This week the pipeline scored 25 new papers. Here are the 10 strongest by our rigor-weighted score (how scoring works).
1. The Cross-Section of Stock Returns and AI Exposure
Holy Grail · Math 7.0/10 · Rigor 9.0/10 · NLP & LLMs, HFT & Execution
We study 380 trillion tokens of realized AI consumption across more than four hundred LLMs. We build a high-frequency AI factor and show that a long-short strategy based on firms’ AI exposure earns significantly positive returns. The average strategy return is larger based on intensive, frontier-ori…
2. Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target
Holy Grail · Math 8.5/10 · Rigor 7.5/10 · Portfolio Optimization, Factor Investing
Forecasters often score the same units per date against one standardized realized outcome. We show that every standardized forecast splits exactly into a component aligned with this common target and a component uncorrelated with it. Three consequences follow: forecast-error correlation largely mirr…
3. Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting
Holy Grail · Math 7.5/10 · Rigor 8.0/10 · Machine Learning, Portfolio Optimization
Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate int…
4. Modeling interest rate swap volatility with GARCH processes
Holy Grail · Math 7.5/10 · Rigor 8.0/10 · Volatility, Options & Derivatives
We examine the conditional volatility dynamics of the USD 1Yx10Y forward swap rate using GARCH(1,1), GJR-GARCH(1,1), and a two-regime Markov-switching GARCH (MSGARCH) model. The analysis uses daily data from 2007 to 2023 and incorporates market-implied measures (ATM swaption volatility and the SRVIX…
5. Liquidity Provision and Rebate Design in Option Markets
Holy Grail · Math 9.0/10 · Rigor 7.0/10 · Volatility, Market Microstructure
We provide a model for the nested optimisation problem of market making and rebate design problems in option markets and find optimal strategies. A single market maker trades multiple European call options in a local-stochastic volatility option market with both make and take strategies, modeled, re…
6. Leaky-integrator reconstruction: taming error accumulation in recursive differenced time-series forecasting
Holy Grail · Math 6.5/10 · Rigor 8.0/10 · Machine Learning
Recursive differenced forecasting, the standard remedy for non-stationarity, predicts one-step changes and integrates them by cumulative summation. We show that this reconstruction is a discrete integrator with a pole on the unit circle, so the biased increment errors of a learned nonlinear model ar…
7. Model-agnostic noise reduction for high-dimensional time series data
Holy Grail · Math 8.0/10 · Rigor 7.0/10
We develop a model-agnostic framework for noise reduction in high-dimensional time series that explicitly targets optimal recovery of a low-dimensional latent dynamic component contaminated by observational white noise. Under the assumption that the latent dynamics live in a low-dimensional linear d…
8. Rough Bergomi turns grey
Holy Grail · Math 9.0/10 · Rigor 6.0/10 · Volatility
We propose a tractable extension of the rough Bergomi model, replacing the fractional Brownian motion with a generalised grey Brownian motion, which we show to be reminiscent of models with stochastic volatility of volatility. This extension breaks away from the log-Normal assumption of rough Bergom…
9. FedIncome: Federated Learning for Income Estimation in Digital Lending Under Data Sovereignty Constraints
Holy Grail · Math 6.0/10 · Rigor 8.0/10 · Risk Management
Verified income is often unavailable in digital loan applications, forcing lenders to rely on reported income and potentially leading to over-lending, overly conservative offers, or rejection of creditworthy applicants. Cross-institutional data-sharing constraints make this problem especially diffic…
10. Proof of Stake economy under centralized exchanges–a mean field model
Holy Grail · Math 8.5/10 · Rigor 5.0/10 · Crypto & DeFi
We consider the interaction between centralized trading and decentralized Proof of Stake (PoS) blockchain ecosystems. Motivated by the increasing dominance of centralized exchanges and the institutionalization of crypto markets, we study how trading activities on centralized exchanges affect staking…
Browse everything new in the flowchart library, or explore by area on the topic hubs.