---
title: Quant Letter No. 132: September 2026, Week 4
url: https://www.ml-quant.com/issues/2026-09-25/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2026-09-25
---

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

*This week balances methodological rigor with practical market insights. Tail risk estimation and time-series validation trade-offs address foundational modeling challenges, while label engineering and LLM look-ahead bias expose common pitfalls in factor and AI development. Key reads: Semi-Discrete Optimal Transport, Time-Series Validation Trade-Offs Revisited, and Label Engineering for Stock Selection.*

## Top picks

### 1. [Tail Risk via Semi-Discrete Optimal Transport](https://arxiv.org/abs/2609.27785) · arXiv

### 2. [Artificial Intelligence and Financial Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7515878) · SSRN

### 3. [Agentic AI Systems Beat Asset Pricing Benchmarks](https://econpapers.repec.org/RePEc:nbr:nberwo:35431) · RePEc

### 4. [Frozen Referee for Agent Factor Mining](https://arxiv.org/abs/2609.27051) · arXiv

### 5. [Label Engineering for Stock Selection](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7494298) · SSRN

## What's rising

### Option pricing: 14 papers this week, 3.0× the usual 4.6

### Anomalies: 24 papers this week, 2.2× the usual 11

### Jump processes: 14 papers this week, 2.3× the usual 6.1

### Monte Carlo: 25 papers this week, 1.7× the usual 14.5

### Implied volatility: 24 papers this week, 1.7× the usual 14.1

## GitHub radar

### Quant repos rising

#### [Open-Dev-Society/OpenStock](https://github.com/Open-Dev-Society/OpenStock): Open-source platform for tracking real-time stock prices and company insights. (8 quants, 19.2k stars, +3,593 this week)

#### [jarrodwatts/jev-trader](https://github.com/jarrodwatts/jev-trader): AI trading bot making one Jev trade decision per Monad block. (4 quants, 2,395 stars, +1,462 this week, new repo)

#### [brycewang-stanford/Auto-Empirical-Research-Skills](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills): Collection of 23,000+ agent skills for empirical research in social sciences. (4 quants, 4,374 stars, +500 this week)

#### [anthropics/financial-services](https://github.com/anthropics/financial-services): Anthropic's financial services implementation. (4 quants, 37.5k stars, +2,589 this week)

#### [Yijia-Xiao/FinanceHarness](https://github.com/Yijia-Xiao/FinanceHarness): Autonomous financial deep research framework with agentic capabilities. (2 quants, 176 stars, +33 this week, new repo)

#### [caiovicentino/eikos](https://github.com/caiovicentino/eikos): Calibrated typed-decision models for finance and trading applications. (2 quants, 18 stars, +18 this week, new repo)

#### [securo-finance/securo](https://github.com/securo-finance/securo): Open-source self-hosted privacy-first personal finance manager. (2 quants, 3,783 stars, +181 this week)

#### [ccxt/ccxt](https://github.com/ccxt/ccxt): Unified API for 100+ crypto exchanges and prediction markets. (2 quants, 44.1k stars, +123 this week)

### What quants are playing with

#### [NandhaKishorM/laya](https://github.com/NandhaKishorM/laya): Non-autoregressive decision engine for typed choices over text in 100+ languages. (28 quants, 24.0k stars, +23.7k this week, new repo)

#### [browser-use/jev-ultrafast](https://github.com/browser-use/jev-ultrafast): Fastest and cheapest web agent for automation tasks. (19 quants, 20.1k stars, +14.0k this week, new repo)

#### [google/ax](https://github.com/google/ax): Google's open agentic orchestration runtime for agent systems. (19 quants, 11.1k stars, +9,108 this week)

#### [jaredpalmer/kev](https://github.com/jaredpalmer/kev): Decision models built on Qwen3.5/3.8 you can train locally. (13 quants, 6,886 stars, +6,653 this week, new repo)

#### [Contrastive-LM/CLM](https://github.com/Contrastive-LM/CLM): Contrastive language model implementation. (8 quants, 1,065 stars, +1,065 this week, new repo)

#### [nokia-applied-research/AnyJev](https://github.com/nokia-applied-research/AnyJev): Turn any LLM into a Jev-style decision model with typed decisions. (7 quants, 590 stars, +590 this week, new repo)

## Our track record

### Of the 1,631 finance papers we featured as new at least a year ago, 34% are now published, and 8 of our early picks have 100+ citations.

### [FinGPT: Open-Source Financial Large Language Models](https://arxiv.org/abs/2306.06031) was featured 5 days after release; it has 492 citations.

## arXiv

__[Tail Risk via Semi-Discrete Optimal Transport](https://arxiv.org/abs/2609.27785)__: Proposes semi-discrete optimal transport to capture heavy tails in financial returns, maintaining stable tail ratio estimates across diverse neural generators when standard Lipschitz methods fail. (2026-09-24, fanfare: 4)

![Variational method for optimal transport](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-01-001a7c5a.png)

__[Frozen Referee for Agent Factor Mining](https://arxiv.org/abs/2609.27051)__: Proposes a statistical referee that judges investment factors proposed by language-model agents using out-of-sample market outcomes, ensuring false-discovery control at any stopping time. (2026-09-24, fanfare: 4)

![Persistence and monetisation by family](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-02-0501a54b.png)

__[Time-Series Validation Trade-Offs Revisited](https://arxiv.org/abs/2609.29530)__: Proves that training sufficiency, test coverage, and temporal causality cannot be maximized simultaneously in time-series validation, pricing each constraint explicitly. (2026-09-25, fanfare: 4)

![The feasible region of strictly causal schemes, \alpha+\beta\leq 1 (Theorem 1 (c)), and the coordinates of the standard](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-03-d6b3b9ad.png)

__[Adversarial RL for Hawkes Market Making](https://arxiv.org/abs/2609.22785)__: The research extends adversarial reinforcement learning for market making to handle self-exciting order arrivals and price impact, using an LSTM module to improve robustness in complex microstructure environments. (2026-09-22, fanfare: 3)

![Kernel density estimates of terminal wealth in G19](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-04-51074eeb.png)

__[MFAST Framework for News-Based Trading](https://arxiv.org/abs/2609.23703)__: Introduces a market-friction-aware framework that converts timestamped financial news into auditable trading decisions while accounting for execution timing, transaction costs, and liquidity constraints. (2026-09-22, fanfare: 3)

![MFAST system architecture for market-friction-aware news-based trading](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-05-fe752553.png)

__[Universal Diffusion Models for Volatility Surfaces](https://arxiv.org/abs/2609.22893)__: A universal diffusion model trained on pooled data from 50 stocks learns to jointly generate implied volatility surface changes and stock returns, extrapolating well to unseen stocks. (2026-09-22, fanfare: 3)

![Conditional FiLM denoiser architecture](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-06-686203ce.png)

__[AlphaDiverse: Multi-Agent Alpha Factor Mining](https://arxiv.org/abs/2609.29014)__: Proposes a multi-agent system with post-training that automates alpha factor mining locally, using diverse research paths and joint optimization to broaden exploration while maintaining prediction quality. (2026-09-25, fanfare: 3)

![AlphaDiverse overview](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-07-00e00707.png)

__[Forecast-Dojo: LLM Forecasting Benchmark](https://arxiv.org/abs/2609.28876)__: Introduces a replayable environment combining 1,568 resolved prediction-market questions with 18.8M dated news articles to benchmark and train language-model forecasting agents on historical data. (2026-09-25, fanfare: 3)

![Overview of Forecast-Dojo](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-08-1e9c90b3.png)

__[Active Portfolio Allocation with SPT](https://arxiv.org/abs/2609.27113)__: Formulates a stochastic control problem for actively allocating between equal-weighted and market portfolios based on a diversity-dispersion model, outperforming passive strategies during market bubbles. (2026-09-24, fanfare: 3)

![Top row: A simulated path of market diversity and dispersion under the calibrated mean-reverting SDD model (left), and](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-09-7374f4a8.png)

__[Decision-Focused Learning for Portfolio Optimization](https://arxiv.org/abs/2609.21427)__: Proposes a KKT-based decision-focused learning method that trains mean-variance portfolio models by directly minimizing downstream portfolio loss while preserving all constraints. (2026-09-21, fanfare: 3)

__[DefaultGNN for Corporate Default Prediction](https://arxiv.org/abs/2609.25542)__: A dual-perspective graph neural network framework predicts corporate defaults from buyer-seller transaction networks, improving approval rates by 7-11 percentage points without increasing default risk. (2026-09-23, fanfare: 3)

![Overall framework of DefaultGNN . View-specific embeddings learned from multiplex transaction networks are fused via](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-11-5ffc58b8.png)

__[Sentiment Arcs in Central Bank Communication](https://arxiv.org/abs/2609.25034)__: The study shows that how monetary policy sentiment unfolds across a press conference, not just its average tone, predicts rate changes and shapes forecaster expectations at the ECB and Fed. (2026-09-23, fanfare: 3)

![Seed phrase validation: PCA of seed embeddings](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-12-acbff833.png)

__[Trust, Rule of Law, and the Size Premium](https://arxiv.org/abs/2609.26212)__: Meta-analysis of 1,613 size-premium estimates across 31 countries finds that stronger rule of law is associated with larger size premia, contrary to intuition. (2026-09-23, fanfare: 3)

![Bayesian Model-Averaged Coefficient Summary](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-13-322c707a.png)

__[Multi-Task Learning for Stock Forecasting](https://arxiv.org/abs/2609.25617)__: A hierarchical multi-task framework jointly predicts price movement, volatility and volume using liquidity-aware signals, outperforming neural and tree-based baselines on Chinese equity indices. (2026-09-23, fanfare: 3)

![Cumulative long-short returns of APO and three portfolio-construction baselines](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-14-4d7feed8.png)

__[Temporal Hierarchy Forecasting for Electricity](https://arxiv.org/abs/2609.23223)__: Jointly reconciling hourly price and spread forecasts improves intraday electricity price prediction accuracy by up to 19.7% and battery-arbitrage profits by up to 10.4%. (2026-09-22, fanfare: 3)

![Top two panels: German (DE) and Spanish (ES) day-ahead electricity prices from 5 January 2018 to 31 December 2025](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-15-82628f04.png)

__[Macroeconomic Tail Risk Drivers](https://arxiv.org/abs/2609.26994)__: A regime-switching volatility-in-mean VAR reveals that the drivers of growth and inflation tails differ from median dynamics, with macroeconomic uncertainty playing a larger role in downside risk. (2026-09-24, fanfare: 3)

![Time series of GNP growth, inflation, and credit spread showing tail risk distributions with regime shading.](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-16-bc38253e.png)

__[ETH-TraceBench: Ethereum DeFi Benchmark](https://arxiv.org/abs/2609.23659)__: Introduces a large-scale benchmark on 1.35 billion Ethereum transactions to evaluate DeFi representations under temporal, protocol, and contract drift, revealing model degradation on unseen pools. (2026-09-22, fanfare: 3)

![ETH-TraceBench benchmark construction and evaluation pipeline](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-17-ae28e506.png)

__[FinInteract Benchmark for Ambiguous Financial QA](https://arxiv.org/abs/2609.24002)__: A benchmark reveals that language models answer financial questions above 90 percent with clarification but only 28.9 percent when they must elicit it themselves, exposing model ambiguity resolution. (2026-09-22, fanfare: 3)

![Per-category model performance on clarification capability across entity, metric, temporal, and recognition policy ambiguities.](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-18-653e8945.png)

__[Stochastic Nested Fixed Point BLP Estimation](https://arxiv.org/abs/2609.23998)__: A stochastic nested fixed-point estimator reduces memory and computational cost for random-coefficients logit demand models, enabling estimation on 100 million markets in hours. (2026-09-22, fanfare: 3)

![Small-Sample Distribution of the BLP Estimator](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-19-bb02e026.png)

__[Rough HAR Model for Realized Variance](https://arxiv.org/abs/2609.21587)__: Augmenting HAR with a negative moving-average component approximates rough dynamics, outperforming classical models out-of-sample and matching continuous-time rough model accuracy. (2026-09-21, fanfare: 3)

![Autocorrelation functions comparing fBm, IOU, Rough AR, and Rough HAR models](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-20-0922e21e.png)

__[Optimal Liquidity Provision and Rebate Design](https://arxiv.org/abs/2609.26606)__: Develops a nested optimization model for market making and rebate design in option markets, showing how exchanges can set fees to incentivize liquidity provision and improve market depth. (2026-09-23, fanfare: 2)

![Limit order execution intensities for ask and bid sides across spread ticks](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-21-bda870db.png)

__[Surface-Driven Stochastic Volatility for Commodities](https://arxiv.org/abs/2609.27138)__: Develops a surface-driven stochastic volatility framework for commodity options using daily volatility surface factors, recovering vol-of-vol and leverage parameters from smile dynamics. (2026-09-24, fanfare: 2)

![Time series of daily CME CVOL soybean surface indicators: ATM volatility, skew, skew ratio, and convexity from 2013–2025.](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-22-8ffaed0a.png)

__[Network Realized GARCH-Itô Models](https://arxiv.org/abs/2609.29515)__: Introduces a network realized GARCH-Itô model that identifies dynamic volatility transmission among assets using high-frequency data, outperforming recursive forecasts on sector ETFs. (2026-09-25, fanfare: 2)

![Connectedness across market regimes](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-23-782d0f3b.png)

__[FinRankGRPO: LLM Portfolio Ranking](https://arxiv.org/abs/2609.24175)__: Develops a two-stage framework that fine-tunes language models for listwise asset ranking using Spearman rank correlation rewards, achieving a Sharpe ratio of 0.636 on asset allocation. (2026-09-22, fanfare: 2)

![The two-stage construction framework of our FinRankGRPO, Stage 1 is SFT in high quality distill CoT datasets, Stage 2](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-24-ba73f686.png)

__[Optimal Execution Under Cash Constraints](https://arxiv.org/abs/2609.27786)__: Extends the Almgren-Chriss optimal execution framework to enforce intertemporal cash constraints, reducing peak cash drawdown while maintaining implementation shortfall in multi-asset rebalancing. (2026-09-24, fanfare: 2)

![Joint distributions of peak cash drawdown and combined IS for Ours and AC free](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-25-f1c496e3.png)

__[Machine Learning Detects Black-Scholes Deviations](https://arxiv.org/abs/2609.27764)__: Tree-based machine learning outperforms neural networks at detecting systematic option-pricing deviations from Black-Scholes using 2.6 million real contracts, with domain-expert features crucial. (2026-09-24, fanfare: 2)

![Model comparison across three representational regimes](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-26-812392bb.png)

__[Rule-Based Pricing Algorithms in Digital Markets](https://arxiv.org/abs/2609.26861)__: Experiments show that algorithm design features like warnings, pre-configured strategies, and LLM advice raise market prices by increasing starting prices and fostering cooperative algorithm designs. (2026-09-24, fanfare: 2)

![Average Market Price by LLM Model Configuration](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-27-92f54243.png)

__[Critical Line Algorithm and Constrained LASSO](https://arxiv.org/abs/2609.25704)__: Shows that mean-variance portfolio selection and the constrained LASSO trace identical piecewise-linear solution paths, mapping their parametrizations exactly. (2026-09-23, fanfare: 2)

![Proposition 4 checked along the path](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-28-f60037a5.png)

__[Optimal Investment under Integrated Variance Clocks](https://arxiv.org/abs/2609.26349)__: Characterizes optimal consumption and investment strategies in markets with stochastic volatility clocks using infinite-horizon backward SDEs, extending to rough and hyper-rough regimes. (2026-09-23, fanfare: 2)

![Optimal Investment under Integrated Variance Clocks](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-29-368f83d5.png)

__[Deep Learning Reflected BSDE under Paired Ambiguity](https://arxiv.org/abs/2609.23768)__: Develops a deep learning scheme for optimal stopping under simultaneous model and discount-rate ambiguity, with application to American option valuation under uncertainty. (2026-09-22, fanfare: 2)

![Training diagnostics showing value estimates and control processes converging across multiple scenarios with bounded discount rate ambiguity.](https://www.ml-quant.com/issues/2026-09-25/figures/arxiv-30-ad24fd37.png)

## SSRN

__[Artificial Intelligence and Financial Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7515878)__: A survey examines how AI transforms information production, intermediation, and market structure, with implications for efficiency, competition and financial stability. (2026-09-24, fanfare: 4)

__[Label Engineering for Stock Selection](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7494298)__: Reshaping the prediction target through location, scale and shape transformations raises long-short Sharpe from 0.68 to 1.69, with label choice mattering more than model choice. (2026-09-22, fanfare: 4)

__[Reinforcement Learning Agents Enable Collusion](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7500483)__: Q-learning pricing agents in simulated duopolies reach supracompetitive outcomes with no communication, achieving collusion indices of 0.778 and 40% profit gains over competitive benchmarks. (2026-09-24, fanfare: 4)

__[Defence Sector Repricing Before Ukraine](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7477998)__: European defence stocks repriced sharply starting November 2021, two to three months before Russia's invasion, delivering 26% alpha and reflecting release of ESG-exclusion constraints. (2026-09-19, fanfare: 4)

__[Forward Guidance and Bank Credit Supply](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7514178)__: High-frequency analysis reveals contractionary forward guidance immediately cuts bank lending, while expansionary guidance produces weak stimulus, driven by binding capital constraints. (2026-09-23, fanfare: 3)

__[LLM Stock Rankings and Look-Ahead Bias](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7490302)__: Testing whether a large language model ranks stocks by forecasting or memory, the study finds a significant information-coefficient gap of 0.185 inside versus outside its training window, suggesting substantial look-ahead contamination. (2026-09-22, fanfare: 3)

__[Training-Data Leakage in LLM Stock Signals](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7485818)__: The study measures recall versus forecasting in an LLM's stock rankings by comparing cross-sectional information coefficients inside and outside the training window. (2026-09-21, fanfare: 3)

__[Zero Fees Drive Fake Volume in Crypto Futures](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7512338)__: Analysis of Kalshi's regulated Bitcoin and Ethereum futures reveals that 39-48% of notional trades are mechanical fixed-size orders that vanish when fees are charged, indicating costless artificial volume rather than legitimate trading. (2026-09-23, fanfare: 3)

__[FOMC Semantic Novelty and Financial Stress](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7519200)__: Semantic surprises extracted from Federal Reserve statements predict subsequent financial-stress dynamics and reduce forecast error by up to 23%, particularly when initial stress is high or during recessions. (2026-09-24, fanfare: 3)

__[LASSO Benchmarks Reveal Mutual Fund Alpha](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7508299)__: Using factor selection, the study finds mean active alpha of plus 9 basis points monthly for mutual funds, reversing the no-alpha conclusion when benchmarks are tailored to each fund. (2026-09-23, fanfare: 3)

__[Margin Debt Growth and Factor Momentum](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7512099)__: Factor momentum strategies earn 49 basis points per month extra return following quarters of rapid margin-debt growth, a predictability that persists after publication and reflects limits to arbitrage correction. (2026-09-23, fanfare: 3)

__[LLM Factor Search with Transaction Cost Penalties](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498983)__: The paper builds a closed-loop system where an LLM proposes equity factors penalized for execution costs and shows that accounting for trading costs dramatically improves net performance. (2026-09-21, fanfare: 3)

__[Training Option Models on Prices not Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498639)__: The paper compares machine learning option pricing trained on pricing errors versus implied-volatility errors using 8.67 million S&P 500 index-option observations from 1997 through 2025. (2026-09-22, fanfare: 3)

__[Securitization Amplifies Rate Transmission](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7515879)__: Banks engaged in securitization contract lending more sharply after monetary tightening because their investor base demands higher returns and cuts risk exposure when rates rise. (2026-09-24, fanfare: 3)

__[Hedge Fund Leverage Amplifies Bond Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7506360)__: Leveraged hedge fund positions amplify sovereign bond yield sensitivity to monetary shocks by over a quarter through directional rebalancing, with effects scaling to position intensity. (2026-09-23, fanfare: 3)

__[Price Delay and Momentum Profits](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7518623)__: Momentum profits concentrate among firms with high price delay, a measure of information friction, directly supporting theories that gradual information incorporation drives momentum. (2026-09-24, fanfare: 3)

__[Industry Networks Predict Market Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7486138)__: Using production, employment, and sales data across 426 industries, the research shows that upstream industry signals predict aggregate monthly stock returns with 23.8% out-of-sample R-squared. (2026-09-19, fanfare: 3)

__[Expectations Drive Term Structure Sensitivity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7497046)__: Decomposing yield sensitivity without assuming rational expectations reveals that expectations rather than risk premia drive short- and medium-term bond yields, with systematic inconsistencies across horizons. (2026-09-21, fanfare: 3)

__[Hedge Fund Returns and Interest Rate Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7493702)__: Using SEC filings from 2013-2021, the paper finds hedge fund returns show heterogeneous sensitivity to interest rates, with effects varying by strategy, leverage, and derivative exposure. (2026-09-20, fanfare: 3)

__[Settlement Risk Prices Currency Excess Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7201787)__: Hungary's 2015 adoption of payment-versus-payment settlement reduced currency excess returns by ten basis points, demonstrating settlement risk is a priced friction limiting arbitrage. (2026-09-24, fanfare: 3)

__[Tail Risk Forecasting with Cubic Distributions](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7504480)__: A cubic quantile framework forecasts Value-at-Risk and Expected Shortfall more reliably than GARCH benchmarks across eight equity indices without requiring a parametric density. (2026-09-24, fanfare: 3)

__[Physics-Constrained Neural Operators for Option Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498326)__: A deep operator network maps volatility surfaces to option prices under the Heston model 15,000 times faster than finite-difference methods while reducing dynamic hedging variance by over 59% under transaction costs. (2026-09-21, fanfare: 2)

__[Systemic Risk in Global Banking Networks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7493706)__: Combining quantile-connectedness, tail-risk measures, and network analysis, the research shows tail connectedness exceeds median levels and lower-tail effects persist longer, with the VIX alone reliably predicting next-week systemic risk. (2026-09-20, fanfare: 2)

__[Negative Rates Cut Bank Lending via Asset Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7489554)__: Japan's 2016 negative-rate policy reduced lending from low-profitability banks holding reserves, consistent with lower expected returns on bank assets rather than deposit-side stress. (2026-09-19, fanfare: 2)

__[Banking Structure and Euro-Area Monetary Transmission](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7519040)__: A 100-basis-point contractionary monetary shock lowers inflation and sales across 20 euro-area economies, with transmission strength varying by bank asset-risk exposure and assets-to-GDP ratio rather than a simple weak-strong taxonomy. (2026-09-24, fanfare: 2)

__[Fed Communication Divergence and High-Frequency Trading](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7479619)__: Semantic and tonal shifts across sequential Federal Reserve communications generate significant intraday price movements and abnormal volume, revealing incomplete information absorption at initial announcement. (2026-09-19, fanfare: 2)

__[Negative Rates and Firm Valuations](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7512572)__: Comparing firms across the ECB's 2014 negative rate adoption shows treated European firms had higher valuations but reduced leverage, suggesting cash-flow and discount-rate channels dominate tax-shield effects. (2026-09-23, fanfare: 2)

__[Signature-Based Structural Credit Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498599)__: The study develops a time-varying signature asset model for structural credit that improves calibration across CDS maturities and equity option prices, especially for high-yield firms. (2026-09-22, fanfare: 2)

__[Minimax Portfolio Optimization Under Tail Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7486600)__: The research proposes a data-driven portfolio method that blends tail-risk models and projects onto valid mixtures, providing bounds on Expected Shortfall regret without Wasserstein assumptions. (2026-09-21, fanfare: 2)

__[Distressed Debt Exchanges and Creditor Trilemma](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7502204)__: Analysis of 284 distressed exchanges from 2009-2022 reveals over 50% of firms face subsequent default, with large illiquid creditors trapped in a prisoner's dilemma explaining high acceptance rates. (2026-09-22, fanfare: 3)

## RePEc

__[Agentic AI Systems Beat Asset Pricing Benchmarks](https://econpapers.repec.org/RePEc:nbr:nberwo:35431)__: Optimized AI systems analyzing earnings call transcripts double explained variation in stock returns versus standard benchmarks while improving interpretability through human-readable decision rules. (2026-09-17, fanfare: 4)

![Progress on Explaining Asset Prices Around Earnings Announcements](https://www.ml-quant.com/issues/2026-09-25/figures/repec-01-1af3061c.png)

__[Stablecoins and the Mundell-Fleming Trilemma](https://econpapers.repec.org/RePEc:fip:fednsr:103702)__: Wallet-level stablecoin data shows crisis countries experience inflows during banking restrictions; this endogenizes capital mobility and tightens monetary policy constraints. (2026-09-14, fanfare: 4)

![Hump-shaped curve showing equilibrium enforcement rises then falls with stablecoin adoption.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-02-f9565d96.png)

__[Skewness Risk in Currency Markets](https://econpapers.repec.org/RePEc:cpr:ceprdp:20587)__: Using model-free skewness measures from currency options, the study shows that skewness risk is priced in currency returns and explains variation across a broad cross-section of currency portfolios. (2026-09-17, fanfare: 3)

__[Global Credit Cycle Factor Pricing](https://econpapers.repec.org/RePEc:cpr:ceprdp:21268)__: A nonlinear factor constructed from credit spreads and equity volatility prices global corporate bond returns, explaining up to 13% of three-month-ahead return variation across markets. (2026-09-16, fanfare: 3)

__[Asset Embeddings from Portfolio Holdings](https://econpapers.repec.org/RePEc:cpr:ceprdp:20082)__: The paper shows that portfolio holdings contain all information needed for asset pricing and develops asset embeddings analogous to word embeddings to represent firms and predict valuations. (2026-09-18, fanfare: 3)

__[Intermediary Constraints and Global Risk Pricing](https://econpapers.repec.org/RePEc:fip:fedgif:103716)__: A two-country model shows that uncertainty shocks tighten intermediary constraints, widening credit spreads, appreciating the dollar, and raising currency risk premia globally. (2026-09-14, fanfare: 3)

![Model responses to uncertainty shock: credit spreads, exchange rates, and risk premiums over time.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-06-ee191d19.png)

__[Carry Trade Returns and Crash Risk](https://econpapers.repec.org/RePEc:cpr:ceprdp:20745)__: Focusing on dollar-lira trading, the paper shows that higher crash risk significantly increases carry trade expected returns, accounting for 46–77% of compensation through Shapley decomposition. (2026-09-17, fanfare: 3)

__[Predicting Market Stress with Random Forests](https://econpapers.repec.org/RePEc:cpr:ceprdp:20439)__: Tree-based machine learning models predict the full distribution of financial market stress 27% better than traditional time-series methods, with macro uncertainty and monetary policy expectations as key drivers. (2026-09-17, fanfare: 3)

__[Credit Channel of Monetary Policy in Practice](https://econpapers.repec.org/RePEc:boe:boeewp:023260)__: UK firm survey data validates that external borrowers face larger cost-of-capital increases and cut investment more than internal funders when rates rise, accounting for a quarter of monetary policy's total effect. (2026-09-14, fanfare: 3)

![Distribution of reported impacts of higher interest rates on sales, employment and investment, in 2023 Q3](https://www.ml-quant.com/issues/2026-09-25/figures/repec-09-5afeeb7e.png)

__[Monetary Policy Shocks Impair Innovation Financing](https://econpapers.repec.org/RePEc:boe:boeewp:023581)__: Monetary tightening reduces R&D more sharply among firms lacking cash-flow-based borrowing, generating persistent 0.12% output loss that younger, high-patent firms bear disproportionately. (2026-09-21, fanfare: 3)

![Persistent productivity loss over 12 years, larger for non-borrowers than borrowers post-shock](https://www.ml-quant.com/issues/2026-09-25/figures/repec-10-37560323.png)

__[AI Architecture and Financial Stability](https://econpapers.repec.org/RePEc:cpr:ceprdp:20681)__: Q-learning and large language model investors generate systematically different behaviors in fund redemption settings, with Q-learning showing excessive coordination and amplified fragility under default risk. (2026-09-17, fanfare: 3)

__[Hedge Fund Demand Inelasticity in Repo](https://econpapers.repec.org/RePEc:zbw:safewp:343098)__: Using German sovereign bond repo data, the research shows hedge funds are price-elastic in cash markets but highly inelastic in repo, inheriting elasticity from their cash-market counterparties. (2026-09-17, fanfare: 3)

![Scatter plot showing relationship between hedge fund repo positions and mispricing measures across market segments.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-12-0bcdc6e3.png)

__[Household Portfolios and Monetary Transmission](https://econpapers.repec.org/RePEc:cxv:wpaper:2602)__: Corporate leverage affects how monetary tightening transmits to the real economy: equity holders lose wealth while safe-asset holders are cushioned, raising the sacrifice ratio. (2026-09-21, fanfare: 3)

__[Financial Constraints and Monetary Price Response](https://econpapers.repec.org/RePEc:hhs:rbnkwp:0468)__: Swedish data reveals that financially constrained firms adjust prices less to monetary shocks, materially dampening aggregate inflation response to policy changes. (2026-09-14, fanfare: 3)

![Impulse Response Functions of Monthly Macro Variables](https://www.ml-quant.com/issues/2026-09-25/figures/repec-14-80a043c2.png)

__[Machine Learning for Implied Volatility Forecasting](https://econpapers.repec.org/RePEc:fip:fedgfe:103519)__: Tree-based models partition the option surface by moneyness and maturity to forecast volatility, reducing one-month-ahead errors by 13 percent versus benchmark models. (2026-09-17, fanfare: 3)

![Autocorrelation Function of Implied Volatilities](https://www.ml-quant.com/issues/2026-09-25/figures/repec-15-ca11c478.png)

__[Capital Flows and Exchange Rates Policy](https://econpapers.repec.org/RePEc:boe:boeewp:023263)__: In response to US monetary tightening, financial channels dominate for small open economies: credit spreads widen and output falls despite currency depreciation. (2026-09-14, fanfare: 3)

![Impulse responses showing GDP, exports, exchange rate, and credit spread with and without financial frictions.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-16-1d62efd5.png)

__[Rate Insurance in Equity and Bond Returns](https://econpapers.repec.org/RePEc:nbr:nberwo:35636)__: Stock returns are dampened by rate insurance: falling rates cushion payoff risk in bad times while rising rates in good times hedge duration exposure. (2026-09-13, fanfare: 3)

![Rate insurance effect comparing corporate bonds and equities across duration periods 1988-2019.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-17-31b661f5.png)

__[Common Factors Across Stocks, Bonds, Options](https://econpapers.repec.org/RePEc:nbr:nberwo:35579)__: The research identifies common risk factors spanning stocks, corporate bonds, and options linked to economic indicators, revealing significant market segmentation and cross-asset hedging opportunities. (2026-09-13, fanfare: 2)

![Cumulative returns of the first five common factors (F C)](https://www.ml-quant.com/issues/2026-09-25/figures/repec-18-154327bc.png)

__[Credit Card Banking Economics and Profitability](https://econpapers.repec.org/RePEc:nbr:nberwo:35607)__: Analysis of 550 million US credit card accounts shows that despite high charge-off rates, card lenders earn 1.5% alpha and 6.8% return on assets through pricing power and non-interest income. (2026-09-12, fanfare: 3)

__[Bank Runs History and Economic Consequences](https://econpapers.repec.org/RePEc:nbr:nberwo:35504)__: A database of 3,984 historical US bank runs shows runs are more likely in weak banks but often occur in strong banks; failures concentrate in fundamentally weak institutions. (2026-09-14, fanfare: 3)

__[Algorithmic Trading in Agricultural Futures](https://econpapers.repec.org/RePEc:ags:aaea26:404354)__: The study finds that algorithmic trading lowers realized volatility but increases tail co-movement and asymmetry in China's corn and soybean futures markets. (2026-09-25, fanfare: 2)

__[LASH Risk and Interest Rate Movements](https://econpapers.repec.org/RePEc:cpr:ceprdp:20158)__: The study measures liquidity risk from solvency hedging in sterling repo and swaps, finding that pre-crisis LASH risk predicted pension fund bond sales during the 2022 UK market stress. (2026-09-18, fanfare: 2)

__[High-Yield Corporate and Sovereign Bonds Converge](https://econpapers.repec.org/RePEc:cpr:ceprdp:20100)__: Analysis of 20 years of US junk bonds and emerging market sovereign debt reveals surprisingly similar average returns, Sharpe ratios, default frequencies, and haircuts across the two asset classes. (2026-09-18, fanfare: 2)

__[Economic News Drives Agricultural Volatility](https://econpapers.repec.org/RePEc:ags:asea26:404810)__: Financial and macroeconomic news topics systematically predict implied volatility in corn and soybean markets, with program trading and 2008 crisis topics most robust at short horizons. (2026-09-23, fanfare: 2)

__[USDA Reports Anchor Commodity Price Expectations](https://econpapers.repec.org/RePEc:ags:aaea26:404411)__: Traders place 15% weight on USDA crop reports relative to private priors when forming price expectations, with this anchoring weight rising when private analyst disagreement increases. (2026-09-23, fanfare: 2)

__[Collateral Policy Surprises Stabilize Banking](https://econpapers.repec.org/RePEc:zbw:bubdps:343110)__: Expansionary central bank collateral policy surprises reduce bank default risk and volatility while compressing government bond spreads, transmitting effects distinctly from asset purchases. (2026-09-21, fanfare: 2)

![Scatter plots showing collateral policy surprise correlation with CDS spreads across multiple financial indicators.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-26-c83c53c6.png)

__[Adaptive LASSO-MGARCH Volatility Forecasting](https://econpapers.repec.org/RePEc:cdf:wpaper:2026/4)__: Introducing coefficient-specific penalization into multivariate GARCH equations reduces complexity and improves out-of-sample covariance forecasts across bonds, equities, and commodities. (2026-09-16, fanfare: 2)

![Time evolution of returns for the eight assets](https://www.ml-quant.com/issues/2026-09-25/figures/repec-27-b4d64442.png)

__[Pension Funds' Swap-Driven Liquidity Risk](https://econpapers.repec.org/RePEc:cpr:ceprdp:21095)__: Dutch pension funds use interest rate swaps more aggressively when underfunded, exposing themselves to margin calls exceeding 6% of assets and forcing procyclical sales of government bonds. (2026-09-16, fanfare: 2)

__[A Theory of Bank Liquidity Requirements](https://econpapers.repec.org/RePEc:ecb:ecbwps:20263252)__: The study develops a general equilibrium model of financial intermediation showing that liquidity regulation alone cannot achieve efficient allocations and requires complementary policies like bank size limits. (2026-09-17, fanfare: 2)

![Supply and demand curves showing equilibrium cash determination in financial markets.](https://www.ml-quant.com/issues/2026-09-25/figures/repec-29-d78f5b03.png)

__[Too-Big-to-Fail Premium in European Banking](https://econpapers.repec.org/RePEc:dnb:dnbwpp:868)__: European banks with assets exceeding half of home GDP enjoy at least 30 percent lower credit spreads, and this implicit subsidy persists and depends on sovereign fiscal strength. (2026-09-17, fanfare: 2)

![Time-varying estimate of TBTF wedge, scaled to Dec 2024](https://www.ml-quant.com/issues/2026-09-25/figures/repec-30-671485e1.png)