---
title: Quant Letter No. 135: October 2026, Week 3
url: https://www.ml-quant.com/issues/2026-10-16/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-16
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2026-10-16
---

# Quant Letter: October 2026, Week 3: Weekly quantitative finance newsletter

*This week pivots toward machine learning in discovery and execution. Foundation models learn market regimes from order flow; genetic programming and RL agents discover alpha factors across assets and frequencies. But a survey of 47 LLM trading systems finds reported margins vanish on retest, and a massive pre-registered sweep of 18,630 crypto strategies finds none viable. See Foundation Models Learn Market Regimes, EvoQuantLab, and LLM-Based Trading Systems Survey.*

## Top picks

### 1. [Foundation Models Learn Market Regimes](https://arxiv.org/abs/2610.20104) · arXiv

### 2. [LLM-Based Trading Systems Survey](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7610285) · SSRN

### 3. [Large Language Models in Economics Research](https://econpapers.repec.org/RePEc:kan:wpaper:202618) · RePEc

### 4. [EvoQuantLab: Genetic Programming for Factor Discovery](https://arxiv.org/abs/2610.17130) · arXiv

### 5. [Factor Zoo Reallocation Across Market Segments](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7607684) · SSRN

## What's rising

### Text as data: 18 papers this week, 2.2× the usual 8.1

### Crypto assets: 44 papers this week, 1.4× the usual 31.1

### Random forests: 13 papers this week, 1.9× the usual 6.8

## GitHub radar

### Quant repos rising

#### [getnao/nao](https://github.com/getnao/nao): Open source analytics agent for agentic analytics and chat-with-data. (3 quants, 1,937 stars)

#### [marc-shade/world-intel-mcp](https://github.com/marc-shade/world-intel-mcp): MCP server with 139 tools for real-time global intelligence data. (3 quants, 959 stars)

#### [nautechsystems/nautilus\_trader](https://github.com/nautechsystems/nautilus_trader): Production-grade Rust-native trading engine with event-driven architecture. (3 quants, 30.2k stars, +399 this week)

#### [ErTasselli/OpenTerminal](https://github.com/ErTasselli/OpenTerminal): Terminal-style trading dashboard built on free public market data. (2 quants, 1,764 stars, +342 this week, new repo)

#### [KriXord/Agent-Memory-with-Episodic-Retrieval-for-Financial-Decision-Making](https://github.com/KriXord/Agent-Memory-with-Episodic-Retrieval-for-Financial-Decision-Making): Agent memory with episodic retrieval for financial decision-making. (2 quants, 3 stars, +2 this week, new repo)

#### [will-hill/GPU-Quant-Finance](https://github.com/will-hill/GPU-Quant-Finance): GPU-accelerated quantitative finance library. (2 quants, 24 stars, +15 this week)

#### [anthropics/financial-services](https://github.com/anthropics/financial-services): Financial services tools and libraries. (2 quants, 40.0k stars, +863 this week)

#### [polakowo/vectorbt](https://github.com/polakowo/vectorbt): Backtesting engine for thousands of trading ideas. (2 quants, 9,394 stars, +78 this week)

### What quants are playing with

#### [morluto/rea](https://github.com/morluto/rea): Reverse engineer anything with agents, from app behavior down to native binaries. (83 quants, 283k stars, +229k this week)

#### [wheresryan22/anatomy](https://github.com/wheresryan22/anatomy): Agent skill for creating detailed, interactive isometric illustrations of systems. (14 quants, 13.5k stars, +13.5k this week, new repo)

#### [storytold/wordcraft](https://github.com/storytold/wordcraft): Open-source, clean-room reimplementation of Microsoft Word in pure Rust. (9 quants, 13.5k stars, +11.3k this week, new repo)

#### [boykopovar/AnyPS5](https://github.com/boykopovar/AnyPS5): Tool for automatic PS5 executables porting to Linux and Windows. (9 quants, 39.3k stars, +16.0k this week, new repo)

#### [storytold/artcraft](https://github.com/storytold/artcraft): Intentional crafting engine for artists, designers, and filmmakers. (9 quants, 29.9k stars, +17.7k this week)

#### [ARahim3/DigUp](https://github.com/ARahim3/DigUp): Search your computer by file contents: photos, PDFs, documents, recordings, videos. (8 quants, 4,220 stars, +4,219 this week, new repo)

## We called it

### [Merchants of vulnerabilities: How bug bounty programs benefit software vendors](https://arxiv.org/abs/2404.17497): now published in Production and Operations Management (featured 1 May 2024, 5 days after release; 6 citations)

### [Cross-Currency Basis Swaps Referencing Backward-Looking Rates](http://arxiv.org/abs/2410.08477v1): now published in SIAM J. Financial Math. (featured 23 Oct 2024, 12 days after release; 2 citations)

### [When Do AI Gains Become Broadly Shareable? A Policy Threshold for AI-Driven Automation](http://arxiv.org/abs/2505.18687v1): now published in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (featured 30 May 2025, 6 days after release; 1 citations)

## arXiv

__[Foundation Models Learn Market Regimes](https://arxiv.org/abs/2610.20104)__: Autoregressive transformers trained on limit-order-book message streams learn amortized Bayesian inference over market regimes, matching optimal prediction and enabling accurate parameter calibration. (2026-10-15, fanfare: 4)

![Diversity ablation: S1 models, fixed 400M-token budget, K distinct regimes in training (two seeds; bands span seeds)](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-01-04d294f0.png)

__[EvoQuantLab: Genetic Programming for Factor Discovery](https://arxiv.org/abs/2610.17130)__: A training-free framework combines genetic programming and LLM diagnosis loops to discover robust alpha factors across daily and hourly frequencies in equities and cryptocurrency. (2026-10-14, fanfare: 4)

![Cumulative excess return comparison of EvoQuantLab versus competing factor discovery methods over time](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-02-539aa775.png)

__[LLMs Assess Correctness but Not Contribution](https://arxiv.org/abs/2610.18435)__: GPT-4o evaluates research correctness with predictive value for publication but cannot judge originality or significance, suggesting technical peer review can delegate to models while contribution assessment requires people. (2026-10-14, fanfare: 4)

__[Reinforcement Learning for Hawkes Market Making](https://arxiv.org/abs/2610.16524)__: The study proposes a neural network architecture for market making that models self-exciting order arrivals through learnable exponential features and trains via reinforcement learning to optimize quoting policy. (2026-10-14, fanfare: 3)

![Distribution of final \hat{V} across 30 seeds for two intensity-sensitive configurations of Table 1 . Boxes span the](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-04-2189f2b5.png)

__[AlphaPilot: Multi-Turn LLM Agents for Alpha Mining](https://arxiv.org/abs/2610.15488)__: A reinforcement-learning framework trains multi-turn tool-using LLM agents to discover factor expressions by conditioning on market descriptions and querying real-data feedback. (2026-10-14, fanfare: 3)

![Overview of the AlphaPilot training pipeline](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-05-5fdcce40.png)

__[AlphaRLM: Literature-Grounded Factor Discovery](https://arxiv.org/abs/2610.14959)__: An reinforcement-learning framework trains language models to construct executable symbolic factors from financial literature, aligned via market feedback, outperforming baselines on Chinese and U.S. equity indices. (2026-10-14, fanfare: 3)

![AlphaRLM framework overview showing literature-guided factor assembly, market-aligned policy learning, and factor pool construction.](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-06-688b5522.png)

__[GROMM: Arbitrage-Free Option Market Models](https://arxiv.org/abs/2610.16732)__: The research develops a statically and dynamically arbitrage-free model for European option prices with smooth interpolation, fitting market data within bid-ask spreads for over 95% of relevant options. (2026-10-14, fanfare: 3)

![Individual and cumulative variance explained by the spot-oriented DLV factor system](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-07-b54a59e0.png)

__[Phase-Type Point Processes for Event Streams](https://arxiv.org/abs/2610.14948)__: A multiscale phase-type Hawkes model measures how fast prices absorb macroeconomic news versus self-exciting echoes, showing direct absorption in about one second and extended responses up to 137 seconds. (2026-10-14, fanfare: 3)

![Expected cumulative price change, in basis points, after a CPI surprise of +1 (blue) or -1 (orange) standard deviation,](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-08-2943d4b6.png)

__[Market Impact Estimation via Causal Networks](https://arxiv.org/abs/2610.12537)__: A causal prior-data fitted network trained on synthetic market priors estimates true market impact by isolating price movement from trading flow versus information, addressing bias in classical models. (2026-10-12, fanfare: 3)

![Confounding bias in market impact: observational vs interventional slopes across information coupling](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-09-0a88a6c1.png)

__[Earnings-Call Passiveness and Stock Returns](https://arxiv.org/abs/2610.19087)__: Passive-voice fraction in earnings calls predicts temporary mispricings for good news and longer-run underperformance for bad news, independent of standard sentiment measures. (2026-10-15, fanfare: 3)

![Simplified matching rules Example](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-10-647744fa.png)

__[Heavy-Tailed Score Matching for Limit Order Books](https://arxiv.org/abs/2610.21081)__: StochLOB replaces Gaussian noise with jump-Lévy and stable-noise corruptions to capture bursty limit-order-book flow, improving tail-window stress diagnostics on held-out LOB data. (2026-10-16, fanfare: 3)

![Heavy-tailed distribution fits for crypto-BTC showing normal vs. fitted distributions on log scale.](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-11-683d3bf6.png)

__[LLM Stock Forecasting with Event Graphs](https://arxiv.org/abs/2609.34004)__: RICE-Alpha uses event graphs and historical reliability to improve LLM-based stock forecasting, achieving stronger results on Nasdaq-100 and Hang Seng panels than competing LLM agents. (2026-10-16, fanfare: 3)

![Net asset value of Rice-Alpha , the baselines, and the index in (a) the U.S. and (b) Hong Kong from 2024-01-03; models](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-12-4f65a6e1.png)

__[XForecast News-Grounded Stock Prediction](https://arxiv.org/abs/2610.16131)__: XForecast introduces a benchmark combining stock prices with curated financial news to predict four-week-ahead returns, using weighted metrics that emphasize news-driven opportunities. (2026-10-14, fanfare: 3)

__[Semi-Static Hedging in Rough Heston Model](https://arxiv.org/abs/2610.13543)__: The paper shows that combining dynamic trading in the underlying with static positions in three vanilla options reduces variance-swap hedging error by more than 95% across different market roughness regimes. (2026-10-12, fanfare: 3)

![Hedging effectiveness η(m) reaching 99% with m=3 across three Hurst regimes](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-14-0d61cfe2.png)

__[Exit Timing for SPX Short-Straddle Portfolios](https://arxiv.org/abs/2610.13126)__: An MLP-initialized reinforcement-learning framework optimizes exit timing for short-straddle options, achieving 37.54% cumulative return and a Sharpe ratio of 1.705 out-of-sample over 2024-2026. (2026-10-12, fanfare: 3)

![Out-of-sample portfolio NAV and drawdown for the deterministic strategies, representative reinforcement-learning runs,](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-15-bb0eae0a.png)

__[Attribution-Propagation for ML Portfolio Adaptation](https://arxiv.org/abs/2610.15144)__: A first-order attribution framework maps feature exposures to portfolio-performance sensitivities, enabling post-training intervention that improves net Sharpe ratios without retraining. (2026-10-14, fanfare: 3)

![Evolution of cross-model feature-structure similarity between XGB and FFN. Each curve is a 63-day moving average](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-16-54a0cc5f.png)

__[CorrFlow: Equivariant Correlation-Matrix Generation](https://arxiv.org/abs/2610.13606)__: A generalized Fisher transform and permutation-equivariant flow-matching network generate valid correlation matrices with 100% validity and superior feature distances versus GAN and diffusion baselines. (2026-10-12, fanfare: 3)

![The spectral change between the full, naturally weighted training and test splits](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-17-95668f10.png)

__[Monte Carlo Tree Search for Feature Selection](https://arxiv.org/abs/2610.13574)__: A Monte Carlo Tree Search framework selects predictive features by out-of-sample validation rather than training error, improving stability and interpretability under multicollinearity. (2026-10-12, fanfare: 3)

![Correlation matrix of the best performing individual 15-feature GNRPA subset](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-18-8d846868.png)

__[Backtesting Defects in Live Intraday Systems](https://arxiv.org/abs/2610.21846)__: Six defects from data, code, and configuration caused live intraday trading to diverge from backtest replay, none visible in summary statistics, each requiring specific controls. (2026-10-16, fanfare: 2)

__[Early Detection of Pension Sponsor Distress](https://arxiv.org/abs/2610.14120)__: A gradient-boosted classifier predicts pension sponsor distress one to two quarters ahead from SEC filings, reaching 0.887 AUC-ROC, with application to dynamic self-investment caps in sponsor securities. (2026-10-14, fanfare: 3)

![SVI (full-sample refit) for a subset of sponsors, 2015–2025](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-20-90b57054.png)

__[Bayesian Optimization of CVaR with Unknown Kernels](https://arxiv.org/abs/2610.18306)__: HE-CV-UCB adaptively eliminates misspecified surrogate models and achieves no-regret Conditional-Value-at-Risk optimization when kernel hyperparameters are unknown. (2026-10-14, fanfare: 3)

![CVaR regret comparison showing HE-CV-UCB achieving zero regret versus baseline methods on synthetic spike function](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-21-b32a24da.png)

__[E-Backtesting Expected Shortfall Without VaR](https://arxiv.org/abs/2610.17681)__: Sequential backtests for Expected Shortfall using only observed losses and ES forecasts control false rejections, with time-series extension under AR-GARCH structure proving convergent under grid refinement. (2026-10-14, fanfare: 2)

![Mean log capital before and after the reporting change ( N=1000 )](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-22-dd228597.png)

__[Structured SDEs for Realized GARCH Forecasting](https://arxiv.org/abs/2610.17732)__: A continuous-time volatility model incorporating realized measures forecasts one-day-ahead integrated variance, showing strong out-of-sample performance relative to GARCH and related benchmarks across 17 equity indices. (2026-10-14, fanfare: 2)

![One-step-ahead variance forecasts of the proposed SDE and Realized GARCH for representative equity indices](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-23-434a3115.png)

__[Tail-Risk Conditional Autoregressive Expectile Models](https://arxiv.org/abs/2610.13446)__: A realized tail-risk model using high-frequency intraday data forecasts value-at-risk and expected shortfall with competitive performance across U.S. stock returns and multiple tail levels. (2026-10-12, fanfare: 2)

![VaR and ES forecasts overlay returns, showing model performance capturing tail risk dynamics.](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-24-a13b1b25.png)

__[Identification in Multivariate Hawkes Processes](https://arxiv.org/abs/2610.19428)__: The study characterizes how latent common signals generate spurious cross-excitation in Hawkes models and uses third-order cumulants to identify true excitation mechanisms, with applications to cryptocurrency data. (2026-10-15, fanfare: 2)

![Exact directional asymmetry (\bar{\Psi}\_{21}-\bar{\Psi}\_{12})/(\bar{\Psi}\_{21}+\bar{\Psi}\_{12}) in the symmetric](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-25-d688c5e8.png)

__[SwingGuard: Risk-Conditioned Swing Trading Agents](https://arxiv.org/abs/2610.12988)__: A dual-timescale multi-agent framework generates trading strategies conditioned on current risk and maintains ongoing position governance between strategy revisions on cryptocurrency, preserving returns after transaction costs. (2026-10-12, fanfare: 2)

![BTC, ETH, and capped portfolio performance with cumulative returns and drawdown paths.](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-26-4cbd99a3.png)

__[Screening, Speed, and Maker Spreads](https://arxiv.org/abs/2610.21510)__: The research derives break-even screening rates for liquidity providers defending against stale quotes, showing that one-second repricing requires far less screening than Gaussian models predict. (2026-10-16, fanfare: 2)

![Posted fee, revenue at execution, and five-second adverse selection across the Uniswap pools](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-27-1340b34c.png)

__[Vine Copula Simulation with Reinforcement Learning](https://arxiv.org/abs/2610.20037)__: A data-driven approach combines vine-copula simulation with reinforcement learning to optimize dynamic portfolio selection across equities and gold with CVaR penalties. (2026-10-15, fanfare: 2)

![Net wealth and drawdown re-compounded from the 22 retained net returns, with initial wealth of 100,000](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-28-2a2abea2.png)

__[Intermediary Liquidity and Debt Relief Financing](https://arxiv.org/abs/2610.12875)__: Using Ginnie Mae buyout options, the study finds that nonbank issuers repurchase fewer delinquent loans when funding markets freeze, delaying about $19 billion in mortgage resolution compared to depositories. (2026-10-12, fanfare: 2)

![Nonbank exercise temporarily shifted away from large balances](https://www.ml-quant.com/issues/2026-10-16/figures/arxiv-29-89782258.png)

__[Liquidity Provision and Transaction-Cost Benchmarks](https://arxiv.org/abs/2610.21057)__: The study shows that automated market maker pools matched to transaction-cost-aware benchmarks have zero loss-versus-rebalancing, clarifying the investment interpretation of pool design. (2026-10-16, fanfare: 2)

## SSRN

__[LLM-Based Trading Systems Survey](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7610285)__: A survey of 47 LLM trading systems across six markets finds that reported margins shrink or vanish when rerun, with best evidence placing language models upstream of execution. (2026-10-15, fanfare: 4)

__[Factor Zoo Reallocation Across Market Segments](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7607684)__: Rejected factors earn 1.30 Sharpe in their home market versus 0.85 overall, yielding 3.8% six-factor alpha per year through venue reallocation constrained by signal-to-noise limits. (2026-10-14, fanfare: 4)

__[Pre-Registered Rates and Currency VaR](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7616161)__: A frozen Gaussian VaR model, pre-registered and anchored in Bitcoin, passed coverage tests but showed clustering in 2020, 2022 and 2023, while exponentially weighted variance improved. (2026-10-16, fanfare: 4)

__[Pre-Registered Trading Strategy Search Results](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7594361)__: A blockchain-verified sweep of 18,630 cryptocurrency and FX trading variants found no strategies exceeding a Deflated Sharpe of 0.95, with median detectable Sharpe of 3.49 and collective underperformance versus random selection. (2026-10-12, fanfare: 4)

__[Itô Formula for Rough Volatility Inference](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7615661)__: A new calculus framework for rough volatility below the semimartingale regime enables bias-corrected estimation of leverage effects and roughness with central limit theorems, rejecting semimartingale assumptions for recent S&P data. (2026-10-15, fanfare: 4)

__[Infinite Factor Structure in Asset Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7596842)__: The research reveals that pooling returns across market states creates an infinite-factor structure unconditionally, meaning infinitely many priced components and no finite principal-component basis for expected returns. (2026-10-12, fanfare: 4)

__[Machine Learning Methods in Asset Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7611982)__: A survey reviews machine learning methods for predicting stock returns in time series and cross-section, covering LASSO regularization, deep learning, genetic programming, and LLM applications. (2026-10-14, fanfare: 3)

__[Tail Risk and Equity Premium Prediction](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7593226)__: Using partial least squares on 18 tail-risk proxies, the study constructs an index that strongly predicts the equity premium both in- and out-of-sample. (2026-10-10, fanfare: 3)

__[Machine Learning Forecasts Systemic Crises](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7614659)__: Random forests and gradient boosting forecast financial crises across 147 years and 17 countries with 77 percent accuracy, using real-sector predictors as the dominant source. (2026-10-15, fanfare: 3)

__[Transformer Stock Prediction Across Horizons](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7605161)__: Transformer-based models capture pricing signals via self-attention that boost out-of-sample Sharpe ratios across one-, three-, six-, and twelve-month stock return forecasts, outperforming standard machine learning approaches. (2026-10-14, fanfare: 3)

__[Analyst Sentiment Predicts M&A Deal Failure](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7604418)__: Language models analyzing analyst tone in M&A calls reveal that fear and anxiety about deals predict completion delays, failure, and long-run underperformance even when markets initially react favorably. (2026-10-13, fanfare: 3)

__[Pooled ML for International Multi-Asset Allocation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7610204)__: Machine learning forecasts of equity, bond, bill and housing returns from 1870-2020 across 16 countries improve Sharpe ratios substantially when trained on pooled cross-country data rather than country-specific samples. (2026-10-15, fanfare: 3)

__[Liquidity Reweighting for ML Return Forecasts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7617338)__: Trading-cost aware portfolio construction that reweights holdings by liquidity and trades only when forecasts exceed the bid-ask spread lifts net Sharpe from negative to positive on machine learning predictions. (2026-10-16, fanfare: 3)

__[Arbitrage in Logically Related Prediction Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7587019)__: Integer programming identifies arbitrage across linked prediction-market contracts where prices violate logical constraints, recovering 1.9 million relations and earning 2.2% guaranteed profit after spreads and fees. (2026-10-10, fanfare: 3)

__[Fed Deposits and Bank Lending Through Primary Dealers](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7617178)__: The study shows deposit inflows from quantitative easing at primary dealers predict subsequent lending and employment growth in exposed counties, revealing a concentrated channel for monetary transmission. (2026-10-15, fanfare: 3)

__[Index Rebalancing Price Pressure in Bonds](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7601879)__: Month-end index rebalancing that increases duration generates predictable demand and 1.19 basis points of monthly return concentrated on the rebalancing day in government bond futures. (2026-10-14, fanfare: 3)

__[Consumption-Implied Stock Valuation Cycle](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7600358)__: Stock prices and consumption share a long-run trend whose deviations mean-revert and predict market returns over one to two years, identifying consumption as a macroeconomic anchor for asset values. (2026-10-12, fanfare: 3)

__[CNN Term-Structure Surfaces for Commodity Carry](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7600983)__: Encoding commodity futures curves as time-maturity surfaces and applying convolutional networks extracts carry information that predicts returns beyond standard factors and improves the mean-variance frontier. (2026-10-12, fanfare: 3)

__[Size Premium in Brazilian Equity and Credit](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7607262)__: The study finds no equity size premium in Brazil, but an unexplained 6.8 to 8.8 percentage point credit spread for small firms that rises sharply with corporate delinquency. (2026-10-13, fanfare: 3)

__[High-Frequency Trading Quality in China](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7599578)__: Order-level latency variation at China's exchange shows that HFT raises short-horizon price noise and adverse-selection costs but slightly improves pricing efficiency. (2026-10-12, fanfare: 3)

__[Jump Risk Premiums in Cryptocurrency](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7604181)__: Cryptocurrencies sensitive to positive market jumps earn lower returns, a negative premium unexplained by coskewness and strongest when retail sentiment is high. (2026-10-13, fanfare: 3)

__[Model Capacity and Signal-to-Noise Tradeoff](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7595679)__: Comparing predictive models across US and Indian equity markets shows that additional capacity helps when signal is strong but not when it is weak, with simplest models matching complex ones in high-noise regimes. (2026-10-13, fanfare: 3)

__[Repo Haircuts and Dealer Constraints](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7618239)__: The study shows that dealer balance-sheet constraints, collateral convenience yields, and client outside options jointly determine repo haircuts, with leverage ratios reshaping market functioning and monetary policy transmission. (2026-10-16, fanfare: 3)

__[Electoral Risk and Crypto Connectedness](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7613178)__: Elections in major democracies raise cryptocurrency correlation, reducing portfolio diversification, with the effect driven by shifting expectations about future regulatory environments. (2026-10-16, fanfare: 3)

__[Synthetic Leverage Costs in Leveraged ETFs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7603998)__: Single-stock leveraged ETFs incur excess financing costs averaging 6.2% annually through total-return swaps, fully passed to investors and substantially larger than disclosed expense ratios. (2026-10-13, fanfare: 3)

__[Shiller CAPE Predictive Power Over 140 Years](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7603798)__: The CAPE ratio significantly predicts ten-year real stock returns across 1881–2023 even after rigorous statistical tests, with out-of-sample predictive power highly dependent on market regime. (2026-10-13, fanfare: 3)

__[Currency Risk in Remittance Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7600423)__: Exchange-rate hedging costs explain about 16 percent of remittance fees, especially in thin currency markets, and induce operators to adjust variable fees while raising exit risk. (2026-10-12, fanfare: 3)

__[Regimes to Portfolios via Gradient Boosting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7595598)__: An interpretable machine-learning framework linking regime identification to cross-asset portfolio construction earns 0.60 net Sharpe, not significantly different from a 60/40 benchmark. (2026-10-12, fanfare: 2)

__[NoLBERT News Topics and Stock Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7617420)__: A news reader trained only on pre-1995 text produces stable topics but earns 1.12 monthly Sharpe via ensemble with other readers, significant before multiple-testing adjustment. (2026-10-16, fanfare: 2)

__[Malliavin-Informed Policy Gradients for Portfolio Optimization](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7598820)__: The paper develops a Malliavin-informed policy-gradient estimator using stochastic control variates to reduce variance in continuous-time reinforcement learning for dynamic portfolio selection. (2026-10-14, fanfare: 2)

## RePEc

__[Large Language Models in Economics Research](https://econpapers.repec.org/RePEc:kan:wpaper:202618)__: A review of LLM applications finds that contextual interpretation improves some tasks but measurement error persists, and trading signals do not always generate profits. (2026-10-15, fanfare: 4)

__[Whale Trades and Cryptocurrency Market Dynamics](https://econpapers.repec.org/RePEc:fip:fedpwp:103741)__: Large bitcoin trades reshape participant composition and trigger herding, raising volatility, while ethereum whales produce minimal market impact, revealing persistent information asymmetries. (2026-10-09, fanfare: 3)

![Percentage change in non-whale buy activity peaks 15 minutes after whale alerts across investor sizes.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-02-0525d1e4.png)

__[NBFIs as Crisis Shock Absorbers](https://econpapers.repec.org/RePEc:imf:imfwpa:2026/197)__: Nonbank financial institutions contract loan syndication during banking crises but expand bond underwriting, helping firms that maintain NBFI relationships weather downturns better. (2026-10-10, fanfare: 3)

__[Macro-Financial Crisis Prediction Framework](https://econpapers.repec.org/RePEc:tin:wpaper:20260074)__: A mixture-of-experts approach combining ensemble models and logistic regression predicts developing-economy crises while decomposing risk into interpretable fiscal and financial components. (2026-10-10, fanfare: 3)

![Comparison of balanced scores (F1-score) across different crisis decision](https://www.ml-quant.com/issues/2026-10-16/figures/repec-04-0bbfdff1.png)

__[Transformer Models for Financial Sentiment](https://econpapers.repec.org/RePEc:ecb:ecbwps:20263283)__: FinBERT-based sentiment measures agree more closely with human raters than dictionary methods and better distinguish positive, neutral, and negative financial news articles. (2026-10-09, fanfare: 3)

![Confusion matrices comparing transformer-based and dictionary sentiment measures against human labels](https://www.ml-quant.com/issues/2026-10-16/figures/repec-05-75d42ea7.png)

__[Gold and Geopolitical Reserve Currency Risk](https://econpapers.repec.org/RePEc:nbr:nberwo:35669)__: Rising geopolitical risk fragments safe-asset demand: countries shift toward gold when sanction risk heightens, raising gold prices and Treasury yields as US convenience yields fall. (2026-10-05, fanfare: 3)

![Bond and gold prices spike around geopolitical transition, showing flight-to-safety behavior.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-06-78fc986f.png)

__[US Tightening and Emerging Market Resilience](https://econpapers.repec.org/RePEc:nbr:nberwo:35673)__: The study compares monetary tightening in the 1980s and 2020s, finding that fiscal space—not exchange-rate flexibility alone—explains why emerging markets have avoided crisis this time. (2026-10-05, fanfare: 3)

![Foreign exchange reserves to GDP ratios were much lower in 1982 than in 2022](https://www.ml-quant.com/issues/2026-10-16/figures/repec-07-c85a2c1f.png)

__[Rising Income Risk Among Top Earners](https://econpapers.repec.org/RePEc:nbr:nberwo:35664)__: Analysis of IRS tax returns shows permanent income risk rose nearly 70% among the top 5% since the 1970s, depressing risk-free rates and widening wealth inequality. (2026-10-07, fanfare: 3)

![Income risk evolution 1970-2010 across income percentiles for employed and non-employed households.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-08-e00239e3.png)

__[Climate Policy Uncertainty and Financial Stress](https://econpapers.repec.org/RePEc:baf:cbafwp:cbafwp26285)__: A structural VAR shows climate policy uncertainty depresses equities and raises financial stress through credit channels, creating supply-driven downturns distinct from conventional uncertainty shocks. (2026-10-10, fanfare: 3)

![Uncertainty Measures](https://www.ml-quant.com/issues/2026-10-16/figures/repec-09-6aab96ea.png)

__[Inflation Inattention on Production Networks](https://econpapers.repec.org/RePEc:fip:fedcwq:103851)__: The research shows that firms in industries with larger network weights forecast inflation more accurately, and production networks endogenously increase nominal rigidity by about 30 percent. (2026-10-12, fanfare: 3)

![Industry characteristics and forecast accuracy in the model](https://www.ml-quant.com/issues/2026-10-16/figures/repec-10-b26d4882.png)

__[Private Money History and Stablecoins](https://econpapers.repec.org/RePEc:pri:cepsud:359)__: The paper uses monetary history to identify five institutional foundations for scalable private money and assesses how contemporary stablecoins and the GENIUS Act address them. (2026-10-12, fanfare: 3)

![Official Foreign Exchange Reserves by Currency](https://www.ml-quant.com/issues/2026-10-16/figures/repec-11-755b0430.png)

__[Bayesian Geopolitical Oil Price Scenarios](https://econpapers.repec.org/RePEc:bde:opaper:2616e)__: A framework maps Middle East geopolitical risk to oil prices and inflation through scenario analysis updated in real time using market prices and expert assessments. (2026-10-05, fanfare: 3)

![Three-block operational framework: geopolitical scenarios to physical supply disruption to Brent price paths.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-12-8bb9f557.png)

__[Financial Interdependence and Currency Competition](https://econpapers.repec.org/RePEc:nbr:nberwo:35541)__: A model shows that as China's financial markets deepen, network effects allow the renminbi to compete with the dollar, triggering a discrete shift from cooperation to fragmentation. (2026-10-05, fanfare: 3)

![Two curves showing dollar and yuan issuance equilibria across financial market depth parameters.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-13-f4b64638.png)

__[DSGE Estimation with FOMC Text Data](https://econpapers.repec.org/RePEc:nbr:nberwo:35487)__: Incorporating unstructured text from Federal Reserve transcripts into a DSGE model sharpens monetary policy inference and implies a flatter, less backward-looking Phillips curve. (2026-10-07, fanfare: 3)

__[AI Capital and Skill Complementarity](https://econpapers.repec.org/RePEc:fip:fedcwq:103765)__: A calibrated model finds AI complements high-skill workers and equipment, with AI price declines expansionary but increased usage contractionary due to complementarity constraints. (2026-10-07, fanfare: 3)

![Transitory impulse response: halve AI price (ρ = 0.90)](https://www.ml-quant.com/issues/2026-10-16/figures/repec-15-65a06391.png)

__[Monetary Pass-Through in European Credit Markets](https://econpapers.repec.org/RePEc:mnb:wpaper:2026/1)__: ECB tightening passes nearly fully to mortgage rates but weakly to consumer credit, with younger borrowers facing stronger mortgage pass-through than older ones. (2026-10-12, fanfare: 2)

![Horizontal bar charts comparing pass-through effects by age, maturity, and interest rate position across credit markets.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-16-cf913f3a.png)

__[QE Effects Through Corporate Bond Markets](https://econpapers.repec.org/RePEc:boe:boeewp:023256)__: Bank of England quantitative easing lowered corporate bond yields but did not increase real investment; instead firms used proceeds for buybacks and reduced bank borrowing. (2026-10-09, fanfare: 2)

![Maturity rating distribution of bond issuance](https://www.ml-quant.com/issues/2026-10-16/figures/repec-17-178c04d4.png)

__[Debt Dictionaries in Financial Markets](https://econpapers.repec.org/RePEc:fip:fedpwp:103784)__: Stock and bond investors extract different value signals from earnings calls, with bondholders emphasizing operations and risk while equityholders focus on growth and innovation. (2026-10-16, fanfare: 2)

![Scattertext Visualization of Stock and Bond Reactions](https://www.ml-quant.com/issues/2026-10-16/figures/repec-18-76d9f04f.png)

__[Solvency-Liquidity Bank Stress Testing](https://econpapers.repec.org/RePEc:boe:boeewp:023262)__: A stochastic balance-sheet model quantifies how solvency and liquidity risks interact, finding that amplification effects from behavioral responses explain roughly one-third of default risk. (2026-10-07, fanfare: 2)

![Weighted Average Probability of Default Comparison with Market Estimates](https://www.ml-quant.com/issues/2026-10-16/figures/repec-19-9a89c2e0.png)

__[Corporate Bond Demand Multipliers](https://econpapers.repec.org/RePEc:ehl:lserod:138916)__: Heterogeneous substitutability between corporate bonds implies security-level multipliers are much smaller than previous estimates, though portfolio multipliers remain substantial. (2026-10-12, fanfare: 2)

__[Corridor Invoicing as Real Hedging](https://econpapers.repec.org/RePEc:bol:bodewp:wp1232)__: Italian trade data reveals firms use invoicing currency bilaterally and by country to hedge country-specific risk, not just currency risk, reducing profit variance beyond net exposure. (2026-10-13, fanfare: 2)

![Annual EUR/USD Exchange Rate](https://www.ml-quant.com/issues/2026-10-16/figures/repec-21-f0052309.png)

__[Reserve Accumulation and Sovereign Debt Dynamics](https://econpapers.repec.org/RePEc:sad:ypaper:23)__: The research finds that reserve adequacy shapes how global financial shocks transmit to sovereign spreads and external debt in emerging markets, with over-accumulation dampening spread responses. (2026-10-05, fanfare: 2)

![Reserves, public debt, and sudden stops in emerging and advanced economies](https://www.ml-quant.com/issues/2026-10-16/figures/repec-22-cfda845d.png)

__[Oil and Non-Oil Geopolitical Risk on US Volatility](https://econpapers.repec.org/RePEc:pre:wpaper:202626)__: Decomposing geopolitical risk into oil and non-oil components predicts US industry stock volatility better than aggregate measures across 49 sectors. (2026-10-09, fanfare: 2)

![Estimated coefficients for GPR-Oil (left column) and GPR-NonOil (right column) in model M3, across the 49 Fama-French](https://www.ml-quant.com/issues/2026-10-16/figures/repec-23-50bc9d5a.png)

__[Cryptocurrency Dependence Under Market Stress](https://econpapers.repec.org/RePEc:hal:journl:hal-05752791)__: The study proposes a multi-stage method combining neural networks and copulas to detect regime changes and finds cryptocurrency dependence with traditional assets increases sharply during crises. (2026-10-12, fanfare: 2)

![Network graphs showing cryptocurrency connectedness with traditional assets across crisis and normal periods](https://www.ml-quant.com/issues/2026-10-16/figures/repec-24-7cee04ae.png)

__[Exchange Rates and Information-Driven Premia](https://econpapers.repec.org/RePEc:imf:imfwpa:2026/188)__: A model shows asymmetric information about monetary policy can make exchange-rate risks uninsurable, generating foreign-exchange premia and opening a case for policy coordination. (2026-10-05, fanfare: 2)

__[Government Debt, Non-Banks, and Market Dysfunction](https://econpapers.repec.org/RePEc:bis:bisblt:136)__: The analysis finds high public debt and growing non-bank footprint increase the risk of market dysfunction in government debt markets while making very favorable conditions more likely. (2026-10-10, fanfare: 2)

![Bar chart comparing non-banks, domestic central bank, banks, and foreign official holders of government debt between 2021 and 2025.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-26-11e12aad.png)

__[Digital Lending, Bank Risk, and Competition in Mexico](https://econpapers.repec.org/RePEc:imf:imfwpa:2026/198)__: Digital lending by non-banks reduces individual bank risk-taking and competition, with moderate systemic effects and stronger pressure on smaller banks. (2026-10-08, fanfare: 2)

__[Retail Access to Private Markets: Equilibrium Effects](https://econpapers.repec.org/RePEc:nbr:nberwo:35665)__: Opening private markets to retail investors modestly improves their welfare while reducing firms' cost of capital and shrinking private equity alpha. (2026-10-09, fanfare: 2)

![Retail participation conditions and participation rates in private markets by firm capital share.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-28-d31d0247.png)

__[Public Carry Trades and Korea's Fiscal Sustainability](https://econpapers.repec.org/RePEc:fip:fedlwp:103774)__: Korea's carry-trade strategy strengthens public net worth near-term but cannot offset projected deficits or restore long-term fiscal sustainability without reform. (2026-10-09, fanfare: 2)

![Comparison of NPS reported returns with proxy indices](https://www.ml-quant.com/issues/2026-10-16/figures/repec-29-0218c6d3.png)

__[Inflation Targets and Zero Lower Bound Risk](https://econpapers.repec.org/RePEc:ise:remwps:wp04282026)__: Switzerland and Japan face the highest risk of hitting the zero bound under current inflation targets; higher average inflation substantially reduces this constraint. (2026-10-05, fanfare: 2)

![Zero lower bound probability curves across eight countries by inflation target level.](https://www.ml-quant.com/issues/2026-10-16/figures/repec-30-97940ac0.png)