Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

22436586 · Jun 202619922001200920172026
48 results for annualized returns

Study estimates Medallion's compounded return before fees at 31.8%.

problem Incorrectly using yearly returns for compounding leads to overestimation of fund performance.
method Used fund sizes and trading profits to estimate compounded return; used manager's wealth as proxy for Simons.
result Annualized compounded return of Medallion before fees is likely under 35%

The p-index improves investment performance for NYSE stocks but not for SSE stocks.

problem Improving investment performance for stocks using the p-index.
method Comparing different p-ratio strategies and empirical efficient frontiers for SSE and NYSE stocks.
result The p-index enhances investment performance for NYSE stocks but not for SSE stocks.

Estimates returns for dollar cost averaging using geometric Brownian motion.

problem Estimating returns for dollar cost averaging investing strategy.
method Uses geometric Brownian motion and log-Normal distribution to construct a lower bound for returns. Computes parameters recursively and in closed form for dollar cost averaging. Compares to lump sum investing for matching wealth distributions.
result Probability of negative returns is less than 2.5% for 40 years of annual dollar cost averaging.

A3T-GCN model forecasts FTSE100 stock prices using technical indicators and financial ratios.

problem Forecasting closing stock prices of FTSE100 constituents.
method Hybrid A3T-GCN architecture using technical indicators, financial ratios, and sector correlations.
result A3T-GCN model improves prediction accuracy with annualized log-returns and shorter sequence lengths.

The paper finds stocks with higher dynamic network risk have lower returns.

problem Understanding and pricing short-term and long-term dynamic network risk in stock returns.
method Examined the relationship between stock sensitivities to dynamic network risk and expected returns, using economic theory and empirical analysis.
result A one-standard deviation increase in long-term network risk loadings associates with a 7.66% drop in annualized expected returns.

The study finds that supply chain information from LLM embeddings improves stock returns predictions.

problem Predicting stock returns using textual information from annual reports.
method Combining LLM embeddings of annual reports with supply chain knowledge graph propagation.
result Network-augmented embeddings significantly predict stock returns with a Sharpe ratio of 0.86 and alpha of 7.27%.

Paper uses LLMs to analyze annual reports for stock investment, improving efficiency.

problem Manual analysis of annual reports is time-consuming and requires expertise.
method Leverages Large Language Models to extract and analyze annual reports.
result Machine Learning model trained on LLM outputs outperforms S&P500 returns.

The paper uses PCA and HMM to forecast stock returns outperforming buy-and-hold.

problem Predicting stock returns accurately.
method Applied PCA to covariance matrix of S&P 500 stocks, used HMM on principal components, and forecasted stock returns.
result The model outperforms buy-and-hold strategy in terms of annualized Sharpe ratio.

The paper links labor income risk to stock returns using industry portfolio returns.

problem Understanding the impact of sectoral shifts on stock returns.
method Using cross-industry dispersion (CID) as a proxy for unemployment risk, the paper examines the relationship between stock returns and the sensitivity of returns to CID innovations.
result Stocks with high sensitivity to CID have lower expected returns, suggesting they are more exposed to sectoral shifts and unemployment risk.

Investor emotions predict earnings announcements, but excitement lowers returns.

problem The impact of investor emotions on earnings announcements and their returns.
method Social media data analysis over a decade to test the relationship between investor emotions and earnings announcements.
result Excitement about earnings announcements is associated with lower announcement returns.

Over the past half-century, the empirical finance community has produced vast literature on the advantages of the equally weighted S\&P 500 portfolio as well as the often overlooked disadvantages of the market capitalization weighted Standard and Poor's (S\&P 500) portfolio (see \cite{Bloom}, \cite{Uppal}, \cite{Jacobs…

2016-03-19abs ↗pdf ↗

PolyBench benchmarks LLMs on real market data, revealing significant performance gaps.

problem Benchmarking LLMs for real-world event prediction from live market signals.
method Multimodal benchmark derived from Polymarket, evaluating 7 LLMs under identical market states.
result Only two models achieve positive financial returns, highlighting the gap between fluency and probabilistic reasoning.

Bayesian approach confirms no return predictability for 1926-2004 data, weak evidence for 1953-2021.

problem Investigating return predictability using Bayesian methods.
method Developed a new shrinkage type prior for a model parameter in a VAR system, compared to other estimation methods.
result Bayesian approach outperforms reduced-bias estimator in terms of size and power.

End-to-end framework optimizes financial metrics using neural networks.

problem Difficult portfolio optimization in financial markets due to non-stationarity and high costs.
method Directly optimizes differentiable financial metrics via neural networks, incorporating realistic costs and rebalancing.
result Best model achieves +7.86% total return, outperforming S&P 500 by 12.38 percentage points.

Improved stock selection through predictive fundamentals and uncertainty estimates.

problem Selecting stocks based on future financial data to outperform traditional factor models.
method Train deep nets to forecast future fundamentals, incorporate uncertainty estimates, and adjust portfolios to manage risk.
result Simulated annualized return of 17.7% and Sharpe ratio of 0.84 for uncertainty-aware model, significantly higher than 14.0% and 0.52 for standard factor models.

Sentiment analysis of DAX40 stocks improves performance by 5.38% annually.

problem Creating a more responsive stock market index using sentiment analysis.
method Extract sentiment from news articles, adjust index weights based on sentiment, compare performance to existing indices.
result Sentiment index outperforms DAX40 by 7.51% annually, adjusted for costs.

Proposes a two-stage sector rotation method using machine learning and deep learning.

problem Identifying sectors with high investment attractiveness based on market conditions.
method Two-stage methodology: 1) Predict ETF prices using market indicators and feature selection, 2) Rank sectors based on predicted returns and select top sectors.
result The proposed methodology outperforms equally weighted portfolios and Echo State Networks show outstanding performance.

This paper proposes a new portfolio allocation method using LLMs to outperform traditional strategies.

problem Persistent tradeoff between risk and return in portfolio management.
method Follow-the-leader approach with sentiment-based trade filtering and LLM-driven hedging.
result Empirical results show a 69% increase in annualized returns and 119% in Sharpe ratio compared to SPY buy-and-hold.

Interpretable machine learning uncovers ESG's explanatory power on equity returns across sectors and capitalizations.

problem Explaining equity returns beyond market factors using ESG data.
method Interpretable machine learning models, cross-validation scheme, random company-wise validation.
result Gradient boosting models explain unaccounted price returns, with ESG data outperforming basic fundamental features.

The paper introduces a new pairs trading model using nonlinear and non-Gaussian state-space models.

problem Developing a robust trading strategy for pairs of assets with non-Gaussian and heteroskedastic innovations.
method A nonlinear and non-Gaussian state-space model for the spread between two assets, with mean reversion modeled as a mean-reverting process.
result The new trading strategy yields significantly higher returns and Sharpe ratios compared to existing methods.

Study finds no consistent return predictability using payout ratios across 16 countries.

problem Return predictability using payout ratios in various markets.
method Analysis of 16 developed countries' bond, equity, and housing markets using payout-price ratios.
result No consistent in-sample and out-of-sample performance with positive utility gain.

Deep neural networks improve portfolio construction by jointly modeling returns and risks.

problem Traditional portfolio construction methods fail under time-varying market conditions.
method Jointly modeling dynamic expected returns and risk structures using deep neural networks.
result Deep forecasting model achieves competitive predictive accuracy and economically meaningful directional accuracy.

Study examines the impact of employment benefit costs on firm profitability.

problem Impact of employment benefit costs on firm profitability.
method Panel data regression analysis using E-Views.
result There is a significant positive relationship between employment benefit costs and firm profitability.

Classification outperforms regression in portfolio construction, yielding higher Sharpe ratios.

problem Determining which machine learning approach (classification vs. regression) is more effective for portfolio construction.
method Used stacking ensemble of gradient boosted tree, random forest, and neural network models.
result Classification yields higher Sharpe ratios and economically significant alphas compared to regression.

Quantum stochastic walks optimize portfolios by leveraging financial networks, improving Sharpe ratios and reducing turnover.

problem Optimizing portfolios in noisy financial markets with superior risk-adjusted returns.
method Embed assets in a weighted graph, using quantum stochastic walks to derive optimal portfolio weights from the stationary distribution.
result Quantum stochastic walks can lift Sharpe ratios by up to 27% and reduce turnover from 480% to 2-90%.

Study finds monthly SIPs outperform first-day SIPs in Nifty 50 by 0.5-2.5% annually.

problem Underexplored impact of SIP timing in India's equity market.
method 22-year analysis using multi-layered statistical framework (non-parametric tests, effect size metrics, SSD).
result Monthly SIPs (EXP-SIP) outperform first-day SIPs (FTD-SIP) by 0.5-2.5% annually over short-to-medium-term horizons.

This study compares three portfolio design approaches for stock selection.

problem Designing a profitable portfolio with precise stock returns and risks.
method Three portfolio design approaches: mean-variance portfolio, hierarchical risk parity, and autoencoder-based portfolio.
result Autoencoder portfolios outperform MVP on annual returns, but MVP is best on risk-adjusted returns.

This study compares three portfolio optimization methods on Indian stocks.

problem Comparing portfolio optimization methods on Indian stocks.
method Mean-Variance, Hierarchical Risk Parity, and Reinforcement Learning approaches.
result Reinforcement Learning outperformed other methods in terms of Sharpe ratio.

In this thesis, we develop a comprehensive account of the expressive power, modelling efficiency, and performance advantages of so-called trading agents (i.e., Deep Soft Recurrent Q-Network (DSRQN) and Mixture of Score Machines (MSM)), based on both traditional system identification (model-based approach) as well as on…

2019-09-12abs ↗pdf ↗

NYSE stock prices show persistent correlations over years, exploitable through arbitrage strategies.

problem Predicting and exploiting long-term price correlations in NYSE stocks.
method Analyzed 1000 NYSE stocks over 5 years, measured discrepancies from Brownian motion, and tested arbitrage strategies.
result 45% of a stock's 1-hour returns variance is explained by cross-correlations with other stocks, especially during high volatility periods.

We uncover a large and significant low-minus-high rank effect for commodities across two centuries. There is nothing anomalous about this anomaly, nor is it clear how it can be arbitraged away. Using nonparametric econometric methods, we demonstrate that such a rank effect is a necessary consequence of a stationary rel…

2016-07-26abs ↗pdf ↗

The paper models US inflation and hyperinflation using monetary and GDP data.

problem Understanding and predicting inflation and hyperinflation.
method Developed economic models to predict US CPI growth based on BMS, GDP, and savings.
result An exact relationship between CPI growth and BMS growth minus GDP and savings growth was found, with a residual term.

Framework integrates financial and annual report data for better corporate credit ratings.

problem Lack of insights from non-financial data in credit rating models.
method Uses FinBERT to extract features from annual reports and combines them with financial data.
result Improves credit rating accuracy by 8-12%.