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.

169,181 papers · 148 categories

Trend · papers per month

6131925 · Dec 202419922001200920182026
48 results for historical graffiti

Capsule network improves handwriting recognition of historical graffiti.

problem Recognizing historical graffiti letters carved on stone walls.
method Used capsule deep neural network on a challenging dataset of 4000 images of 34 letters.
result Validation accuracy and AUC values were significantly higher for capsule network than for CNN.

Machine learning identifies historical graffiti letters with high accuracy.

problem Identifying historical graffiti letters carved on stone walls.
method Pre-processed a dataset of 4000 images of carved letters, applied MLR and CNN models.
result CNN model achieved AUC values close to 0.99 for both notMNIST and CGCL.

ArtificialReplay improves data efficiency in bandits using historical data.

problem Data inefficiency in warm-starting bandit algorithms.
method ArtificialReplay, a meta-algorithm for incorporating historical data into any bandit algorithm.
result ArtificialReplay uses only a fraction of historical data compared to a full warm-start approach, achieving identical regret.

ADR helps LLMs find and use historical analogies for foresight analysis.

problem LLMs struggle to find relevant historical analogies due to surface-level matching.
method Proposes CANA framework with mechanism alignment and cross-analogy confirmation.
result CANA improves historical analogy generation by up to 10%.

Proposes dynamic borrowing method for historical data in clinical trials.

problem Insufficient statistical power in rare and pediatric disease clinical trials.
method Dynamic borrowing method based on frequentist approach using similarity measures.
result Demonstrates usefulness of dynamic borrowing in reanalyzing clinical trial data.

Data describing historical economic growth are analysed. Included in the analysis is the world and regional economic growth. The analysis demonstrates that historical economic growth had a natural tendency to follow hyperbolic distributions. Parameters describing hyperbolic distributions have been determined. A search …

2015-09-09abs ↗pdf ↗

Study shows noisy historical data can still predict future text classification well.

problem Challenges in text classification with noisy, historical data.
method Examined how performance metrics on noisy data reflect future model performance.
result Noisy training data can be used to build effective prediction models for cleaner inputs.

Improved Bayesian inference using power priors with historical data.

problem Improving Bayesian inference with historical data.
method Generalized power priors that adapt to the α\alpha parameter of Amari's α\alpha-divergence.
result Improved performance through appropriate choices of the α\alpha parameter.

Develops algorithms to exploit historical and pre-clustered arm information in bandit problems.

problem Optimizing decision-making in multi-armed bandit and contextual bandit problems with historical observations and pre-clustered arms.
method META algorithm that combines historical observations and pre-clustering information, deriving regret bounds for various scenarios.
result META algorithm effectively balances between using historical observations and clustering, outperforming the other in different scenarios.

Combines experimental and historical data for robust policy evaluation.

problem Policy evaluation with mixed data sources, especially experimental vs historical.
method Linear integration of estimators from experimental and historical data, optimized for MSE minimization.
result Proposed estimators outperform traditional methods in ridesharing company data.

In this paper we look at the efficacy of different risk measures on energy markets and across several different stock market indices. We use both the Value at Risk and the Tail Conditional Expectation on each of these data sets. We also consider several different durations and levels for historical risk measures. Throu…

2011-11-18abs ↗pdf ↗

The paper develops a method to forecast financial risk multiple steps ahead using quantile time series and historical simulation.

problem Forecasting financial risk multiple steps ahead with accurate estimation of Value-at-Risk (VaR) and Expected Shortfall (ES).
method Quantile-based, semi-parametric historical simulation estimation of VaR and ES models, using quantile loss function and resampling.
result The proposed method accurately forecasts VaR and ES one and multiple steps ahead, superior to existing methods.

Calibrates historical and implied correlations in energy markets.

problem Challenges in aligning historical correlations of futures contracts with implied volatility smiles.
method Multiplicative multi-factor Heath-Jarrow-Morton model combined with stochastic volatility from lifted Heston model, using Kemna-Vorst approximation and Fourier-based techniques.
result Remarkable joint historical and implied calibration fits on the German power market.

Econophysics embodies the recent upsurge of interest by physicists into financial economics, driven by the availability of large amount of data, job shortage in physics and the possibility of applying many-body techniques developed in statistical and theoretical physics to the understanding of the self-organizing econo…

2008-02-11abs ↗pdf ↗

Contextualizing financial news improves stock price predictions.

problem Predicting stock prices from financial news requires understanding historical context.
method Proposed a method using a large language model for main articles and a small model for historical context.
result Historical context significantly improves model performance across methods and time horizons.

A new GNN model predicts stock trends by learning historical and future correlations.

problem Limited improvement in stock trend prediction models due to ignoring future patterns.
method DishFT-GNN framework that trains a teacher and student model to capture historical and future data correlations.
result State-of-the-art performance on real-world datasets.

New models avoid probability in option pricing, matching historical and implied volatilities.

problem Developing option pricing models without probability.
method Statistical analysis of historical volatility and pathwise lift of stock dynamics.
result Option pricing models can be based on pathwise properties of stock dynamics.

RL improves market making with historical data time travel.

problem Limited ability to simulate and fully appraise the impact of actions in competitive systems.
method Introduces 'consistent data time travel' to adjust historical data time index.
result Significant improvement in agent's gain with data time travel.

Historical returns depend on historical closing prices and distributions. We describe how to compute adjusted closing prices from closing price/distribution data with an emphasis on spreadsheet implementation. Then the growth of a security from one date to another (1 + total return) is just the ratio of the correspondi…

2011-05-15abs ↗pdf ↗

Identifying the type of font (e.g., Roman, Blackletter) used in historical documents can help optical character recognition (OCR) systems produce more accurate text transcriptions. Towards this end, we present an active-learning strategy that can significantly reduce the number of labeled samples needed to train a font…

2016-01-27abs ↗pdf ↗

Study examines risk of digital currencies using GARCH and Filtered Historical Simulation.

problem Risk management of digital currencies like Bitcoin, Ethereum, Litecoin, and Ripple.
method GARCH modelling followed by Filtered Historical Simulation.
result Digital currencies are subject to higher risk, requiring higher buffer and risk capital.

Two ML approaches compare in recognizing tables from historical records.

problem Recognizing rows and columns in hand-written registry books.
method Comparison of Conditional Random Field and Graph Convolutional Network.
result Both ML methods achieve an 89 F1 score for table detection.

Improves trial efficiency by adjusting for historical prognostic scores.

problem Reducing statistical uncertainty in randomized trial estimates.
method Linear covariate adjustment using a prognostic model trained on historical data.
result Prognostic covariate adjustment achieves minimum variance and reduces mean-squared error.

Improved handwriting recognition for historical documents with minimal labeled data.

problem Challenges in recognizing historical documents, especially lack of text-line annotations.
method Trained a deep CRNN system on 10% labeled data, augmented with crafted multiscale data, and applied model-based normalization.
result Achieved second best result in ICDAR2017 competition on publicly available READ dataset.

This study compares financial density forecasts using risk-neutral and historical schemes.

problem Comparing the forecasting ability of risk-neutral and historical financial density models.
method Comprehensive comparison of 15 predictive schemes over 21 years, evaluating statistical consistency, local accuracy, and forecasting errors.
result Risk-neutral densities outperform historical-based predictions in terms of information content.

The study uses historical revenue data to forecast music catalog cashflows and multipliers.

problem Valuation of music catalogs based on historical revenue data.
method Risk-neutral approach using discounted cashflows formula.
result Ask prices are close to multipliers justified by median song cashflows, while best bids are near multipliers justified by bottom decile cashflows.

Combines historical and market data for better portfolio selection.

problem Improving portfolio selection through diverse information integration.
method Bayesian learning via Gaussian mixture model to harmonize historical and market data.
result The method enhances forecasting accuracy and robustness across various capital markets.

The paper evaluates criteria for selecting cryptocurrencies based on historical data.

problem High risk of cryptocurrencies due to volatility.
method Characterized returns and risks using historical data in short time windows (7 and 15 days). Analyzed the importance of criteria using various methods.
result Importance of criteria for selecting cryptocurrencies is analyzed and evaluated.

DBNs improve VaR forecasting compared to traditional models, but SVaR forecasts are conservative.

problem Forecasting VaR and SVaR using dynamic Bayesian networks.
method DBN framework applied to S&P 500 index returns, comparing to autoregressive models and historical simulation.
result DBNs achieve comparable VaR forecasting accuracy to historical simulation models, but SVaR forecasts remain conservative.

The paper explores using historical data to improve clinical trial analysis by optimizing covariate weights.

problem Limited covariates in small clinical trials reduce the effectiveness of analysis.
method Leverage historical data to pre-specify covariate weights as a composite covariate.
result A composite covariate improves the cost/benefit ratio and reduces overfitting in small clinical trials.

Study refines trend-following strategy to improve adaptability.

problem Challenges in practical implementation of historical trend-following strategies.
method Modifications to historical strategy, including T-bills exclusion, alternative allocations, industry exclusions, momentum signals, and Walk-Forward Analysis.
result Persistent challenges in adapting historical strategies to modern markets.

This paper reviews and compares deep generative models for financial time series and VaR.

problem Forecasting risk factor distribution in financial markets.
method Apply multiple deep generative models (CGAN, CWGAN, Diffusion, Signature WGAN) and propose new methods for conditional time series generation.
result Top performing models are Historical Simulation, GARCH, and CWGAN.

Study shows survivorship bias inflates returns in India's small-cap index.

problem Survivorship bias in emerging market small-cap indices.
method Reconstructing historical index composition through market capitalization ranking and comparing equal-weight portfolios of current constituents versus all historical members.
result Survivor-only backtesting overstates returns by 4.94 percentage points and Sharpe ratios by 0.097.

LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.

problem Behavioral biases in LLMs' stock return forecasts.
method Comparison of LLM forecasts with crowd-sourced estimates and historical data.
result LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.