.8k stars, +15.2k this week)

#### [deepseek-ai/dsh-superagent-prototype](https://github.com/deepseek-ai/dsh-superagent-prototype): Towards a more autonomous agent system. (22 quants, 20.1k stars, +20.1k this week, new repo)

#### [storytold/craft-anything](https://github.com/storytold/craft-anything): Understand how any software works and craft your own. (10 quants, 17.0k stars, +17.0k this week, new repo)

#### [milind-soni/OpenMausBot](https://github.com/milind-soni/OpenMausBot): Open-source bot with virtual machine for agent use. (10 quants, 14.6k stars, +5,650 this week, new repo)

#### [floci-io/floci](https://github.com/floci-io/floci): AWS local emulator alternative. (10 quants, 30.7k stars, +3,363 this week)

## We called it

### [Convergence of Heavy‐Tailed Hawkes Processes and the Microstructure of Rough Volatility](https://arxiv.org/abs/2312.08784): now published in Mathematical Finance (featured 20 Dec 2023, 6 days after release; 18 citations)

### [Course-Skill Atlas: A national longitudinal dataset of skills taught in U.S. higher education curricula](https://arxiv.org/abs/2404.13163): passed 25 citations (featured 24 Apr 2024, 5 days after release)

### [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://arxiv.org/pdf/2312.00752.pdf): passed 10,000 citations (featured 5 Jun 2024)

## arXiv

__[LLM Stock-News Signals Under Scrutiny](https://arxiv.org/abs/2611.03985)__: A pre-registered blinded test finds that language-model readings of company news lose their predictive power in real time and that commercial models identify masked companies in two-thirds of cases. (2026-11-04, fanfare: 4)

![No pre-registered strategy survives costs: net of 10 basis points every main book loses, and the convergence strategy](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-01-82374404.png)

__[LLM Knowledge Cutoffs and Backtests](https://arxiv.org/abs/2611.06808)__: A benchmark of 2,226 dated facts reveals that frontier language models underreport their knowledge and answer most facts they claim not to know, compromising backtest validity. (2026-11-05, fanfare: 4)

![What models know versus what they say](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-02-f49f1183.png)

__[Cryptocurrency Trend Factor Audit](https://arxiv.org/abs/2611.01951)__: A code audit of the cryptocurrency trend factor reveals that after correcting for future-information use and technical-indicator issues, the factor's alpha becomes statistically insignificant and cannot replace momentum. (2026-11-03, fanfare: 3)

![Performance revisions and benchmark dependence](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-03-b7d649d3.png)

__[Bounded LLM Research Loop for Trading](https://arxiv.org/abs/2611.06607)__: An open-source research loop constrains language-model proposals to strict JSON and enforces immutable data splits, discovery gates, and hash-chained logs to prevent false discoveries in backtest-driven strategy development. (2026-11-05, fanfare: 3)

__[PanelGP Nonlinear Factor Model](https://arxiv.org/abs/2611.04040)__: A Gaussian-process factor model with nonlinear loadings estimated from firm characteristics improves stock ranking and portfolio Sharpe ratios over linear alternatives on S&P 500 data. (2026-11-04, fanfare: 3)

![Results by number of factors H over the evaluation period](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-05-fac5effc.png)

__[Anytime-Valid Backtest Rules for Agents](https://arxiv.org/abs/2611.03384)__: A protocol using e-processes and Ville arguments lets researchers monitor candidates born at data-dependent times and adaptively chosen, bounding false promotion rates without a fixed sample size. (2026-11-03, fanfare: 3)

![E-process paths over time and portfolio wealth comparison from 2015–2026](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-06-e8e49101.png)

__[AI Agents, Market Makers, and Automated Stress](https://arxiv.org/abs/2611.01799)__: The paper models learning traders on automated market makers, showing herds and arbitrage-dominated markets have identical statistics yet stress episodes differing unboundedly in length, and that maker-taker pricing restores stability. (2026-11-03, fanfare: 3)

![(a) Theorem 4.2 : expected stress-episode length ( c=0 , Gaussian news) in a herd-dominated and an arbitrage-dominated](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-07-a0a86ed9.png)

__[CosmosAlpha: Graph-Based Alpha Factor Mining](https://arxiv.org/abs/2611.04555)__: A graph-structured framework discovers alpha factors using an LLM, connecting factors by generation, similarity, and correlation while applying Pareto-guided search to balance quality, fertility and diversity. (2026-11-04, fanfare: 3)

![Overview of CosmosAlpha](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-08-a5f34240.png)

__[Order-Flow Herding vs Racing On-Chain](https://arxiv.org/abs/2611.02616)__: Decomposing cross-account order-flow persistence on decentralized exchanges, the study isolates two components and finds that on-chain herding mostly reflects arbitrageurs racing to centralized prices, not independent traders. (2026-11-03, fanfare: 3)

![Daily herding share against the herding ratio \kappa (lag one)](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-09-85e1eb47.png)

__[Expected Shortfall Under Overlapping Sampling](https://arxiv.org/abs/2610.41624)__: When estimating expected shortfall from overlapping multi-day returns, the mismatch with standard independent-sampling theory causes systematic downward bias that weakens capital coverage, especially under heavy tails. (2026-11-02, fanfare: 3)

![Metric values comparing non-overlapping and overlapping sampling schemes across distributions.](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-10-698f85dc.png)

__[Wallet Identity for Return Prediction](https://arxiv.org/abs/2611.05218)__: Using pseudonymous wallet addresses from on-chain order books as features, the study finds persistent top-trader markouts reaching 3.11 basis points at ten seconds and improving one-second prediction. (2026-11-04, fanfare: 3)

![Drop-one contributions at the one-second ridge benchmark](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-11-27e4bc51.png)

__[Penalizing Common Trades in Portfolio Models](https://arxiv.org/abs/2611.03453)__: A post-model layer that reduces portfolio concentration by penalizing shared exposures cuts maximum drawdown from 23.6% to 14.1% on a cross-asset test. (2026-11-03, fanfare: 3)

![The wrapper reduces the deepest realized loss and traded notional, while the asset-omission diagnostic retains the](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-12-5f3b1c6f.png)

__[LLM Priors and News Graphs for Stock Ranking](https://arxiv.org/abs/2611.04217)__: A graph framework that weights extracted relations by reliability improves stock ranking on the S&P 500 by 16.4% in average recall and 22.6% in success rate. (2026-11-04, fanfare: 3)

![Static gate weights for representative stocks from different news coverage groups: NVR (low coverage, freq=0.094), BKNG](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-13-cab04688.png)

__[Rough Instantaneous Squared VIX Model](https://arxiv.org/abs/2611.07120)__: A rough-memory VIX model with Mittag-Leffler decay improves term-structure fit and out-of-sample option pricing, with larger gains during elevated volatility and shorter maturities. (2026-11-06, fanfare: 3)

![VIX option implied-volatility surface](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-14-1b2b47cf.png)

__[Tensor Learning for Limit Order Books](https://arxiv.org/abs/2611.02866)__: A tensor-native model for limit-order-book forecasting preserves the multi-way structure of market side, price level, and order attributes, outperforming flattened matrix approaches on benchmarks. (2026-11-03, fanfare: 3)

![A snapshot of a limit order book snapshot at a single event](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-15-b0d542c2.png)

__[Panel LP Bias Correction in Stata](https://arxiv.org/abs/2610.41428)__: A new Stata command implements panel local projections with split-panel jackknife correction, removing the Nickell bias that invalidates standard inference in dynamic models across regions or countries. (2026-11-02, fanfare: 3)

![Impulse responses of real GDP to household debt and nonfinancial firm debt](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-16-23eb27b7.png)

__[Panel VAR vs LP Convergence Rates](https://arxiv.org/abs/2611.00677)__: Panel VARs converge at the faster rate with N and T combined, while panel LPs converge only in T; the paper characterizes this efficiency-robustness trade-off and provides a test to choose between them. (2026-11-03, fanfare: 3)

__[Neural Realized Measures for Volatility](https://arxiv.org/abs/2611.07287)__: Learning forecast-supervised weights for intraday volatility aggregation reduces forecasting error while preserving the structure of classical realized measures like raw realized variance. (2026-11-06, fanfare: 2)

![Classical realized-measure and NRM pipelines](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-18-f943dcef.png)

__[Neural Score-Driven Volatility Models](https://arxiv.org/abs/2611.05778)__: A score-driven volatility model using neural networks to represent innovation density flexibly outperforms Gaussian and Student-t benchmarks, especially during high-volatility periods like COVID-19. (2026-11-05, fanfare: 2)

![Neural network innovation densities compared to Gaussian and Student-t benchmarks across tails.](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-19-de84b6d0.png)

__[Nonparametric GARCH Neural Estimator](https://arxiv.org/abs/2611.04157)__: An iterated neural estimator for GARCH processes alternates between learning the recursion and updating conditional variances, achieving minimax-optimal rates for in-sample and forecasting tasks. (2026-11-04, fanfare: 2)

![Neural network architecture diagram showing inputs, hidden layers, and conditional variance output.](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-20-40b51f0b.png)

__[Predicting Factor Decay with ML](https://arxiv.org/abs/2611.03668)__: Machine learning models predict when cross-factor predictability will erode, achieving high C-index on held-out pairs and finding that stronger signals decay faster. (2026-11-04, fanfare: 2)

![Four-model diagnostic: MSE improvement (%) from including HML lags, by regime and model class](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-21-be2618a5.png)

__[Market-Making Regret with Persistent Orders](https://arxiv.org/abs/2611.06159)__: A deterministic market-making policy achieves logarithmic regret against fixed quotes and square-root regret against dynamic quotes when orders persist until execution. (2026-11-05, fanfare: 2)

__[Identifying Shocks Through Heteroskedasticity](https://arxiv.org/abs/2610.41361)__: The study unifies identification results for structural shocks when variance paths differ, solving a generalized eigenvalue problem that nests prior work and clarifies what rank tests on second moments actually identify. (2026-11-02, fanfare: 2)

![Simulated price and quantity in the demand and supply example](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-23-4cc943dd.png)

__[FinForesight: Financial Forecasting Benchmark](https://arxiv.org/abs/2611.01621)__: A diagnostic backtesting framework evaluates deep research systems on four financial forecasting tasks across three markets, with controlled information cutoffs to prevent information leakage and assess whether historical backtests predict live performance. (2026-11-03, fanfare: 2)

![Can controlled T2 backtests approximate T3 forecasting performance? The model knowledge cutoff c\_{m} marks the T1/T2](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-24-3ea01e6b.png)

__[Volatility Response to Price Trends at Minute Lag](https://arxiv.org/abs/2611.04533)__: Measuring minute-by-minute volatility response to preceding trends, the research finds asymmetry and evidence of one-sided temporal response in cryptocurrencies but not equities, decomposed via time-reversal symmetry. (2026-11-04, fanfare: 2)

![The measurement](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-25-66663532.png)

__[Bounded-Memory Forecast Intervals and Stress](https://arxiv.org/abs/2611.04223)__: Aggregate forecast-interval coverage can hide state-specific failures when economic regimes return after long absence; recent-only calibration undercovers during high volatility despite meeting overall targets. (2026-11-04, fanfare: 2)

![FIFO empirical coverage at B=250 . Points show asset-averaged coverage and vertical bars show pointwise 95% paired](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-26-86a39b3b.png)

__[Fast Regime Switching in Derivatives Pricing](https://arxiv.org/abs/2611.00466)__: The paper solves regime-switching models for affine and exponential-Lévy securities by reducing to one linear system, expanding the solution in mean holding time and pricing bonds, options, and credit instruments. (2026-11-03, fanfare: 2)

__[Specification LASSO for Asset Pricing](https://arxiv.org/abs/2611.03391)__: A two-step LASSO-based method selects variables and model specification jointly in high dimensions, with oracle properties; applied to characteristics-based pricing, it reveals linear and nonlinear effects and interactions with firm size. (2026-11-03, fanfare: 2)

![Estimated interaction surface between one-month momentum ‘mom1m’ and firm size ‘mve’. Both axes are standardized](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-28-de956299.png)

__[Multidimensional Analyst Views from LLM Text](https://arxiv.org/abs/2611.04119)__: Question-based outlook scores extracted from analyst reports by an LLM improve prediction of target-price revisions beyond traditional sentiment measures. (2026-11-04, fanfare: 2)

![Prediction performance of separately trained GICS-sector models using current revision and QOS. Bars show pooled](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-29-21f9412f.png)

__[Repair Risk in Crypto Option Surfaces](https://arxiv.org/abs/2611.00958)__: Option-surface repairs that satisfy no-arbitrage constraints admit multiple admissible solutions, and finite-difference amplification causes downstream Greeks and risk measures to diverge substantially. (2026-11-03, fanfare: 2)

![Fixed-set multiplicity and local amplification](https://www.ml-quant.com/issues/2026-11-06/figures/arxiv-30-bcfd702c.png)

## SSRN

__[The Hidden Sharpe Ratio](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679420)__: The study estimates maximum Sharpe ratios in large cross-sections without constructing the efficient portfolio, finding annualized maximal Sharpe of 7.4 in U.S. equities versus benchmark estimates of 1.0 to 4.0. (2026-11-03, fanfare: 4)

__[AI Bias Toward ESG in Analysis](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679880)__: Following AI adoption, financial analysts revise high-ESG forecasts upward and become more bullish, but forecast accuracy deteriorates and errors rise for top-ESG firms. (2026-11-05, fanfare: 4)

__[Reproducibility of ML Finance Papers](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7677538)__: Testing 459 quantitative-finance machine-learning papers' released code, the study finds that execution success rates fall steeply due to environment and dependency issues, not link rot alone. (2026-11-04, fanfare: 4)

__[Information Coefficient Sample Size Limits](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7672859)__: Cross-sectional IC volatility has a floor from factor risk that does not shrink with breadth, capping effective sample size at roughly fifty observations. (2026-11-03, fanfare: 4)

__[Point-in-Time LLM Sentiment on Crypto Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7669918)__: Headlines scored by LLM within minutes predict cross-sectional cryptocurrency returns with a daily long-short Sharpe of 2.21 until the signal decays. (2026-11-03, fanfare: 3)

__[Monetary Policy Expectations of Hedge Funds](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7673758)__: Fine-tuned LLM analysis of hedge fund letters reveals policy expectations that predict yield-curve moves beyond market rates and correlate with fund returns. (2026-11-03, fanfare: 3)

__[Monetary Policy Effects on Dividend Growth and Risk Premium](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7671839)__: Using equity and risk-free rate term structures, monetary policy shocks affect both expected dividend growth and equity risk premium, with effects beyond duration matching. (2026-11-03, fanfare: 3)

__[Risk-Budgeted Mean-Variance Portfolios](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7672259)__: A convex optimization method combines risk budgeting with expected returns, delivering higher average returns than risk parity with lower turnover and concentration than traditional mean-variance portfolios. (2026-11-03, fanfare: 3)

__[Time-Series Momentum Decay and Long-Only Recovery](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7670198)__: The classic TSMOM long-short premium has decayed to a zero net Sharpe, but a long-only volatility-targeted version across multiple horizons earns 0.58 with strong crisis protection. (2026-10-31, fanfare: 3)

__[Creditor Capacity and Debt Renewal](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7668600)__: A 2021 life-insurer capital rule change shows that when incumbent creditors' capacity shrinks, corporate debt issuance falls and firms struggle to refinance maturing debt. (2026-11-03, fanfare: 3)

__[Auto Loan ABS Data Shortcomings](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7672141)__: Analysis of 19.8 million securitized auto loans reveals that reported data systematically understate risk through selection bias, carry-over reporting gaps, and priced-at-origination hidden credit differences. (2026-11-03, fanfare: 3)

__[LLM Memorization and Look-Ahead Bias](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7666459)__: Large language models recall Indian firm financials from within their training data with accuracy that declines sharply for smaller firms, creating serious look-ahead bias in LLM-based backtests. (2026-11-03, fanfare: 3)

__[When Financial News Gets Priced In](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7673798)__: Analyzing 1.68 million stock-day events from 4.57 million articles, the study finds that directional price moves concentrate before and at publication day, with little incremental return later. (2026-11-04, fanfare: 3)

![Cumulative abnormal return in the news direction around publication (day 0), five event tags plus the neutral placebo](https://www.ml-quant.com/issues/2026-11-06/figures/ssrn-13-6fd33b1b.png)

__[Firm Investment in Data Capital](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7680002)__: Measuring data investment from earnings calls, the research shows data capital's share of investment reached about one-eighth in 2025 and commands a market premium of 12 dollars per dollar invested. (2026-11-05, fanfare: 3)

__[Tokenization's Hidden Cost to Price Discovery](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7670078)__: NFT airdrops on Ethereum raise block fees and failure rates, shifting price discovery off-chain and impeding native-token information incorporation critical for proof-of-stake security. (2026-10-31, fanfare: 3)

__[Bank Shocks and Private Credit Lending](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7675178)__: Private credit funds that borrow from banks transmit funding shocks to firm lending; following SVB's collapse, exposed banks increased credit-line commitments while cutting direct lending to nonfinancial firms. (2026-11-03, fanfare: 3)

__[Short Squeezes in Corporate Bonds](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7672878)__: The study identifies two types of squeezes in corporate bonds that degrade price discovery and returns, with lender squeezes predicting negative short-horizon returns and market squeezes predicting positive ones. (2026-11-03, fanfare: 3)

__[Corporate Bond ETF Creation Puzzle](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679881)__: Finds that authorized participants create corporate bond ETF shares at discounts to offload overvalued inventory, causing delivered bonds to underperform by 5.3 basis points. (2026-11-05, fanfare: 3)

__[Exchange Rates with Disagreeing Arbitrageurs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7671358)__: Models how wealth redistribution among arbitrageurs with different beliefs amplifies exchange rate volatility and generates interest-parity wedges, accounting for 62 percent of observed variance. (2026-11-03, fanfare: 3)

__[Congressional Trading Information Value](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7679885)__: Using machine learning to map firm disclosures to congressional committee jurisdictions, finds no evidence that members earn abnormal returns from legislative access or committee hearings. (2026-11-05, fanfare: 3)

__[Anchoring on Nominal Earnings Surprise](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7676359)__: Shows that stock returns respond more to the same percentage surprise when reported earnings are larger in cents, consistent with anchoring on nominal rather than percentage earnings beats. (2026-11-04, fanfare: 3)

__[Trade Exposure and Sovereign Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7673059)__: Research shows trade exposure determines whether commodity-price rises reduce or increase sovereign risk, with exporters gaining from higher prices and importers facing reinforced costs. (2026-11-03, fanfare: 3)

__[Green Tastes vs. Beliefs in AI Investors](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7673158)__: Using language models as synthetic investors reveals institutional portfolios tilt greener despite weaker green tastes, and beliefs about green returns turn pessimistic after 2020. (2026-11-02, fanfare: 3)

__[Physics-Enforced Network for Convenience Yield](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7677598)__: A neural network that analytically enforces the Gibson-Schwartz PDE recovers commodity convenience yield from futures and avoided implausible estimates during the April 2020 WTI dislocation. (2026-11-03, fanfare: 2)

__[Volatility Surface Shape and Carry](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7670046)__: Tests term-structure and skew trading signals in equity volatility from free public data, showing term-structure carry lifts Sharpe ratio to 2.94 but skew lacks sufficient historical data. (2026-10-31, fanfare: 2)

__[Retail Crypto Returns Against Casino Odds](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7676458)__: Memecoin traders get back 0.754 per unit staked, worse than any casino game, while perpetual futures and prediction markets match casino returns. (2026-11-04, fanfare: 2)

__[Predicting Stablecoin Depegs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7670421)__: A gradient-boosted classifier trained on 219 USD-pegged stablecoins predicts which coins will lose their peg within one week, achieving 0.59 average precision on test data. (2026-10-31, fanfare: 2)

__[Informed Trading in Prediction Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7670998)__: A likelihood-ratio framework ranks wallets by their information content in binary prediction markets, separating ranking from multiple testing and validating the method through simulation. (2026-10-31, fanfare: 2)

__[Efficiency in Individual Prediction Contracts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7673098)__: Studying 244 resolved Kalshi markets, the research finds that efficiency is measurable ex post but not predictable ex ante, and naive trading strategies fail against market benchmarks. (2026-11-04, fanfare: 2)

__[Quantitative Tightening in Segmented Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7678418)__: Models how central banks must retain more reserves for rate control when interbank trading cannot redistribute reserves across heterogeneous banks, even if aggregate demand is sufficient. (2026-11-03, fanfare: 2)

## RePEc

__[Newspaper Reasons Explain Returns](https://econpapers.repec.org/RePEc:nbr:nberwo:35885)__: Wall Street Journal market summaries explain 30-40% of daily and monthly returns out of sample when filtered for stated reasons, compared to under 10% for macro variables. (2026-11-05, fanfare: 4)

![Monetary policy expansionary and contractionary periods overlaid with interest rate movements over time.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-01-529a7e80.png)

__[High-Dimensional Distributional VAR](https://econpapers.repec.org/RePEc:zbw:imfswp:344237)__: HiDVAR, a data-rich distributional framework, improves inflation tail-risk assessment by 28% in CRPS relative to standard benchmarks and performs well in real-time evaluation. (2026-11-02, fanfare: 4)

![Predicted Probabilities of Inflation surpassing 4.5%](https://www.ml-quant.com/issues/2026-11-06/figures/repec-02-778e0443.png)

__[Stablecoins, Digital Dollarization, and Triffin Dilemma](https://econpapers.repec.org/RePEc:gwc:wpaper:2026-015)__: Model shows that stablecoin design cannot remove peripheral currency risk but redeploys it; a new Triffin dilemma emerges where the issuer's capital must grow with its open position. (2026-11-02, fanfare: 4)

![Time series showing currency value, holdings, inflation, and consumption dynamics across stablecoin regimes.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-03-537de7dc.png)

__[Fed Chair Emotions Affect Global Markets](https://econpapers.repec.org/RePEc:een:camaaa:2026-86)__: Facial and textual emotions from Fed Chair press conferences generate immediate effects on foreign exchange and equity returns, with non-additive cross-modal interactions. (2026-11-02, fanfare: 3)

![Meeting-Level Facial Expression Index and Its Five-Meeting Moving Average](https://www.ml-quant.com/issues/2026-11-06/figures/repec-04-a85e8606.png)

__[Multilingual Text for Volatility Forecasting](https://econpapers.repec.org/RePEc:hal:journl:hal-05723648)__: A hybrid FinBERT-HAR-X framework using multilingual news reduces S&P 500 volatility forecast error by 21% and improves realized Sharpe ratios out of sample. (2026-11-02, fanfare: 3)

![Out-of-sample cumulative performance of allocation strategies comparing HAR-X variants from 2022-2024.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-05-7b200dfa.png)

__[Investor Disagreement from Language Models](https://econpapers.repec.org/RePEc:zbw:cbscwp:344253)__: Using LLM personas, disagreement over news headlines predicts trading volume, with income and education disagreement most predictive and fundamentals generating least disagreement. (2026-11-02, fanfare: 3)

![LLM Persona Responses Closely Match Human Responses Out of Sample](https://www.ml-quant.com/issues/2026-11-06/figures/repec-06-b6f2ec22.png)

__[Pension Fund Forced Selling in Equities](https://econpapers.repec.org/RePEc:nbr:nberwo:35896)__: U.S. pension funds facing negative cash flows sell equities as primary liquidity source rather than rebalancing, absorbing $0.67 per dollar of shock through equity sales. (2026-11-02, fanfare: 3)

![Asset Allocation from Pension Fund Holdings](https://www.ml-quant.com/issues/2026-11-06/figures/repec-07-b9ef8c09.png)

__[Bank of Japan Stock Purchase Impacts](https://econpapers.repec.org/RePEc:nbr:nberwo:35886)__: Using policy-rule discontinuities, the study finds BOJ stock purchases raise long-term rates but lift prices only after yield curve control pegged rates at zero. (2026-11-02, fanfare: 3)

![Unconventional Monetary Policies by the Bank of Japan](https://www.ml-quant.com/issues/2026-11-06/figures/repec-08-1e4f31d3.png)

__[Central Bank Independence and Sovereign Borrowing Costs](https://econpapers.repec.org/RePEc:tcd:tcduee:tep2226)__: Tighter statutory constraints on central bank lending to government reduce real borrowing costs in developing economies while raising debt-to-GDP, with effects strongest where credibility gains matter most. (2026-11-02, fanfare: 3)

![Histogram of central bank lending reforms over time with cumulative reform count trend lines.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-09-500e792c.png)

__[Wars and Military Threats in Sovereign Bonds](https://econpapers.repec.org/RePEc:diw:diwwpp:dp2186)__: Analysis of 300,000 monthly bond prices since 1822 shows wars lower external bond returns by five percentage points and raise default risk, while military threats depress threatened states' borrowing costs. (2026-11-02, fanfare: 3)

![Bond returns decline sharply after war onset, with increased default risk and debt-to-GDP ratio.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-10-1afd407a.png)

__[Consumer Attention to Monetary Policy](https://econpapers.repec.org/RePEc:fip:fedcwq:103975)__: Survey of 170,000 consumers shows that attention to monetary policy is driven by incentives; those planning major purchases are significantly more attentive to interest rate news. (2026-11-02, fanfare: 3)

![Attention to monetary policy spikes around FOMC meetings for consumers planning major purchases](https://www.ml-quant.com/issues/2026-11-06/figures/repec-11-47af4d4d.png)

__[Inflation Forecasting with Expectation De-Anchoring](https://econpapers.repec.org/RePEc:zbw:imfswp:344239)__: A model allowing expectations to shift to a low-inflation equilibrium cuts forecast errors roughly 50 percent versus central bank projections for euro area core inflation in the 2010s. (2026-11-02, fanfare: 3)

![Euro area core inflation forecasts comparing transition and target models with uncertainty bands.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-12-8d102ce1.png)

__[State-Dependent Local Projections for Shocks](https://econpapers.repec.org/RePEc:fip:fedhwp:103968)__: The study develops nonparametric local projections to identify how economic shocks affect outcomes differently across states, uncovering a hump-shaped investment response to monetary policy that linear methods understate. (2026-11-02, fanfare: 3)

![Impulse Response of Firm-Level Investment to a Monetary Policy Shock](https://www.ml-quant.com/issues/2026-11-06/figures/repec-13-82bfdedd.png)

__[News Shocks and Inflation in Open Economies](https://econpapers.repec.org/RePEc:bis:biswps:1389)__: Large oil discoveries with production lags of five years show that anticipated future output raises core inflation a decade ahead, with effects concentrated in nontradables under fixed exchange rates. (2026-11-02, fanfare: 3)

__[Sovereign Default Risk and Climate Adaptation](https://econpapers.repec.org/RePEc:idb:brikps:14759)__: A sovereign default model shows that high borrowing costs and debt overhang depress public adaptation spending, yet adaptation yields the largest welfare gains when financing is tightest near default. (2026-10-30, fanfare: 3)

__[Emotions and Inflation Expectations by Income](https://econpapers.repec.org/RePEc:toh:dssraa:155)__: Lower-income households form inflation beliefs two and a half times more sensitive to their emotional state than higher-income households, affecting expectations substantially independent of fundamentals. (2026-11-02, fanfare: 3)

__[Brazilian Monetary Policy Surprises](https://econpapers.repec.org/RePEc:cdp:texdis:td705)__: Analysis of COPOM announcements reveals target and path surprises move the yield curve differently, with nonlinear effects and sign asymmetries in inflation expectation responses. (2026-11-02, fanfare: 2)

![Target and path monetary policy surprises factors across COPOM meetings](https://www.ml-quant.com/issues/2026-11-06/figures/repec-17-94aa1753.png)

__[Financial Conditions and Macro Tail Risk](https://econpapers.repec.org/RePEc:ris:crcrmw:023696)__: Adding financial conditions to macro forecasts raises recession tail probabilities and lowers growth quantiles, though out-of-sample forecast improvement is inconsistent. (2026-10-26, fanfare: 2)

__[AI Exposure and Financial Sector Tails](https://econpapers.repec.org/RePEc:bca:bocawp:26-40)__: AI-scenario contributions to financial-sector tail risk vary substantially by country, with downside asymmetry in Europe and the UK but limited impact in North America. (2026-11-02, fanfare: 2)

![Concept of the Expected Shortfall decomposition](https://www.ml-quant.com/issues/2026-11-06/figures/repec-19-f587379a.png)

__[Monetary Policy Investment Response Heterogeneity](https://econpapers.repec.org/RePEc:fip:fednsr:103901)__: The study estimates the full distribution of firms' investment responses to monetary policy using clustering regression, finding only 5 percent of firm-time observations show strong sensitivity. (2026-10-26, fanfare: 2)

![3D surface plots showing monetary policy response heterogeneity across firm characteristics dimensions.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-20-00c2a1e4.png)

__[Debt Restructuring and Monetary Policy in EMDEs](https://econpapers.repec.org/RePEc:cgd:wpaper:759)__: Analysis of 17 domestic debt restructurings reveals that monetary transmission often fails to recover post-restructuring due to balance-sheet constraints across sovereigns, central banks, and financial institutions. (2026-11-02, fanfare: 2)

__[News-Based Measure of Perceived Financial Stress](https://econpapers.repec.org/RePEc:bca:bocsap:26-50)__: A news-based stress index for Canada reveals that perceived financial stress operates through household precautionary behavior, independently of market-based financial shocks. (2026-11-05, fanfare: 2)

![News stress index compared with VIX, consumer confidence, and business confidence over time.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-22-2a440755.png)

__[Bank Liquidity Regulation and Private Credit Growth](https://econpapers.repec.org/RePEc:bis:biswps:1388)__: The liquidity coverage ratio significantly boosts private credit growth in counties with more LCR-subject banks, an effect comparable in magnitude to 2012 capital requirement increases. (2026-11-02, fanfare: 2)

![Private credit versus LCR footprint](https://www.ml-quant.com/issues/2026-11-06/figures/repec-23-39172bcb.png)

__[Fiscal Policy Design and Monetary Transmission](https://econpapers.repec.org/RePEc:cam:camdae:2683)__: Analytical framework shows how debt size, composition, and fiscal rules drive three channels—debt service, debt composition, and fiscal cyclicality—that amplify or dampen monetary policy effects. (2026-11-02, fanfare: 2)

![Flow diagram showing monetary policy transmission through government budget, fiscal policy, debt holdings to consumption](https://www.ml-quant.com/issues/2026-11-06/figures/repec-24-361ee202.png)

__[Monetary Policy and Housing Supply and Demand](https://econpapers.repec.org/RePEc:bca:bocsap:26-52)__: Rate increases substantially reduce house prices and mortgage purchases, with housing starts and permits falling slowly, suggesting demand responds more sharply than supply. (2026-11-02, fanfare: 2)

![House price decomposition across multiple horizons showing demand and supply components.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-25-6857bfce.png)

__[Cross-Border Payment Costs for Firms](https://econpapers.repec.org/RePEc:bca:bocsap:26-49)__: Analysis of quoted prices reveals that banks charge firms 2-3.5% for cross-border payments, with foreign exchange margins dominating costs and substantial price dispersion across banks for identical corridors. (2026-11-02, fanfare: 2)

![Density distributions of pricing dispersion by transfer amount across banks, showing variation by corridor and payment size.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-26-6b1e7681.png)

__[Commercial Real Estate Uncertainty Index](https://econpapers.repec.org/RePEc:bav:wpaper:252_dietl_nguyen.rdf)__: A new uncertainty index for commercial real estate predicts prices and construction spending and accounts for 46 percent of spending forecast errors, outperforming existing uncertainty measures. (2026-11-02, fanfare: 2)

![Real estate uncertainty indices (REU, CREU, MU, FU) from 1993-2025 at 3-quarter forecast horizon.](https://www.ml-quant.com/issues/2026-11-06/figures/repec-27-fd5021c4.png)

__[Seasonal Effects in Interest Rate Pass-Through](https://econpapers.repec.org/RePEc:zbw:bofrdp:344221)__: The research finds that euro-area banks transmit interest rate changes more slowly to lending rates in the fourth quarter during tightening, consistent with year-end volume targets. (2026-11-02, fanfare: 2)

__[Stablecoins and Creditor Subordination Risk](https://econpapers.repec.org/RePEc:fip:fedcwq:103919)__: New U.S. legislation grants stablecoins superpriority in bankruptcy, allowing distressed issuers to subordinate existing creditors and shift losses to depositors before any filing occurs. (2026-10-27, fanfare: 2)

__[Private Equity Performance Persistence Review](https://econpapers.repec.org/RePEc:fau:wpaper:wp2026_03)__: Literature review finds genuine skill in private equity performance persistence, especially in venture capital, but shows estimates often weaken under stricter methods and richer data. (2026-11-03, fanfare: 2)

![Network visualization of author keywords co-occurrence](https://www.ml-quant.com/issues/2026-11-06/figures/repec-30-c8f4a780.png)