---
title: Quant Letter No. 136: October 2026, Week 4
url: https://www.ml-quant.com/issues/2026-10-23/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-23
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2026-10-23
---

# Quant Letter: October 2026, Week 4: Weekly quantitative finance newsletter

*This week spans AI risk in trading, neural microstructure learning, and the frontier's limits. Key tensions emerge: LLM traders fall to information attacks while benchmarks show no leading model beats equal-weight; neural filters cut arbitrage uncertainty eightfold yet ML VaR models hide regime-shift failures. Mean-field DEX liquidity and arbitrage-free IV surfaces advance pricing theory. See Information Injection Attacks, State-Space Models Learn Market Structure, and ML Value-at-Risk Validation Under Regime Shifts.*

## Top picks

### 1. [Information Injection Attacks on LLM Traders](https://arxiv.org/abs/2610.26438) · arXiv

### 2. [ML Value-at-Risk Validation Under Regime Shifts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7652318) · SSRN

### 3. [AI Productivity Gains Boost GDP Growth](https://econpapers.repec.org/RePEc:nbr:nberwo:35793) · RePEc

### 4. [Option-Implied Moments Predict Returns and Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7626643) · SSRN

### 5. [Human Capital Concentration in Venture Capital](https://econpapers.repec.org/RePEc:nbr:nberwo:35501) · RePEc

## What's rising

### Market making: 16 papers this week, 1.8× the usual 8.7

### Prediction markets: 17 papers this week, 1.8× the usual 9.5

### DeFi: 14 papers this week, 1.8× the usual 7.9

## GitHub radar

### Quant repos rising

#### [Open-Dev-Society/OpenStock](https://github.com/Open-Dev-Society/OpenStock): Open-source market platform tracking real-time stock prices and alerts. (2 quants, 20.8k stars, +511 this week)

#### [shiyu-coder/Kronos](https://github.com/shiyu-coder/Kronos): Foundation model for the language of financial markets. (2 quants, 43.4k stars, +2,562 this week)

#### [simonlin1212/Vibe-Research](https://github.com/simonlin1212/Vibe-Research): Research workbench for China A-shares, US and HK stocks. (2 quants, 2,782 stars, +63 this week)

#### [666ghj/MiroFish](https://github.com/666ghj/MiroFish): Swarm intelligence engine for financial forecasting and predictions. (2 quants, 81.4k stars, +1,689 this week)

### What quants are playing with

#### [google-research/harness2](https://github.com/google-research/harness2): Unknown tool with no description provided. (43 quants, 18.3k stars, +17.6k this week, new repo)

#### [deepseek-ai/DeepInfer](https://github.com/deepseek-ai/DeepInfer): High-performance large-scale inference framework for DeepSeek models. (23 quants, 20.6k stars, +20.6k this week, new repo)

#### [morluto/rea](https://github.com/morluto/rea): Reverse engineer anything with agents from app behavior to binaries. (15 quants, 370k stars, +76.1k this week)

#### [Ephemeral-AI-Lab/layerfs](https://github.com/Ephemeral-AI-Lab/layerfs): Ephemeral workspaces with durable shared history and parallel agent support. (8 quants, 1,978 stars, +1,529 this week, new repo)

#### [xerj-org/xerj](https://github.com/xerj-org/xerj): Local-first search engine and MCP server for AI agent memory. (8 quants, 13.3k stars, +6,242 this week)

#### [withmarbleapp/os-taxonomy](https://github.com/withmarbleapp/os-taxonomy): Unknown tool with no description provided. (8 quants, 7,258 stars, +2,250 this week)

## We called it

### [Short Communication: Exponential Utility Maximization in a Discrete Time Gaussian Framework](https://arxiv.org/abs/2305.18136): now published in SIAM J. Financial Math. (featured 1 Jun 2023, 3 days after release; 4 citations)

### [Short Communication: On the Separability of Vector-Valued Risk Measures](https://arxiv.org/abs/2407.16878): now published in SIAM J. Financial Math. (featured 31 Jul 2024, 8 days after release; 4 citations)

### [Short Communication: The Price of Information](https://arxiv.org/abs/2402.11864): now published in SIAM J. Financial Math. (featured 21 Feb 2024, 2 days after release; 3 citations)

## arXiv

__[Information Injection Attacks on LLM Traders](https://arxiv.org/abs/2610.26438)__: Fabricated news reaches 62% attack success against LLM trading agents, far exceeding prompt injection, with surface-form credibility cues mattering more than content accuracy. (2026-10-20, fanfare: 4)

![Information injection threat model](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-01-9676ec13.png)

__[State-Space Models Learn Market Structure](https://arxiv.org/abs/2610.28753)__: A Mamba sequence model trained on limit-order-book messages learns order-flow imbalance as an internal representation with R² ≈ 0.59 and generalizes across stocks and microstructure metrics. (2026-10-22, fanfare: 3)

![Learning curves showing order-flow imbalance signal captured by state-space model versus random baseline](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-02-4d35f157.png)

__[Quant-Arena: LLM Strategy Benchmark](https://arxiv.org/abs/2610.30113)__: A public benchmark tests whether large language models can complete end-to-end quantitative research with real trading constraints; no frontier model beats the equal-weight market in 2024. (2026-10-22, fanfare: 3)

![Mean next-day return by daily score decile for the nine models’ best iterative configurations in 2024, in basis points](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-03-63a652df.png)

__[Mean-Field Game of Liquidity Provision on DEXs](https://arxiv.org/abs/2610.28863)__: The research models liquidity provision on decentralized exchanges as a mean-field game and derives closed-form solutions linking critical volatility to market microstructure parameters, validated on Ethereum data. (2026-10-22, fanfare: 3)

![Realized volatility versus critical volatility and participation margin ratio over time for Ethereum Uniswap V3.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-04-f229c33d.png)

__[Neural Filtering for Statistical Arbitrage Uncertainty](https://arxiv.org/abs/2610.25802)__: A neural filter estimates posterior uncertainty over spread states and uses it to size positions, cutting the gap between forecasted and realized returns by two to eight times on Korean equities. (2026-10-20, fanfare: 3)

![(a) Cumulative net return of the strategies of Table 1 , scaled to a common volatility; the random benchmark at its own](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-05-afaaffd6.png)

__[Arbitrage-Free IV Surfaces via Additive Martingales](https://arxiv.org/abs/2610.25671)__: AddMart reconstructs implied volatility surfaces from sparse quotes by mapping to martingale densities, ensuring no-arbitrage by construction and enabling crash probability estimation. (2026-10-20, fanfare: 3)

![Signed CVaR residuals over the test period](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-06-3a8501ec.png)

__[Market Impact in Generative Limit Order Book Models](https://arxiv.org/abs/2610.27100)__: Injecting metaorders into neural limit-order-book generators reveals that market impact emerges naturally from next-token prediction, enabling benchmarking of realistic simulator behavior. (2026-10-21, fanfare: 3)

![The AMD measurements, all three phases in one figure ( 5{\times}2 )](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-07-7f8a4609.png)

__[DSINC Method for Non-Affine Stochastic Volatility](https://arxiv.org/abs/2610.28847)__: The paper extends damped-sinc methods beyond Heston to general one-factor stochastic-volatility models including the 3/2 and SABR, achieving basis-point accuracy with comparable computational cost. (2026-10-22, fanfare: 3)

![Truncated moments for three stochastic volatility models on logarithmic scale](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-08-c3aa1c14.png)

__[Dividend Fairness in Crypto Perpetuals](https://arxiv.org/abs/2610.22839)__: Premium-index funding cannot replicate shareholder cash flows for dividend-paying assets; fairness requires discrete event credits matching dividend atoms, not continuous basis adjustment. (2026-10-19, fanfare: 3)

__[Dynamic Programming for VaR in Continuous Spaces](https://arxiv.org/abs/2610.24439)__: The paper establishes validity of dynamic programming equations for Value-at-Risk objectives in continuous state and action spaces, enabling optimal execution problems with VaR goals. (2026-10-20, fanfare: 3)

![Comparison of static and dynamic strategies under different parameter settings for Regime 2](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-10-4156bc9a.png)

__[Institutional Trader Forecasting Ability](https://arxiv.org/abs/2610.31141)__: High-frequency data shows skillful traders have persistent predictive edge; one-standard-deviation improvement in forecasting ability raises position P&L by 1.02–1.19 units. (2026-10-23, fanfare: 2)

![Annualized Sharpe Ratio of Stock-1 and Stock-2 for the three trading strategies during the second period](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-11-e9ff3492.png)

__[Arithmetic Models for Commodity Options](https://arxiv.org/abs/2610.28071)__: An arithmetic stochastic volatility model for crude oil provides semi-closed-form pricing for vanilla and calendar spread options, hedges daily risk effectively, and improves fit over geometric models. (2026-10-21, fanfare: 2)

![Model-free volatility Level (mean over maturities from 42 to 210 business days, top) and slope (42-day less 210-day](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-12-5a229956.png)

__[Optimal Trading Filters Under Impact](https://arxiv.org/abs/2610.24558)__: Wiener-Hopf factorization yields optimal trading filters for return forecasts under transient price impact, showing fractional filters and the value of mean-reversion timing for signals. (2026-10-20, fanfare: 2)

![Signal speed and Matérn smoothness at fixed predictor variance and market costs](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-13-6c65205c.png)

__[Worst-Case Risk via Spectral Measures](https://arxiv.org/abs/2610.29652)__: A convex variational theory unifies worst-case risk evaluation across different ambiguity sets, yielding closed-form solutions and algorithms for portfolio selection under Wasserstein and distributional uncertainty. (2026-10-22, fanfare: 3)

![Partial-moment ambiguity with \mu=4 , \sigma=1 , \beta=3 , and admissible support \[0,15\] . (a) Worst-case CDFs at t=\pm](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-14-d2dfae68.png)

__[Execution Scheduling Under Concave Impact](https://arxiv.org/abs/2610.23749)__: Optimal execution windows maximize realized P&L by balancing alpha decay against concave impact costs; schedule shapes follow from convex optimization without depending on order size or impact coefficients. (2026-10-19, fanfare: 3)

![Inventory curves showing envelope-optimal execution versus TWAP and AC benchmarks over normalized time.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-15-4bfcc802.png)

__[Adversarial Post-Training for LOB Models](https://arxiv.org/abs/2610.25604)__: Wasserstein GAN post-training on limit order book foundation models cuts error accumulation and improves realism by 17%, outperforming continued pre-training with far lower compute cost. (2026-10-20, fanfare: 3)

![The limit order book and its message stream from records in LOBSTER format](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-16-0893676e.png)

__[Efficiency and Survivor Bias in Cryptocurrency Markets](https://arxiv.org/abs/2610.23283)__: Testing weak-form efficiency on 8,970 cryptocurrencies over thirteen years, the study finds persistent asymmetry in market ranking but reveals that neglected assets lack liquidity rather than predictability. (2026-10-19, fanfare: 3)

![Cumulative wealth from $1 invested in: the paper strategy (equal-weighted bottom decile of surviving coins, weekly](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-17-bd2fd4c6.png)

__[Neural Network Trend Inflation Estimation](https://arxiv.org/abs/2610.26298)__: Deep-π\* attributes trend inflation movements to macroeconomic indicators via neural networks, forecasting inflation more accurately than classical models and signaling the 2021 surge earlier. (2026-10-20, fanfare: 3)

![The drivers of the trends since January 2019](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-18-7adc85d8.png)

__[Regime-Aware Tactical Asset Allocation with NCO](https://arxiv.org/abs/2610.27751)__: The study integrates market regime detection with Nested Clustered Optimization to build multi-asset portfolios, showing improved risk-adjusted returns and reduced downside risk versus regime-agnostic approaches. (2026-10-21, fanfare: 2)

![Rolling 12-month Sharpe ratio comparing regime-aware HMM-NCO versus standard NCO strategies over time.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-19-5d11083a.png)

__[Rough Heston Posterior Inference](https://arxiv.org/abs/2609.31570)__: Simulation-based inference learns posterior distributions for rough Heston parameters and propagates them through neural pricers to deliver calibrated uncertainty intervals for exotic options. (2026-10-23, fanfare: 2)

![Empirical coverage of highest posterior density regions versus nominal level, showing excellent calibration.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-20-7e132539.png)

__[Nash Equilibria in Competitive Market Making](https://arxiv.org/abs/2610.30891)__: The research characterizes pure-strategy Nash equilibria for multi-market-maker games, proves equilibria exist under minimal assumptions, and validates theoretical predictions via simulation. (2026-10-23, fanfare: 2)

![Profitable boundary deviation at an out-of-support candidate midpoint \widehat{m}\leq\underline{v} . Posting](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-21-a64f7507.png)

__[Probabilistic LOB Forecasting with Conditional Diffusion](https://arxiv.org/abs/2610.25495)__: LOBGrad combines autoregressive encoders with diffusion models for limit-order-book forecasting, reproducing microstructure facts and providing calibrated predictive intervals. (2026-10-20, fanfare: 2)

![Illustration of the raw Level-2 LOB, the centered representation used in our model, and the forecasting target](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-22-09c06d1e.png)

__[Diffusion Transformer for Limit-Order Supply Forecasting](https://arxiv.org/abs/2610.22727)__: OrderFlowDiT forecasts unnormalized bid-ask volume fields using unbalanced optimal transport regularization, reducing transport cost by 45.8 percent relative to mean squared error alone. (2026-10-19, fanfare: 2)

![The data at one forecast boundary, within 300 ticks of the mid-price: the book snapshot X\_{k} , the observed field](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-23-33ba1460.png)

__[Extreme Value Theory for Deep Hedging Policies](https://arxiv.org/abs/2610.27214)__: The study applies extreme value theory to train neural hedging policies on tail risk, achieving lower losses under extreme scenarios when relevant observations are scarce. (2026-10-21, fanfare: 2)

![Validation \mathrm{CVaR}\_{0.999} throughout training under the empirical and EVT-based optimization approaches](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-24-6316fac4.png)

__[LLMs on SEC Filings and Stock Market Reactions](https://arxiv.org/abs/2610.24268)__: Analysis of 13 language models on 45,964 Form 10-Q filings shows finance-specialized models produce modest advantages in return ranking but lag analyst consensus in earnings forecasts. (2026-10-20, fanfare: 2)

![Adding cross-sectional fundamental ranks to the same 10-Q MD&A can reverse the return signal inferred from the filing](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-25-1415b330.png)

__[Agentic AI Behavior and Automated Market Stress](https://arxiv.org/abs/2610.22522)__: Deep reinforcement learning simulates three agent archetypes in automated markets, finding herd-followers generate frequent short stress episodes while manipulators create persistent volatility. (2026-10-19, fanfare: 2)

![Rolling volatility comparison across five agent types over time, showing distinct stress patterns.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-26-7f94ec92.png)

__[Lineage-Aware Search in LLM-Based Factor Mining](https://arxiv.org/abs/2610.29663)__: LineageEvo guides large-language-model-based alpha factor search using lineage-conditioned variation and stratified allocation, promoting diverse and predictive factor discovery. (2026-10-22, fanfare: 2)

![LineageEvo system overview showing pipeline from lineage selection through factor generation and validation.](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-27-90317d3c.png)

__[Conflicting History in Return Forecasts](https://arxiv.org/abs/2610.25822)__: Older observations that conflict with recent data reduce foundation models' probability of beating zero across all tested procedures, distinguishing signal extraction from conflicting-history resistance. (2026-10-20, fanfare: 2)

![Higher-signal financial process](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-28-f4173c51.png)

__[Cooperative Multi-Agent Market Making](https://arxiv.org/abs/2610.26789)__: Decomposing a market maker into quoter and risk-manager agents trained with cooperative IPPO on Polymarket reduces held-out losses and improves quoting frequency versus baselines. (2026-10-20, fanfare: 2)

__[Expert Views Improve Markowitz Portfolios](https://arxiv.org/abs/2610.31074)__: The research shows that even small amounts of directionally correct expert information materially improve portfolio allocations in both classical and machine-learning frameworks. (2026-10-23, fanfare: 2)

![Portfolio allocations over 2024–2025 for \lambda=0 , 0.5 , and 1 . The left column shows the Markowitz target](https://www.ml-quant.com/issues/2026-10-23/figures/arxiv-30-0ab2bfca.png)

## SSRN

__[ML Value-at-Risk Validation Under Regime Shifts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7652318)__: The study shows that machine-learning VaR models passing standard backtests breach risk limits two to nine times worse in stressed regimes, revealing false comfort in current regulatory validation. (2026-10-22, fanfare: 4)

__[Option-Implied Moments Predict Returns and Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7626643)__: Using 3.8 billion option contracts, the study finds implied kurtosis predicts five-day returns with 2.33 Sharpe ratio and improves volatility forecasting by 23.3 percent. (2026-10-20, fanfare: 4)

__[Visual Chart Similarity Predicts Stock Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7653398)__: Vision models retrieve visually similar price charts from three decades of history; similar historical patterns predict future cross-sectional returns, especially for stocks with limits to arbitrage. (2026-10-22, fanfare: 4)

__[AI Intensity and Firm Financing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7626298)__: As firms adopt AI, they hold less cash, shift from revolving to term credit, pay higher spreads, and rely more on non-bank lenders while expanding investment and employment. (2026-10-19, fanfare: 4)

__[Quantitative Easing's Loan Renegotiation Channel](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7622438)__: Large purchases of mortgage-backed securities prompt exposed banks to renegotiate existing corporate loans on lender-favorable terms, reducing borrower investment by 6 percent. (2026-10-17, fanfare: 4)

__[Systemic Liquidity Risk and Cross-Sectional Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7632078)__: An intertemporal model shows that bank maturity transformation creates priced systemic risk where high liquidity-beta assets underperform by six to seventeen percent quarterly during stress. (2026-10-20, fanfare: 3)

__[Industrial Emissions Forecast Equity Risk Premium](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7631840)__: When U.S. industry runs hot measured by carbon emissions, expected market returns fall 4.2 percentage points the next year, forecasting returns up to five years ahead. (2026-10-20, fanfare: 3)

__[Monetary Policy Uncertainty and Bank Lending](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7647979)__: Higher monetary policy uncertainty reduces banks' risk-bearing capacity, widening the lending gap between well-capitalized and undercapitalized banks by 1.65 percent in riskier credit. (2026-10-21, fanfare: 3)

__[Asset Pricing With Return-SDF Cumulants](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7636458)__: Log expected excess returns decompose exactly into joint cumulants of returns and the stochastic discount factor, explaining thirty-one anomaly factors with three structural parameters. (2026-10-20, fanfare: 3)

__[Price Impact and Fire Sales in Crowded Trades](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7638998)__: A model of factor crowding shows that forced exits amplify shocks up to sixfold and shift crowding costs from average returns into tail losses. (2026-10-20, fanfare: 3)

__[Arrow-Debreu Prices in Polymarket Contracts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7651118)__: State prices from binary prediction markets on the Fed decision and presidential election satisfy the law of one price for complete contingent claims, with overround declining steadily toward resolution. (2026-10-22, fanfare: 3)

__[Passive Investing and Price Discovery Breakdown](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7652221)__: An agent-based model shows how rising passive market share starves the limit order book of price-sensitive capital, leading to deteriorating price discovery and emergent liquidity crises. (2026-10-23, fanfare: 3)

__[Nonbank Lending to Distressed Firms](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7626438)__: As firms approach bankruptcy, lending shifts to nonbanks and fintechs despite higher losses given default, revealing worse information and more pro-cyclical credit supply during downturns. (2026-10-19, fanfare: 3)

__[Banks' Risk Assessment of AI-Exposed Firms](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7639259)__: After ChatGPT, banks lower default risk for AI-exposed borrowers by about 5 percent but compress credit to market leaders, reordering risk in ways that predict future credit losses. (2026-10-20, fanfare: 3)

__[Automated Trading Homogeneity and Systemic Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7652479)__: A model shows how correlated automated trading decisions generate feedback and forced liquidations, with systemic risk rising as market depth shrinks relative to automated activity. (2026-10-22, fanfare: 3)

__[Verifiable Standard for AI Market Forecasts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7653679)__: A transparency standard with cryptographic timestamping allows independent verification of AI forecasts before market opens, making backtests tamper-proof and comparable across models. (2026-10-22, fanfare: 3)

![Compliance ladder timeline showing verification levels for AI forecasts from October through completion.](https://www.ml-quant.com/issues/2026-10-23/figures/ssrn-16-532de869.png)

__[Placebo Test for Credit Features](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7622180)__: A placebo test reveals that features like central bank tone can raise credit model accuracy merely by indicating when loans were made, not by predicting defaults. (2026-10-17, fanfare: 3)

__[Machine Learning for Equity Timing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7623819)__: Five pre-registered hypotheses about machine learning for volatility, drawdowns, trend filtering, stock ranking, and news failed validation on a 2025-26 holdout despite passing development tests. (2026-10-19, fanfare: 3)

__[Prediction Markets Discipline Option Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7647658)__: Prediction-market prices serve as risk-adjusted state prices to measure event probability and information arrival, improving option valuation and revealing market frictions in elections and Brexit. (2026-10-21, fanfare: 3)

__[VQuant: LLM Architecture for Finance](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7650999)__: A platform couples a language model with deterministic execution to turn natural-language requests into auditable reports where every figure is from live data or reproducible code, not model hallucination. (2026-10-22, fanfare: 3)

__[Candlestick Words Improve Intraday Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7621579)__: Encoding intraday bars as descriptive words adds 1.7 to 3.7 points of out-of-sample R² to standard volatility models after spikes but shows no edge on daily bars. (2026-10-20, fanfare: 3)

__[Corporate Bond Spread Decomposition in Brazil](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7637398)__: Decomposing debenture spreads into issuer, market, and contract components shows issuer risk explains 54 percent of variance, enabling out-of-sample pricing within 14 basis points. (2026-10-21, fanfare: 3)

__[Stock Market Cycles and Regimes](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7649303)__: A new methodology identifies bear and bull markets by bandwidth calibration, finding median durations of 74 and 294 days, and fits regime-switching models on cumulative rather than daily returns. (2026-10-21, fanfare: 3)

__[Price Impact in Prediction Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7651399)__: Using observable outcomes in prediction markets to identify efficient prices, the study decomposes impact into price-moving and anticipation components, finding informed traders earn mostly through prediction. (2026-10-21, fanfare: 3)

__[Dynamic Factor Timing With Transaction Costs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7634558)__: A strategy dynamically allocating across 50 smart-beta factors based on past returns and covariances significantly outperforms static allocation even with transaction costs included. (2026-10-21, fanfare: 2)

__[Volatility Timing in Crowded Factors](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7656082)__: Crowding combined with volatility and market stress improves the risk-adjusted performance of volatility-managed factors more than standard volatility management alone. (2026-10-23, fanfare: 2)

__[Neural Option Pricing Hedging Diagnostics](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7657600)__: The research separates pricing error from hedging loss by decomposing delta-hedge profit and loss into terminal mismatch, residuals, volatility misspecification, rebalancing, and trading costs. (2026-10-22, fanfare: 2)

__[Bootstrap Diagnostics of FX Strategy Edge](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7630778)__: Resampling bootstrap of ten walk-forward validated FX strategies places their median expectancy at the 77th percentile of its own distribution, indicating modest optimization bias. (2026-10-20, fanfare: 2)

__[Cross-Asset Volatility Transmission Connectedness](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7651038)__: Analysis of ten instruments finds U.S. equity futures are net transmitters of volatility shocks while cryptocurrencies became net receivers in 2024-2026, with total connectedness peaking in 2025. (2026-10-22, fanfare: 2)

__[Copulas for Tail Risk in Market Crashes](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7650300)__: Asymmetric Clayton and Gumbel copulas and fat-tailed Student-t copulas substantially outperform Gaussian copulas at capturing lower-tail dependence and crisis losses. (2026-10-22, fanfare: 2)

## RePEc

__[AI Productivity Gains Boost GDP Growth](https://econpapers.repec.org/RePEc:nbr:nberwo:35793)__: Using stock market data to measure AI's effect on software engineering productivity, the study estimates AI raised expected productivity by 32.6% and GDP by 3.6% to 6.5% through end-2025. (2026-10-12, fanfare: 4)

![Software engineering payroll share vs](https://www.ml-quant.com/issues/2026-10-23/figures/repec-01-91e5f329.png)

__[Human Capital Concentration in Venture Capital](https://econpapers.repec.org/RePEc:nbr:nberwo:35501)__: Over 100,000 VC professionals show extreme concentration: 5% generate 90% of profits, with superstar status increasing access to high-quality deal flow. (2026-10-10, fanfare: 4)

![Panel A displays the likelihood for whether a VC professional is included on the Midas list in a given year based on](https://www.ml-quant.com/issues/2026-10-23/figures/repec-02-fe4c1a22.png)

__[AI News Shocks Spark Investment Cycles](https://econpapers.repec.org/RePEc:dnb:dnbwpp:871)__: The research identifies AI news shocks from equity factors and shows they trigger investment-led US growth but create monetary dilemmas via imported inflation in the euro area. (2026-10-12, fanfare: 3)

![Daily AI news shocks over time with cumulative effects around major narrative events](https://www.ml-quant.com/issues/2026-10-23/figures/repec-03-5eeac384.png)

__[Collateral Rights and Financial Runs](https://econpapers.repec.org/RePEc:bon:boncrc:crctr224_2025_783)__: The paper shows that strengthening collateral pledgeability can paradoxically fuel leverage and instability, confirmed by exploiting the 2005 bankruptcy reform's expansion of repo safe harbors. (2026-10-19, fanfare: 3)

![Scatter plot showing positive relationship between repledgeable collateral and dealer leverage with trend line.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-04-c1753cb9.png)

__[Price of Convenience in Money Markets](https://econpapers.repec.org/RePEc:sfu:sfudps:dp26-12)__: A monetary asset pricing model estimates the convenience yield of liquidity at 5.1% annually, roughly ten times conventional measures, with only 24% attributable to urgency. (2026-10-19, fanfare: 3)

![Urgency share over time showing 24% median contribution to convenience yield.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-05-3f6c9ec4.png)

__[Private Debt Returns in Emerging Markets](https://econpapers.repec.org/RePEc:wbk:wbrwps:11479)__: Analysis of 4,109 loans totaling $115 billion reveals that post-crisis private debt in emerging economies outperforms both emerging-market bonds and Treasuries with public market equivalents above 1.02. (2026-10-19, fanfare: 3)

![Default rates: Crisis versus Normal by Income Group](https://www.ml-quant.com/issues/2026-10-23/figures/repec-06-3154f998.png)

__[LLMs as Intransitive Voting Mechanisms](https://econpapers.repec.org/RePEc:nbr:nberwo:35839)__: The study proves that large language models function as voting rules and identifies millions of Condorcet cycles in ChatGPT investment recommendations, creating potential money-pump vulnerabilities. (2026-10-19, fanfare: 3)

![Observed and predicted effects of temperature on ChatGPT-4o’s pairwise investment recommendations](https://www.ml-quant.com/issues/2026-10-23/figures/repec-07-53e96a64.png)

__[Position Limits and Prediction Market Efficiency](https://econpapers.repec.org/RePEc:nbr:nberwo:35845)__: Analysis of PredictIt shows that limiting investor stakes to $850 per contract undermines price accuracy, with bid prices persistently implying arbitrage profits even after fees. (2026-10-19, fanfare: 3)

![Stacked area chart showing prediction market volume by category over time with peak in middle quarter.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-08-e0bb2eaf.png)

__[Subjective Models Shape Monetary Policy Transmission](https://econpapers.repec.org/RePEc:nbr:nberwo:35831)__: Evidence from a multi-country survey shows that heterogeneous beliefs about how monetary policy works significantly alter households' consumption responses to rate changes. (2026-10-12, fanfare: 3)

![Bar chart showing subjective channels' influence on consumption changes by interaction type.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-09-41bd853d.png)

__[Financial Innovation and Currency Dominance](https://econpapers.repec.org/RePEc:nbr:nberwo:35822)__: Dollar-backed payment stablecoins and tokenization likely reinforce dollar dominance despite reducing transaction frictions, with multipolarity potentially increasing fragility. (2026-10-12, fanfare: 3)

__[Financing AI Data Center Buildout](https://econpapers.repec.org/RePEc:nbr:nberwo:35865)__: Estimates show a 188 GW U.S. AI campus buildout requires nearly $9 trillion through 2032, shifting toward leases, joint ventures, and structures that raise leverage and opacity. (2026-10-19, fanfare: 3)

__[Globalization Flattens the Phillips Curve](https://econpapers.repec.org/RePEc:fip:feddwp:103848)__: Research finds that rising import exposure accounts for roughly 40 percent of U.S. Phillips curve flattening since 1976, with major implications for monetary policy trade-offs. (2026-10-12, fanfare: 3)

![Phillips curve slope decline over time, showing import interaction term effect](https://www.ml-quant.com/issues/2026-10-23/figures/repec-12-0c95eb67.png)

__[Shale Oil and U.S. Macroeconomic Shocks](https://econpapers.repec.org/RePEc:nbr:nberwo:35864)__: The shale revolution shifted how oil supply shocks affect the U.S. economy: contractionary effects weakened and became expansionary as the nation transitioned to net petroleum exporter. (2026-10-19, fanfare: 3)

![Oil price shock effects on U.S. industrial production, inflation, and interest rates comparing pre-2019 and 2021 scenarios.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-13-a71eaa54.png)

__[Emissions Trading System Design Costs](https://econpapers.repec.org/RePEc:zbw:zewdip:343564)__: Completing exchange and allocation authority in the EU's carbon market ETS2 cuts present-value policy costs by EUR 1.33 trillion over 2028-2048 versus partial market creation. (2026-10-12, fanfare: 3)

![Country incidence of market completion](https://www.ml-quant.com/issues/2026-10-23/figures/repec-14-e91b3107.png)

__[Inflation Narratives Drive Risk Premia](https://econpapers.repec.org/RePEc:ecb:ecbwps:20263288)__: Inflation risk premia move inversely with demand-versus-supply narratives extracted from financial news, consistent with asset pricing theory across euro area and U.S. maturities. (2026-09-28, fanfare: 3)

__[Stock-Bond Correlations Shift in Euro Area](https://econpapers.repec.org/RePEc:bfr:banfra:1065)__: A matched-issuer study finds euro-area stock-bond correlations have trended toward zero since 2009, with discount rates driving co-movement but financial stress effects weakening in high-inflation periods. (2026-10-21, fanfare: 2)

![Daily mean correlations of stock-bond pairs trending toward zero since 2009](https://www.ml-quant.com/issues/2026-10-23/figures/repec-16-5db690a6.png)

__[Non-Recursive Filtering for Microstructure Noise](https://econpapers.repec.org/RePEc:tin:wpaper:20260068)__: A new parallel filter removes price microstructure noise from high-frequency trade data without bias, producing flat volatility signatures down to one-second frequencies. (2026-10-10, fanfare: 2)

![Filtered spot volatility for NVDA over 12 trading days in Oct 2024 (19.6M trades), the diurnally adjusted estimator](https://www.ml-quant.com/issues/2026-10-23/figures/repec-17-6c73ea40.png)

__[New Keynesian Model of Term Structures](https://econpapers.repec.org/RePEc:bde:wpaper:2635e)__: A production economy with sticky prices explains equity and bond term structure slopes and cyclicality through countercyclical inflation and habit-driven risk premiums. (2026-10-19, fanfare: 2)

![Time variation of the term structures of one-period returns and yields](https://www.ml-quant.com/issues/2026-10-23/figures/repec-18-2c902034.png)

__[Measuring Sovereign Fragmentation in Euro Area](https://econpapers.repec.org/RePEc:bde:wpaper:2520)__: Research develops a high-frequency fragmentation index decomposing euro-area sovereign yields into common, market-driven, and fundamental components, showing Transmission Protection Instrument effectiveness. (2026-10-19, fanfare: 2)

![Stacked area chart decomposing euro sovereign yield spreads into common, market, and fundamental factors over time.](https://www.ml-quant.com/issues/2026-10-23/figures/repec-19-d35b45a0.png)

__[Invoicing Currency and Country Risk Hedging](https://econpapers.repec.org/RePEc:iza:izadps:dp18943)__: Italian customs data shows firms match import and export invoicing currencies by country to reduce profit volatility from exchange-rate movements in real transactions. (2026-10-13, fanfare: 2)

![Annual EUR/USD Exchange Rate](https://www.ml-quant.com/issues/2026-10-23/figures/repec-20-f0052309.png)

__[Causes of the 2000s Housing Cycle](https://econpapers.repec.org/RePEc:nbr:nberwo:35863)__: A synthesis of two decades of research attributes the housing boom to improved fundamentals, credit expansion, rate declines, and shifting expectations, with defaults driving the bust. (2026-10-19, fanfare: 2)

__[Measuring DeFi Ecosystem Activity](https://econpapers.repec.org/RePEc:dnb:dnbwpp:870)__: The paper identifies three structural sources of measurement divergences in blockchain data and proposes approaches to align technical execution with economic meaning in DeFi ecosystems. (2026-10-12, fanfare: 2)

![Example transaction receipt with token transfer](https://www.ml-quant.com/issues/2026-10-23/figures/repec-22-772444d1.png)

__[Repo Market Participants](https://econpapers.repec.org/RePEc:fip:fednls:103821)__: The research examines who participates in U.S. repo markets, the trade-offs influencing repo segment structure, and the implications for monetary policy transmission. (2026-10-12, fanfare: 2)

![Time series charts showing repo market participation growth and yield trends over time](https://www.ml-quant.com/issues/2026-10-23/figures/repec-23-22fbc655.png)

__[Interest Coverage Covenants and Firm Value](https://econpapers.repec.org/RePEc:hal:journl:hal-05724500)__: A capital structure model shows that interest coverage ratio covenants can improve firm value by reducing default costs, though they constrain shareholder discretion. (2026-10-19, fanfare: 2)

__[Private Equity Fund Manager Disclosures](https://econpapers.repec.org/RePEc:nbr:nberwo:35860)__: The study finds that early textual discussions of portfolio companies better predict ultimate performance, while interim valuations matter more later, signaling general partner quality. (2026-10-22, fanfare: 2)

__[Features of Bayesian Nowcasting Models](https://econpapers.repec.org/RePEc:fip:fedgfe:103878)__: Testing eight model features on US GDP forecasts, the study finds dynamic heterogeneity consistently improves point, density, and tail forecasts while other features help selectively. (2026-10-12, fanfare: 2)

![Balanced paired factorial contrasts for quantile scores, by quantile level](https://www.ml-quant.com/issues/2026-10-23/figures/repec-26-237df620.png)

__[Trade War Spillovers Through Production Networks](https://econpapers.repec.org/RePEc:bde:wpaper:2632e)__: A tariff war model shows asymmetric impacts, with the imposing country bearing inflationary burden and the target experiencing larger output contraction via production network propagation. (2026-10-23, fanfare: 2)

__[Supranational Supervision and Firm Investment](https://econpapers.repec.org/RePEc:ecb:ecbwps:20263286)__: European single supervisory mechanism adoption caused firms to reduce intangible asset shares due to tighter lending and higher collateral standards, especially for small firms. (2026-10-10, fanfare: 2)

![Tier 1 regulatory capital, by country](https://www.ml-quant.com/issues/2026-10-23/figures/repec-28-207c918b.png)

__[Dodd-Frank and M&A Activity](https://econpapers.repec.org/RePEc:hal:journl:hal-05741138)__: Increased credit rating agency scrutiny under Dodd-Frank reduced speculative-grade firms' acquisitions, leading to more selective deals and higher announcement returns. (2026-10-16, fanfare: 2)

__[Uncertainty and Sovereign Debt Equilibria](https://econpapers.repec.org/RePEc:nbr:nberwo:35850)__: The paper characterizes how fiscal uncertainty shrinks the range of multiple equilibria in sovereign debt markets, eventually yielding unique interest rates as uncertainty grows. (2026-10-22, fanfare: 2)