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.

168,738 papers · 148 categories

Trend · papers per month

18355370 · May 202619922001200920172026
48 results for walk-forward forecasting

Machine learning predicts Bitcoin returns but trading performance drops with costs.

problem Trading Bitcoin predictions with transaction costs.
method XGBoost, LSTM, iTransformer models evaluated in walk-forward protocol; cost-aware execution filter implemented.
result Cost-aware execution filter restores profitability; XGBoost strategy outperforms.

XGBoost predicts NEPSE Index log returns with low error and high directional accuracy.

problem Forecasting daily log-returns in the NEPSE Index with high accuracy.
method XGBoost machine learning, feature engineering, hyperparameter optimization, walk-forward validation.
result Optimal XGBoost configuration achieves lowest log-return RMSE and MAE.

Framework improves ETF volatility forecasting by adapting to market conditions.

problem Challenges in volatility forecasting due to shifting market conditions and varying model performance.
method Risk-sensitive specialist routing using online risk-sensitive evaluation and state-dependent gating.
result Reduces forecast loss by 24% and underprediction loss by 22% compared to rolling-best baseline.

LSTM and gradient boosting models fail to outperform random chance in predicting MNQ futures.

problem Predicting intraday direction in MNQ futures using LSTM and gradient boosting.
method Comparing LSTM and gradient boosting models on 944 trading days of MNQ futures data.
result No model achieves statistically significant accuracy above random chance.

This study optimizes trading strategy parameters using walk-forward techniques and finds robust performance.

problem Optimizing trading strategy performance through parameter optimization.
method Walk-forward optimization with varying window lengths, tested on Bitcoin, Binance Coin, and Ethereum.
result The strategy outperforms Buy-and-Hold with lower drawdown and higher Information Ratio.

Volatility forecasting and return prediction in high-frequency Chinese equity markets.

problem Improving statistical forecasting performance and economic strategy outcomes in equity markets.
method Developing a sequential two-stage framework combining realized volatility modeling and XGBoost return prediction.
result Regime-aware volatility forecasting outperforms baseline models.

The paper optimizes forecasting for risk-adjusted decisions under trading frictions.

problem Optimizing forecasting accuracy for investment decisions in the presence of transaction costs.
method Develops a utility-weighted calibration criterion to minimize decision loss net of costs.
result Utility-weighted calibration reduces decision loss by over 30% and improves Sharpe ratio.

New model predicts weekly earthquakes with better tail risk assessment.

problem Violation of Poisson assumption in seismic data.
method Neural network for per-cell overdispersion estimation.
result 8.6% reduction in mean pinball deviation, 12.5% lower CRPS in tail events.

This study predicts stock prices using hybrid machine learning and LSTM models.

problem Accurately predicting stock prices despite the efficient market hypothesis.
method Hybrid modeling combining machine learning and deep learning (LSTM) for NIFTY 50 index prediction.
result LSTM-based univariate model with one-week prior data is most accurate.

A study shows that a fine-tuned model's directional accuracy in financial forecasting is largely due to chance, not skill.

problem Misleading directional accuracy in financial forecasting models.
method A reproducible, frozen-data benchmark with paired significance tests to separate skill from base-rate artifact.
result Fine-tuned models do not show significant directional skill over a base rate of 70% in financial forecasting.

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.

Develops a validated trading framework for market microstructure signals.

problem Overfitting and lookahead bias in algorithmic trading.
method Interpretable hypothesis-driven signal generation, reinforcement learning, strict out-of-sample testing.
result Modest annualized returns with strong downside protection and market-neutral characteristics.

Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.

problem Improving deep learning models for forecasting fat-tailed financial returns.
method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.
result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.

DRL optimizes asset managers' hedging timing based on market conditions.

problem Optimal timing for hedging strategies given market conditions.
method Deep Reinforcement Learning framework with contextual information, lagged observations, and robust testing.
result Our approach achieves superior returns and lower risk compared to standard methods.

RGRR allocates between QQQ and DIA based on relative states, improving Sharpe and CAGR.

problem Optimizing ETF allocation between QQQ and DIA for better risk-adjusted returns.
method Screened relative and macro states, globally screened interactions, fixed position mapping, walk-forward validation.
result RGRR improves Sharpe and CAGR compared to 100% QQQ and 50/50 QQQ-DIA allocations.

GMADL loss function improves model performance and reduces transaction costs.

problem Overfitting and high transaction costs in high-frequency algorithmic trading models.
method Introduces GMADL loss function for better optimization and feature selection.
result GMADL produces superior results and reduces transaction costs compared to standard loss functions.

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.

GT-Score reduces overfitting in trading strategies by integrating multiple criteria.

problem Overfitting in data-driven financial models leads to unreliable out-of-sample performance.
method Integrates performance, statistical significance, consistency, and downside risk into a composite objective function.
result Improves generalization ratio by 98% compared to baseline objective functions in walk-forward validation.

Study examines how different time series cross-validation methods affect anomaly detection in multivariate time series.

problem Evaluating anomaly detection in multivariate time series requires preserving temporal dependencies, especially for subsequence anomalies.
method Systematically investigates walk-forward and sliding window methods across various validation configurations and classifier types.
result Sliding window method consistently yields higher precision-recall scores and reduced fold-to-fold performance variance, particularly for deep learning models.

Combines model-based and model-free RL for better financial market performance.

problem Challenges of Reinforcement Learning in volatile financial markets.
method Adapts model-based RL with model-free RL, incorporating contextual signals and walk-forward analysis.
result Outperforms traditional financial models in various metrics.

Hybrid classical-quantum framework optimizes portfolio rebalancing with reduced transaction costs.

problem Optimizing portfolio rebalancing with reduced transaction costs and lookahead bias.
method Combining Ledoit-Wolf shrinkage covariance estimation, hierarchical correlation clustering, entropy-regularised Genetic Algorithm, minimum-variance and equal-weight benchmarks, QUBO formulation, and QAOA for solving the combinatorial optimisation problem.
result GA + QAOA strategy outperforms classical methods with reduced rebalances and transaction costs.

Thinking LLMs struggle with stock prediction, especially as data complexity increases.

problem Evaluating the performance of 'thinking' LLMs in stock prediction, especially under varying levels of cross-sectional complexity.
method Rolling 48m/1m walk-forward evaluation, comparing direct LLMs, TLLMs, and classical learners on cross-sectional ranking loss, MSE, and backtests with transaction costs.
result TLLMs' ranking quality deteriorates as cross-sectional complexity grows, while direct LLMs remain stable.

The purpose of this research paper it is to present a new approach in the framework of a biased roulette wheel. It is used the approach of a quantitative trading strategy, commonly used in quantitative finance, in order to assess the profitability of the strategy in the short term. The tools of backtesting and walk-for…

2016-09-30abs ↗pdf ↗

AlphaZeroBeta uses deep reinforcement learning for market-neutral portfolios, outperforming traditional methods.

problem Traditional portfolio management methods often fail during market regime shifts or when assumptions break down.
method Combines a composite reward function and CNN-GRU policy trained end-to-end via Recurrent PPO.
result Achieves higher Sharpe ratios than baselines while maintaining near-zero benchmark correlations.

Short-term load forecasting is a critical element of power systems energy management systems. In recent years, probabilistic load forecasting (PLF) has gained increased attention for its ability to provide uncertainty information that helps to improve the reliability and economics of system operation performances. This…

2019-03-26abs ↗pdf ↗

Combining forecasts of 16 ED causes improves accuracy and stability.

problem Forecasting accuracy and stability for ED admissions is poor due to model uncertainty and limited data.
method High-dimensional forecast combinations of 16 cause-specific ED forecasts using extensive covariates.
result Forecast combinations yield forecast accuracies of 3.81%-23.54% across causes, outperforming individual models in 50% of scenarios.

Conditional forecasts improve performative prediction accuracy.

problem Performative predictions undermine standard forecasting methods.
method Condition forecasts on covariates to make them forecast-invariant.
result Proper scoring rules fail under conditioning, but two solutions are identified.

Study improves seasonal forecasts using deep learning.

problem Challenges in generating large forecast ensembles and limited observations for verification.
method Developed a probabilistic deep neural network model.
result Demonstrated favorable skill compared to state-of-the-art dynamical forecast systems.

Two new methods improve forecasting of functional time series data.

problem Forecasting of functional time-dependent data.
method Functional Singular Spectrum Analysis (FSFA) based forecasting methods.
result Our methods outperform existing algorithms for periodic stochastic processes.

MPANF improves naive forecast by incorporating directional information.

problem Challenging to surpass naive forecast in financial time series.
method Combines naive forecast with movement prediction and accuracy.
result MPANF generally outperforms common benchmarks.

Simplifies forecast combination by using diversity of out-of-sample forecasts.

problem Estimating optimal weights for forecast combinations is challenging.
method Use out-of-sample forecasts to extract features and calculate weights for forecast combination.
result Achieves superior forecasting performance in point forecasts and prediction intervals.

Microdata improves inflation forecasts after major shocks, study finds.

problem Forecasting inflation in a non-stationary environment with microeconomic data.
method Developed a scan test to detect periods of micro forecast outperformance, combined with adaptive machine learning.
result Micro forecasts improve inflation predictions after major shocks, especially after 2020.