---
title: Quant Letter No. 133: October 2026, Week 1
url: https://www.ml-quant.com/issues/2026-10-02/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-02
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2026-10-02
---

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

*This week centers on AI's expanding role in trading and markets, alongside persistent microstructure patterns and monetary policy transmission. Key papers: "AI Trading Methods: Backtests Versus Real Markets" measures the live-market gap for machine learning and LLM strategies; "Certified Alpha Capacity and Decay" derives exact deployment thresholds before signal decay; "AlphaPareto" applies reinforcement learning to multi-objective alpha discovery. Corporate bond signals predict equity returns; FOMC surprises persist; US rate shocks widen global spreads.*

## Top picks

### 1. [Certified Alpha Capacity and Decay](https://arxiv.org/abs/2610.01115) · arXiv

### 2. [Bond Signals Predict Next-Month Equity Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7527218) · SSRN

### 3. [AI and Corporate Bond Pricing](https://econpapers.repec.org/RePEc:bdi:opques:qef_1057_26) · RePEc

### 4. [AI Trading Methods: Backtests Versus Real Markets](https://arxiv.org/abs/2609.34510) · arXiv

### 5. [Macroeconomic Effects of AI Technology Shocks](https://econpapers.repec.org/RePEc:bdi:wptemi:td_1542_26) · RePEc

## What's rising

### Rough volatility: 7 papers this week

### Reinforcement learning: 28 papers this week, 2.1× the usual 13.3

### Factor models: 32 papers this week, 1.8× the usual 17.3

### Geopolitical risk: 28 papers this week, 1.8× the usual 15.5

### Systemic risk: 44 papers this week, 1.5× the usual 29.2

## GitHub radar

### Quant repos rising

#### [brainbrick-trades/The-Quant-Trading-Vault](https://github.com/brainbrick-trades/The-Quant-Trading-Vault): Collection of 5800+ trading strategies. (3 quants, 335 stars, +335 this week, new repo)

#### [electkismet/AxData](https://github.com/electkismet/AxData): Open-source quantitative database framework for China stocks. (3 quants, 269 stars, +26 this week, new repo)

#### [vivek-v-rao/moving-average-systems](https://github.com/vivek-v-rao/moving-average-systems): Grid search and backtesting for moving-average crossover strategies. (2 quants, 7 stars, +4 this week, new repo)

#### [jarrodwatts/jev-trader](https://github.com/jarrodwatts/jev-trader): AI trade decision agent on Monad blockchain. (2 quants, 2,748 stars, +325 this week, new repo)

#### [nftechie/stonkfly](https://github.com/nftechie/stonkfly): Fly connectome simulation with Coinbase agent trading. (2 quants, 865 stars, +39 this week, new repo)

#### [vivek-v-rao/price-check](https://github.com/vivek-v-rao/price-check): Cross-provider market data validation for OHLCV prices. (2 quants, 16 stars, +16 this week, new repo)

#### [shy3130/tick-stock-panel](https://github.com/shy3130/tick-stock-panel): Self-hosted A-stock selection monitoring and backtesting platform. (2 quants, 5,365 stars, +182 this week)

### What quants are playing with

#### [vectorize-io/hindsight](https://github.com/vectorize-io/hindsight): Agent memory system that learns from interactions. (12 quants, 44.5k stars, +14.5k this week)

#### [Contrastive-LM/CLM](https://github.com/Contrastive-LM/CLM): No description available. (9 quants, 2,719 stars, +1,395 this week, new repo)

#### [NVIDIA/OpenShell](https://github.com/NVIDIA/OpenShell): Safe private runtime for autonomous AI agents. (9 quants, 14.3k stars, +5,482 this week)

#### [NandhaKishorM/laya](https://github.com/NandhaKishorM/laya): Non-autoregressive decision engine for text classification over 100 languages. (8 quants, 30.1k stars, +5,194 this week, new repo)

#### [NVIDIA/structured-data-models](https://github.com/NVIDIA/structured-data-models): Foundation models for structured data. (7 quants, 270 stars, +246 this week)

#### [dzhng/jevgrep](https://github.com/dzhng/jevgrep): CLI for coding agents to find code by description. (6 quants, 2,041 stars, +2,040 this week, new repo)

## We called it

### [Optimal automation under overdispersed discrete risk: thresholds and hysteresis in a Negative Binomial model](http://arxiv.org/abs/2510.05487v1): now published in Journal of Industrial and Management Optimization (featured 9 Oct 2025, 2 days after release; 1 citations)

### [Market-driven equilibria for distributed photovoltaic panel investment](http://arxiv.org/abs/2509.07203v1): now published in Applied Energy (featured 13 Sep 2025, 5 days after release)

### [Impacts of large-scale food fortification on the cost of nutrient-adequate diets: a modelling study in 89 countries](http://arxiv.org/abs/2511.05438v1): now published in BMJ Public Health (featured 12 Nov 2025, 5 days after release)

## arXiv

__[Certified Alpha Capacity and Decay](https://arxiv.org/abs/2610.01115)__: The research measures when a trading signal accumulates enough statistical evidence for deployment before its economic value decays, deriving exact feasibility thresholds. (2026-10-02, fanfare: 4)

![Alpha Survival Frontier curves showing minimum half-life versus Sharpe ratio for different search spaces.](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-01-7d750408.png)

__[AI Trading Methods: Backtests Versus Real Markets](https://arxiv.org/abs/2609.34510)__: A benchmark compares machine learning, reinforcement learning, and large language model trading methods across historical backtests, paper trading, and live markets to measure the gap. (2026-09-29, fanfare: 4)

![AI Trading Methods: Backtests Versus Real Markets](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-02-f133c303.png)

__[AlphaPareto: Formulaic Alpha Discovery with RL](https://arxiv.org/abs/2609.34188)__: The research uses reinforcement learning with multi-objective rewards to discover formulaic alphas that work well together despite evolving reward functions and shifting environments. (2026-09-29, fanfare: 3)

![Overview of the AlphaPareto framework](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-03-6f7e5961.png)

__[Learning to Forecast by Learning to Search](https://arxiv.org/abs/2610.01955)__: Training teaches a language model to improve event forecasting by learning which evidence to gather, beating frontier models on hard questions at lower cost. (2026-10-02, fanfare: 3)

![Anchor-worth: the paired Brier cost of withholding the market price, per policy](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-04-765d19f0.png)

__[Point-in-Time Adaptation for Financial Models](https://arxiv.org/abs/2609.30316)__: A new method adapts financial language models to avoid look-ahead bias using low-rank adapters instead of expensive annual retraining, matching performance of full pretraining. (2026-09-28, fanfare: 3)

![Naive LLM vs](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-05-a7c10a68.png)

__[Market Microstructure in the Age of AI](https://arxiv.org/abs/2609.33058)__: A survey traces how market design has evolved from floor trading through electronic exchanges to AI agents, examining whether markets can allocate goods efficiently without full revelation. (2026-09-29, fanfare: 3)

![Timeline of market microstructure evolution from auction theory through electronic and on-chain markets to AI agents.](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-06-5db1526f.png)

__[Strategic Narratives and Market Positioning](https://arxiv.org/abs/2609.38545)__: The research shows when to follow or fade financial narratives by studying the covariance between institutional statements and revealed trading positions using machine learning. (2026-10-01, fanfare: 3)

![Out-of-sample forecasts in the main simulated market](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-07-3821334c.png)

__[Admissible Portfolio Optimization with Information](https://arxiv.org/abs/2610.00147)__: The research makes conditioning information a decision variable subject to constraints, solving how look-ahead bias and information availability affect portfolio choice and causal identification. (2026-10-02, fanfare: 3)

![Two contracts](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-08-804da70a.png)

__[Uncertainty Quantification for LOB](https://arxiv.org/abs/2609.31491)__: A lightweight module adds confidence estimates to limit-order-book forecasters, raising directional F1 by 0.11-0.15 when predicting the most confident 10% of trades. (2026-09-28, fanfare: 3)

![Directional F1 score versus confidence percentile across assets and horizons, showing performance gains.](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-09-deac3120.png)

__[LLM Textual Measures Diverge](https://arxiv.org/abs/2609.31013)__: Cross-model rank correlations for LLM-extracted sentiment, clarity and risk average only 0.52, and model choice significantly alters coefficient signs and significance in downstream analysis. (2026-09-28, fanfare: 3)

![Figure OA.D.1 : Self-reported confidence: distribution and conditional agreement](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-10-d7d6ea9e.png)

__[Negative Oil and Commodity Squeeze Feedback](https://arxiv.org/abs/2610.00951)__: A feedback model explains extreme commodity futures prices like negative oil by connecting delivery constraints to roll options and long-short position imbalances. (2026-10-02, fanfare: 3)

![Case 1 Monte Carlo illustration](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-11-66db2a43.png)

__[PropAMM Liquidity On Chain](https://arxiv.org/abs/2609.38056)__: Proprietary AMMs earn 0.37 to 1.19 basis points within two seconds by repricing continuously and avoiding arbitrage, compared to passive AMMs losing 0.22 to 0.62 basis points. (2026-09-30, fanfare: 3)

![Tessera ETH/USDC prices and spreads within Base block 50,196,022](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-12-4a043991.png)

__[Replayable Limit Order Book Generation](https://arxiv.org/abs/2609.35867)__: A method generates realistic limit order book messages guaranteed to be consistent with current market state, achieving 100% replayability and 2.7–3.6× speedup over existing approaches. (2026-09-30, fanfare: 3)

![Mean resting-order coverage increases with history length for GOOG and INTC stocks](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-13-45446773.png)

__[HFT System Design from CME Data](https://arxiv.org/abs/2609.32848)__: Measurement of over a year of CME market data reveals transactions cluster within microseconds, yielding design principles: single-thread receivers never queue, two-thread splits reduce tail latency. (2026-09-29, fanfare: 3)

![Table 4 as bars: the share of the single-thread p\_{99} excess ( p\_{99}-T ) that survives each null stream, the real](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-14-30b580e3.png)

__[PPO Hybrid Regime-Aware Policy for Trading](https://arxiv.org/abs/2610.01325)__: Reinforcement learning agent combining policy optimization with regime priors controls drawdown while blending learned and rule-based portfolio exposure on held-out equity data. (2026-10-02, fanfare: 3)

![SPY cumulative returns across methods](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-15-ebb7d650.png)

__[KiT Diffusion Candlestick Model](https://arxiv.org/abs/2609.34507)__: Diffusion transformer foundation model reformulates candlestick prediction as conditional trajectory generation, achieving 0.057 mean return RankIC across markets and timescales. (2026-09-29, fanfare: 3)

![The structure of KiT . (a) Each bar of raw OHLCV is encoded as a five-dimensional log-ratio state](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-16-5324910e.png)

__[Test-Time Reasoning in LLM Trading](https://arxiv.org/abs/2609.30705)__: The study tests whether extra reasoning in large language models improves portfolio returns net of trading costs across multiple model families, finding no reliable gains. (2026-09-28, fanfare: 3)

![Primary low versus baseline return effects across 241 return dates](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-17-e3a282f4.png)

__[Active-Passive Liquidity Gap in Uniswap](https://arxiv.org/abs/2609.37963)__: Analysis of Uniswap pools shows passive liquidity providers underperform aggregate pool returns, with the gap wider on Ethereum than on layer-two blockchains. (2026-09-30, fanfare: 3)

![Passive-active liquidity gap across chains showing Arbitrum, Base, and Ethereum with positive trend.](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-18-b0709d1f.png)

__[Oracle-Parametrized Constant Function Markets](https://arxiv.org/abs/2609.33799)__: A framework shows when oracle-informed automated market makers reduce loss versus rebalancing and improve capital efficiency, with counterfactual backtests on SPY data. (2026-09-29, fanfare: 3)

![Section 4.2 : Pareto-efficient frontiers and optimal parameter configurations across oracle regimes](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-19-9dba9ed2.png)

__[LLMs Extract SEC 10-K Financial Data](https://arxiv.org/abs/2609.35864)__: Large language models outperform traditional methods at extracting missing financial data from SEC filings, with accuracy improving as model size matches document complexity. (2026-09-30, fanfare: 3)

![Bar chart comparing Joint F1 scores across three financial data categories with constraint analysis](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-20-00731bc8.png)

__[LLM Agents in Option Trading](https://arxiv.org/abs/2609.33470)__: An evaluation framework tests language model agents on structured option trading tasks, finding current systems underperform in most real-world scenarios. (2026-09-29, fanfare: 3)

![LiveOption framework diagram showing LLM-agent integration for option trading with environment, scenarios, and evaluation.](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-21-fab5dfba.png)

__[Self-Evolution in Long-Horizon Alpha Research](https://arxiv.org/abs/2609.33524)__: A framework tests whether self-evolving research capabilities improve alpha discovery over time, finding no consistent gains from accumulated experience and tools. (2026-09-29, fanfare: 2)

![EverMine research loop and evaluation framework](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-22-8076c982.png)

__[Multiperiod Bond Portfolio Optimization with Costs](https://arxiv.org/abs/2609.38765)__: The study develops a Markov decision process framework for dynamic bond portfolio management that balances yield and interest-rate risk subject to transaction costs. (2026-10-01, fanfare: 2)

![Simulation of Yields of 5 Year Bond over six months using the Markov Chain Approximation with a 40 bps discretization](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-23-59dd0227.png)

__[Option Replication with Price Impact and Costs](https://arxiv.org/abs/2609.36257)__: The study shows how hedging a derivative via trading the underlying changes its payoff when execution generates price impact and costs, deriving pricing equations and replication conditions. (2026-09-30, fanfare: 2)

![The left panel shows the amount paid (positive N ) or received (negative N ) when executing N shares of the underlying](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-24-2df8a0bd.png)

__[Agentic Limit Order Books and Market Impact](https://arxiv.org/abs/2609.31260)__: The study shows that reinforcement-learning traders in limit order books create phase transitions between orderly trading and volatile cascades, with non-linear market impact dynamics. (2026-09-28, fanfare: 2)

![Mid-price volatility \sigma and probability of order book collapse p across varying Liquidity Provider count n and](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-25-930604ff.png)

__[Option Portfolios with Risk Exposure Constraints](https://arxiv.org/abs/2609.33767)__: A deep learning framework for options trading enforces portfolio-level delta neutrality and other risk constraints during training, improving risk-adjusted returns with lower directional exposure. (2026-09-29, fanfare: 2)

![Delta distributions across option strategies showing near-zero centering with constrained framework](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-26-966c2f32.png)

__[Deep Kernel Hedging Framework](https://arxiv.org/abs/2609.34474)__: A hybrid approach combining neural networks with kernel methods produces robust derivative hedges in low-data regimes and scales via random Fourier features with convergence guarantees. (2026-09-29, fanfare: 2)

![Comparison of the exact RKHS hedging strategy ϕ⋆](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-27-2d33b699.png)

__[Language Models Forecast Stocks](https://arxiv.org/abs/2609.36914)__: Post-training Qwen3-4B via supervised fine-tuning and policy optimization more than doubles direction-magnitude score on chronological stock-price predictions to 43.31. (2026-09-30, fanfare: 2)

![Post-training brings a 4B model to performance comparable to frontier models on BETA. (a) Scores on the 240 scored test](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-28-20b72e8a.png)

__[DualCast Bimodal Forecasting](https://arxiv.org/abs/2609.38197)__: Dual-path language model extended with financial tokens and news-conditioned revision achieves lowest error in 8 of 12 equity and energy forecasting settings across multiple horizons. (2026-10-01, fanfare: 2)

![Overview of DualCast . The scale–shape tokenizer separates scale statistics from residual shape patterns and maps both](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-29-4cf4d9f9.png)

__[Statistical Scenario Analysis](https://arxiv.org/abs/2609.37273)__: Kernel scenario analysis estimates quantile predictions for portfolio stress-test gains, with online calibration to capture dependence between stressed and unstressed risk factors. (2026-09-30, fanfare: 2)

![Dynamics of ACSA and KSA’s prediction interval (PI) widths, for the adversarial portfolio and the factor-neutral](https://www.ml-quant.com/issues/2026-10-02/figures/arxiv-30-60d81ff1.png)

## SSRN

__[Bond Signals Predict Next-Month Equity Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7527218)__: Signals extracted from corporate bond portfolios predict next-month equity returns of same issuers at 21 basis points higher after controlling for stock characteristics. (2026-09-28, fanfare: 4)

__[Order Flow Imbalance Predicts Prediction Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7520438)__: Order flow imbalance predicts contemporaneous mid-price changes in Kalshi binary event contracts, with explanatory power varying from 0.29 for sports to 0.02 for macroeconomic events. (2026-09-26, fanfare: 3)

__[Banks versus Private Credit and Capital Requirements](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7524779)__: The study models how capital requirements tax banks on tailored loans, pushing riskier firms toward private credit; evidence shows that tighter leverage rules reduce bank tailoring by 25 percent in quantitative terms. (2026-09-28, fanfare: 4)

__[FOMC Surprises Persist, Rest Reverts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7533561)__: Analyzing 261 FOMC announcements shows that immediate stock and yield impacts from policy surprises persist, while post-announcement drift and monetary momentum unwind within days or weeks. (2026-09-29, fanfare: 3)

__[US Monetary Policy and Global Trading Costs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7535199)__: The study shows that US federal funds rate shocks widen bid-ask spreads on equities across 37 markets for up to two months, while longer-maturity yield surprises reprice equities without affecting liquidity. (2026-09-28, fanfare: 3)

__[Corporate Bond Returns Cluster in Month Start](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7524680)__: The research finds that the first five trading days of each month account for 73% of individual bond credit returns and 83% of the market credit premium, revealing a concentrated timing pattern in fixed-income compensation. (2026-09-26, fanfare: 3)

__[Global Debt Amplifies US Policy Spillovers](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7541599)__: US monetary tightening triggers larger currency depreciation and sovereign stress in emerging markets when global public debt is high and foreign-currency debt exposure is elevated. (2026-09-29, fanfare: 3)

__[Residual Learning Deepens Asset Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7528558)__: Deep residual networks outperform shallow models in asset pricing, achieving a long-short Sharpe ratio of 2.07 versus 1.92 for shallow versions by preserving and refining earlier layers. (2026-09-29, fanfare: 3)

__[Ant Group IPO Halt and Chinese Fintech Regulation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7545235)__: The study exploits Ant Group's suspended IPO in November 2020 as a natural experiment, finding that highly exposed firms suffered roughly 21 percentage point abnormal returns and experienced a 42% contraction in shadow-loan balances. (2026-09-30, fanfare: 3)

__[Policy Dispersion and Equity Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7531599)__: Using Kalshi FOMC contract probabilities, the paper shows that cross-outcome variance in Federal Reserve policy expectations contains significant information about long-run stock market volatility. (2026-09-30, fanfare: 3)

__[Dynamic Graph Neural Networks for Systemic Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7522878)__: The research proposes a temporal graph neural network with explainability tools for real-time systemic risk surveillance, achieving early warning signals 3-4 quarters ahead of financial distress on bank data. (2026-09-29, fanfare: 3)

__[Monetary Policy and Bond Return Decomposition](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7549733)__: The research decomposes bond returns into real rates, risk premia, and inflation expectations, finding that forward guidance and asset purchases had opposite effects at the zero lower bound versus normal times. (2026-10-01, fanfare: 3)

__[Rollover Clock and Sovereign Debt Limits](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7542158)__: Rollover clock measurement of consolidated Treasury and central bank liability repricing predicts U.S. Treasury interest rates and prices inflation costs of fiscal deficits. (2026-10-01, fanfare: 3)

__[Capacity Limits of Equity Anomalies](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7524338)__: Computing capacity for 35 anomalies reveals that high-alpha long legs support less than $2 billion before trading costs eliminate excess returns, while lower-alpha strategies support billions more. (2026-09-26, fanfare: 3)

__[Idiosyncratic Variance Drag on Individual Stocks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7546579)__: A lognormal model shows that individual stocks carry an idiosyncratic variance penalty making most underperform the index, with about one-third beating the market over five years. (2026-10-01, fanfare: 3)

__[Spot Bitcoin ETF Flows and Bitcoin Returns Timing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7545019)__: Correcting for timestamp mismatch between ETF and Bitcoin markets, the study finds that same-day flows predict next-day returns at 1.67 percentage points per billion of inflow, while prior Bitcoin returns predict flows. (2026-09-30, fanfare: 3)

__[Liquidity Capacity and Cryptocurrency Token Survival](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7536975)__: The research shows that adjusted illiquidity—price impact scaled by market absorption capacity—predicts which cryptocurrency tokens survive better than volatility, improving out-of-sample forecasting of token death. (2026-09-28, fanfare: 3)

__[Crypto Trading Activity Anchors to New York Time](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7526338)__: Bitcoin and Ether trading activity on major venues increases during the UTC window aligned with New York market open, with the effect appearing on both assets. (2026-09-28, fanfare: 3)

__[Portfolio Choice with Forecast Granularity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7547959)__: Investors using machine-learning forecasts can achieve Sharpe ratios of 1.2 by adjusting the number of portfolio groups based on the forecast's information coefficient, beating standard decile sorts. (2026-10-01, fanfare: 2)

__[Public-Data Equity Research Pipeline](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7528419)__: A reproducible pipeline for factor research finds no model reliably beats simple approaches after accounting for transaction costs in point-in-time factor tests. (2026-09-28, fanfare: 2)

__[Filing Timeliness Predicts Stock Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7536681)__: Filing discipline characteristics built from SEC timestamp data alone predict cross-sectional stock returns with a net Sharpe ratio of 1.27, concentrated in smaller and more volatile stocks. (2026-09-30, fanfare: 2)

__[Reproducible US Returns 1792-2026](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7527762)__: A new 234-year synthetic total-return dataset for equities and Treasuries reveals that permanent 3× leverage faces near-total loss in most reconstructions, ranking below 2× on risk-adjusted returns. (2026-09-28, fanfare: 2)

__[Tail Risk Hedging Costs and Trade-offs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7541959)__: Static out-of-the-money put options provide crash protection but drag long-term returns, while dynamic tail-risk strategies adapt to market regimes and deliver superior risk-adjusted returns across cycles. (2026-09-30, fanfare: 2)

__[Integrated Monitoring Framework for Systemic Stress](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7521018)__: The research develops a four-layer diagnostic framework combining network topology, dynamic causality, tail risk, and regime classification to monitor multi-asset systemic stress in real time. (2026-09-26, fanfare: 2)

__[Market Microstructure and AI Agents](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7530158)__: A survey traces how market design rules evolved from floor trading to limit order books to automated market makers to agent-based trading systems. (2026-09-28, fanfare: 2)

__[Geopolitical Risk and Global Market Integration](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7549731)__: Global connectedness across energy, commodity, carbon, and equity markets averages 52.4 percent and spikes to approximately 95 percent during major geopolitical disruptions. (2026-10-01, fanfare: 2)

__[CBDC Risks to Financial Stability](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7540719)__: Calibrated simulations show existing central bank digital currencies remain below thresholds needed to measurably affect bank credit or financial stability. (2026-09-30, fanfare: 2)

__[Market Attention and Information Quality Polymarket](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7540819)__: On-chain prediction market analysis finds 68.2 percent of volume sits in well-calibrated markets with average seven-day pricing error of 0.03. (2026-09-30, fanfare: 2)

__[Order Flow Imbalance in Indian NSE Futures](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7542098)__: Multilevel order flow imbalance in Indian equity derivatives predicts mean-reverting price dynamics with information coefficients growing from -0.004 at ten seconds to -0.032 at sixty seconds. (2026-10-01, fanfare: 2)

__[Bayesian VAR for U.S. Macroeconomic Forecasting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7532698)__: The research develops a compact Bayesian VAR for real-time forecasting of GDP growth, inflation, unemployment, and the federal funds rate, with evaluation emphasizing density scores and predictive-interval diagnostics. (2026-09-27, fanfare: 2)

## RePEc

__[AI and Corporate Bond Pricing](https://econpapers.repec.org/RePEc:bdi:opques:qef_1057_26)__: Using ChatGPT's launch as a natural experiment, the paper finds that hyperscalers saw borrowing costs decline while software firms faced worse terms as debt markets repriced AI winners and losers. (2026-09-28, fanfare: 4)

![Event study showing borrowing cost changes around ChatGPT launch by firm category.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-01-df3bd396.png)

__[Macroeconomic Effects of AI Technology Shocks](https://econpapers.repec.org/RePEc:bdi:wptemi:td_1542_26)__: AI-intensive patents generate delayed productivity and employment gains alongside falling consumer prices, with substantially larger aggregate effects than broader ICT shocks but reducing labor share and increasing wealth inequality. (2026-09-28, fanfare: 4)

![Impulse response functions comparing GDP, TFP, and employment effects across AI, automation, and ICT shocks.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-02-ae958d5d.png)

__[The Fed Put and Bank Risk-Taking](https://econpapers.repec.org/RePEc:ces:ceswps:_12980)__: The paper shows that monetary policy reduces perceived tail risk for bank equity, encouraging banks to originate riskier loans to commercial and industrial borrowers. (2026-09-28, fanfare: 3)

![Error probability increases with loan risk rating, showing monetary policy encourages riskier lending.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-03-eb03757f.png)

__[Transformer-Based CoVaR and Textual Risk](https://econpapers.repec.org/RePEc:bri:uobdis:26/840)__: Integrating financial news embeddings from large language models with market data, the study improves systemic risk forecasts using conditional value-at-risk without requiring large datasets. (2026-09-23, fanfare: 3)

__[AI Extracts Financial Stability Trigger Risks](https://econpapers.repec.org/RePEc:ecb:ecbwps:20263262)__: Large Language Models extract signals about potential trigger events from financial news, improving forward-looking estimates of downside risks and helping monitor financial stability threats ahead of major events. (2026-09-23, fanfare: 3)

![SPOT financial stability indicator compared with geopolitical risk and policy uncertainty measures.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-05-77292298.png)

__[Fed Communication Reduces Policy Uncertainty](https://econpapers.repec.org/RePEc:tse:wpaper:132139)__: The study shows that increased Federal Reserve communication lowers monetary policy uncertainty and generates substantial real effects: industrial production rises 0.3 percent and unemployment falls 0.2 percentage points within two months. (2026-09-28, fanfare: 3)

__[Bank FX Exposure and Real Lending Effects](https://econpapers.repec.org/RePEc:tcb:wpaper:2617)__: The study shows that banks with high foreign exchange risk reduce lending to both exposed and unexposed firms after exchange rate shocks, with measurable real effects on small and medium enterprises. (2026-09-28, fanfare: 3)

![FX exposure distribution with confidence intervals showing bank foreign exchange risk heterogeneity](https://www.ml-quant.com/issues/2026-10-02/figures/repec-07-f9940277.png)

__[Volatility Model Gains and Holdout Validation](https://econpapers.repec.org/RePEc:cte:wsrepe:50798)__: Testing eight volatility models on equity indices with prespecified holdout periods, the research finds that gains from more complex models often do not persist across markets or time. (2026-09-30, fanfare: 3)

![Mean FZ0 differences across volatility models with confidence intervals, multiple markets and specifications.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-08-3149ce7a.png)

__[AI's Impact on Monetary Policy Transmission](https://econpapers.repec.org/RePEc:bdi:opques:qef_1051_26)__: The paper assesses how artificial intelligence affects monetary policy transmission and central bank reactions, finding AI could improve risk assessment and communication but may also amplify systemic vulnerabilities and herding dynamics. (2026-09-28, fanfare: 3)

![AI and the demand for central bank reserves (a) Shift (b) Change in slope](https://www.ml-quant.com/issues/2026-10-02/figures/repec-09-3f71b35d.png)

__[AI and Indian Sovereign Yield Curve Shifts](https://econpapers.repec.org/RePEc:npf:wpaper:26/450)__: Post-AI adoption, longer-maturity Indian bond yields show reduced sensitivity to expected inflation and money supply growth, while short-term yields exhibit heightened inflation sensitivity, suggesting structural transmission changes. (2026-09-28, fanfare: 3)

![Short-term nominal and real interest rates diverging with nominal rates rising post-2020 while real rates remain volatile.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-10-9722861a.png)

__[Trump Re-election and Green Bond Issuance](https://econpapers.repec.org/RePEc:bdi:wptemi:td_1538_26)__: U.S. green bond share declined from 1.7 to 0.6 percent after Trump's re-election and Paris Agreement withdrawal, with the greenium turning positive. (2026-09-28, fanfare: 3)

![Volume of placements](https://www.ml-quant.com/issues/2026-10-02/figures/repec-11-fe2205f0.png)

__[AI Automation vs. Augmentation Labor Effects](https://econpapers.repec.org/RePEc:zbw:glodps:1821)__: AI automation reduces occupational employment by 21 percent with little wage effect, while AI augmentation raises wages by 8 percent, revealing that AI's labor impact depends on the balance between these opposing channels. (2026-09-28, fanfare: 3)

__[Dealer Pricing of Synthetic Dollar Funding](https://econpapers.repec.org/RePEc:boe:boeewp:023631)__: Comparing FX forwards in identical currency pairs and maturities, the study finds large pricing variation across dealers reflecting clientele and pricing power rather than funding costs. (2026-09-28, fanfare: 2)

![Time series of dealer buy and sell FX forward pricing wedges, weighted by notional volume.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-13-8bde8572.png)

__[Path-Dependent Implied Volatility Surface](https://econpapers.repec.org/RePEc:hal:journl:hal-04362544)__: The research shows that past asset price trajectories predict implied volatility movements up to two years forward, with a parsimonious SSVI model capturing this path-dependent behavior. (2026-09-28, fanfare: 2)

__[Portfolio-Balance Term Structure Estimation](https://econpapers.repec.org/RePEc:bca:bocawp:26-33)__: Proposes a two-step estimator to recover portfolio-balance model parameters from Gaussian term structure models, identifying shocks to hedging risk premiums and risk-bearing capacity. (2026-09-28, fanfare: 2)

__[Repo Markets and Federal Reserve Balance Sheet](https://econpapers.repec.org/RePEc:fip:fedgfn:103714)__: The paper examines how Federal Reserve balance sheet changes affect overnight Treasury repo markets and the transmission of monetary policy through money markets. (2026-09-21, fanfare: 2)

__[Dynamic Correlations in Stochastic Volatility](https://econpapers.repec.org/RePEc:cte:wsrepe:50561)__: Decomposing forecasting losses into correlation versus scale components, the paper shows how to diagnose and stabilize dynamic-correlation volatility models using realized-volatility inputs. (2026-09-23, fanfare: 2)

![Cumulative stabilization gains](https://www.ml-quant.com/issues/2026-10-02/figures/repec-17-431d984f.png)

__[LLM Financial Advice Ignores Local Context](https://econpapers.repec.org/RePEc:zbw:safewp:343061)__: Large language models provide nearly identical portfolio advice across twenty-one countries despite local differences, following retail finance conventions rather than academic prescriptions and ignoring household balance sheets. (2026-09-21, fanfare: 2)

![Distribution of recommended equity shares in the primary cell](https://www.ml-quant.com/issues/2026-10-02/figures/repec-18-f373a658.png)

__[Machine-Learned Drivers in Correlation Models](https://econpapers.repec.org/RePEc:cdf:wpaper:2026/12)__: Combining machine-learned forecasts of realized measures with dynamic conditional correlation models improves correlation matrix forecasts, producing valid predictions and beating realized-driver baselines across multiple horizons. (2026-09-30, fanfare: 2)

__[Intangible Capital and Firm Borrowing Constraints](https://econpapers.repec.org/RePEc:boe:boeewp:023254)__: UK firm-level analysis shows that interest rate spreads are less sensitive to capital-to-debt ratios for firms with higher intangible intensity, suggesting intangibles are less effective collateral than tangible assets. (2026-09-21, fanfare: 2)

![Intangible and tangible investment over time](https://www.ml-quant.com/issues/2026-10-02/figures/repec-20-93d28e76.png)

__[Solvency and Systemic Risk in Life Insurers](https://econpapers.repec.org/RePEc:boe:boeewp:023290)__: The research distinguishes solvency risk from systemic risk in European life insurers, finding growing systemic risk exposure since 2007 and evidence of interconnectedness with banks that intensifies during financial stress. (2026-10-02, fanfare: 2)

![Asset allocation of 6 European Life Insurers: 2016 to 2024 Portfolio composition by asset class (percentage) Portfolio](https://www.ml-quant.com/issues/2026-10-02/figures/repec-21-073c46cd.png)

__[Financial Crisis Cycles and Debt Overhang](https://econpapers.repec.org/RePEc:cnn:wpaper:26-015e)__: A theoretical model shows that debt accumulation during booms delays post-crash recovery through debt overhang and coordination failures, with debt restructuring conditional on recapitalization being more efficient than unconditional subsidies. (2026-10-02, fanfare: 2)

__[Monetary Policy Transmission Non-Linearities](https://econpapers.repec.org/RePEc:cbi:wpaper:09/rt/26)__: Analysis of a large macro-financial dataset ranks non-linear monetary transmission channels, finding transmission to long-term rates weakens at high interest rates and high credit growth, with sovereign risk mattering in the euro area. (2026-09-21, fanfare: 2)

![Individual Non-Linear Models for the US—10 Year Treasury Futures Rate— Robustness](https://www.ml-quant.com/issues/2026-10-02/figures/repec-23-1ce930b7.png)

__[Price Conflict Predicts Stock Volatility](https://econpapers.repec.org/RePEc:pre:wpaper:202620)__: The GARCH-MIDAS model incorporating a quarterly news-based Price Conflict Index outperforms benchmarks for forecasting US stock volatility over 150 years of monthly and daily data. (2026-09-23, fanfare: 2)

![S&P 500 and Dow Jones log-returns over 150 years showing volatility clusters](https://www.ml-quant.com/issues/2026-10-02/figures/repec-24-fd9e40cf.png)

__[Covenant-Lite Loans and Regulatory Pressures](https://econpapers.repec.org/RePEc:nbr:nberwo:35617)__: Post-GFC, banks facing stricter regulation increased cov-lite loan issuances due to liquidity advantages that lower credit spreads, particularly for private firms seeking easier asset sales. (2026-09-20, fanfare: 2)

![Loan market issuance trends over time Panel A of this figure shows the percentage of loans (by number and loan amount)](https://www.ml-quant.com/issues/2026-10-02/figures/repec-25-2ac4c26b.png)

__[UK Mortgage Refinancing After Rate Shock](https://econpapers.repec.org/RePEc:boe:boeewp:023579)__: The study finds that UK borrowers shifted toward two-year fixed mortgages despite higher pricing after the 2022 rate shock, seeking flexibility and rate protection rather than minimizing immediate costs. (2026-09-21, fanfare: 2)

![Loan Terminations by Initial Fixed-Rate Term, All Cohorts](https://www.ml-quant.com/issues/2026-10-02/figures/repec-26-e1144e04.png)

__[Fed Unconventional Policy and Exchange Rates](https://econpapers.repec.org/RePEc:dpr:wpaper:1276r)__: The research shows that both large-scale asset purchases and forward guidance appreciate foreign currencies against the dollar, with guidance having larger effects, especially during zero lower bound periods. (2026-09-21, fanfare: 2)

![Foreign exchange impulse responses to forward guidance shocks during zero lower bound periods](https://www.ml-quant.com/issues/2026-10-02/figures/repec-27-303b0906.png)

__[Geopolitical Risk and Emerging Sovereign Spreads](https://econpapers.repec.org/RePEc:bis:biswps:1368)__: The study finds that geopolitical risk raises sovereign credit spreads in emerging markets, with threats having larger effects than acts, and responses shifting substantially after the Ukraine invasion. (2026-09-23, fanfare: 2)

![Sovereign spread responses to geopolitical risk threats versus acts over time.](https://www.ml-quant.com/issues/2026-10-02/figures/repec-28-8a646804.png)

__[Innovation Risk and Firm Investment Gaps](https://econpapers.repec.org/RePEc:bde:wpaper:2628e)__: The research shows that firms' hurdle rates exceed their financial cost of capital due to innovation risk and imperfect pledgeability, explaining weak productivity growth and declining business dynamism. (2026-10-02, fanfare: 2)

__[Central Bank Paths and Forecast Accuracy](https://econpapers.repec.org/RePEc:ces:ceswps:_12972)__: A pre-trained time-series model reading central bank published paths cuts forecast errors better than the banks themselves and hard-conditioned VARs, revealing exploitable institutional differences. (2026-09-21, fanfare: 2)

![Credibility gap for inflation under the Multi input](https://www.ml-quant.com/issues/2026-10-02/figures/repec-30-9253277c.png)