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

126253379505 · Jun 202019922001200920172026
48 results for out-of-sample prediction

Paper develops a method to predict spatial point processes with guarantees.

problem Predicting the number of events in space with uncertainty.
method Regularized method to learn spatial models with out-of-sample guarantees.
result Method provides valid prediction intervals even when model is misspecified.

We identify and validate a model for PCR in high dimensions, improving prediction guarantees.

problem Model identification and out-of-sample prediction in high-dimensional error-in-variables settings.
method Analysis of principal component regression (PCR) in fixed design settings, introducing a linear algebraic condition.
result Consistent model identification and improved out-of-sample prediction guarantees.

Study the impact of overfitting on linear predictive models' performance.

problem Overfitting reduces the out-of-sample performance of linear predictive trading strategies.
method Computed in- and out-of-sample means and variances of PnLs to derive replication ratios.
result Replication ratio diminishes for complex strategies with many assets.

New model optimizes portfolios over multiple periods using predictive control.

problem Optimizing multi-period portfolios with risk and variance objectives.
method Model Predictive Control with Mean-Variance and Risk Parity.
result 30x faster and more robust solutions compared to single period models.

Paper proposes a method to improve prediction intervals for neural networks.

problem Improving prediction intervals for neural network models.
method Adapting extremely randomized trees to neural networks to create ensembles.
result The method yields gains in out-of-sample accuracy and is superior to existing methods.

We consider the multi-class classification problem when the training data and the out-of-sample test data may have different distributions and propose a method called BCOPS (balanced and conformal optimized prediction sets). BCOPS constructs a prediction set C(x)C(x) as a subset of class labels, possibly empty. It tries …

2019-05-10abs ↗pdf ↗

The paper uses machine learning to forecast macroeconomic outcomes with high-dimensional data.

problem Forecasting the full conditional distribution of macroeconomic outcomes.
method Systematically integrating three key principles: high-dimensional data with regularization, rigorous out-of-sample validation, and incorporating nonlinearities.
result Regularization via shrinkage is essential to control model complexity, while nonlinearities yield limited improvements in predictive accuracy.

New method improves predictive systems with better theoretical guarantees.

problem Constructing predictive systems with out-of-sample calibration guarantees.
method Residual Distribution Predictive Systems (RDPs) that nest conformal predictive systems and offer flexibility.
result Empirically, RDPs perform competitively with conformal predictive systems and can be implemented with various regression methods.

Study improves prediction accuracy and uncertainty for mobile sensor data using randomized neural networks.

problem Improving prediction accuracy and uncertainty for mobile sensor data.
method Cross-validation and uncertainty determination for randomized neural networks.
result Improved out-of-sample performance and confidence intervals for prediction error.

Downsampling can improve generalization in ridgeless linear regression, especially with optimal sketching size.

problem Improving generalization in ridgeless linear regression with limited data.
method Investigating the effects of downsampling on the sketched ridgeless least square estimator in the proportional regime.
result Optimal sketching size minimizes out-of-sample prediction risks and stabilizes risk curves.

A new framework for time series forecasting that adapts to varying patterns.

problem Forecasting multivariate time series with predictive heterogeneity.
method Validation-driven clustering framework that applies specialization based on out-of-sample predictive performance.
result Improves robustness to heavy-tailed errors and local anomalies.

The paper proposes a new model for predicting and analyzing economic variables.

problem Predicting and analyzing economic variables in developed regions.
method Time-varying parameter global vector autoregressive (TVP-GVAR) framework combined with machine learning models.
result The proposed model provides high precision out-of-sample predictions and novel insights into economic variable connectedness.

Optimizes decisions without knowing the true distribution using historical data.

problem Optimizing decisions without knowing the true distribution.
method Combines sampling and bisection search algorithms to solve an optimization problem.
result Proves sufficient conditions for local out-of-sample optimality.

High-performing equity factor with Sharpe ratio above 13 out-of-sample.

problem Hidden cross-sectional predictability in stock returns.
method Regime-conditional signal activation combining value and short-term reversal signals.
result Annualized returns of 158.6% with 12.0% volatility, strong performance out-of-sample.

The paper analyzes LOCV for high-dimensional risk estimation, proving error bounds.

problem Estimating out-of-sample prediction error in high-dimensional settings.
method Theoretical analysis of leave-one-out cross validation (LOCV) in penalized regression.
result Finite sample upper bounds on LOCV error, showing it converges to zero as n,p → ∞.

Paper presents a new way to analyze machine learning generalization without probabilistic assumptions.

problem Traditional generalization analysis assumes i.i.d. data, which is often unverifiable.
method Uses sensitivity analysis of optimization problems to derive deterministic generalization bounds.
result Obtains generalization bounds that relate in-sample and out-of-sample evaluations through an error term quantifying data similarity.

The paper tackles stock prediction models by improving their generalizability to out-of-sample domains using causal representation learning.

problem Low signal-to-noise ratio and nonstationary nature of financial markets lead to poor performance of stock prediction models.
method The paper investigates Domain Generalization techniques, focusing on causal representation learning to improve model generalizability. It introduces a novel error bound and a causal discovery technique to mitigate spurious correlations.
result The proposed approach enhances the generalizability of stock prediction models, as demonstrated by numerical results.

We document a mechanism operating in complex adaptive systems leading to dynamical pockets of predictability (``prediction days''), in which agents collectively take predetermined courses of action, transiently decoupled from past history. We demonstrate and test it out-of-sample on synthetic minority and majority game…

2004-10-29abs ↗pdf ↗

CASTLE learns causal DAG to improve model generalization.

problem Improving model generalization to out-of-sample data.
method CASTLE learns causal relationships via adjacency matrix embedded in neural network input layers, reconstructing only causal features.
result CASTLE leads to better out-of-sample predictions compared to other regularizers.

Kalshi prediction markets forecast cryptocurrency volatility through monetary policy and inflation signals.

problem Forecasting cryptocurrency volatility using prediction markets.
method Monetary policy and inflation signals from Kalshi prediction markets.
result Signals from Kalshi prediction markets predict cryptocurrency volatility with statistical significance.

The paper predicts and explains the decay of stock anomaly performance over time.

problem Predicting and explaining the drop in risk-adjusted performance of stock anomalies.
method The authors propose ex-ante characteristics based on hypotheses of out-of-sample decay and in-sample overfitting.
result The year of publication explains 30% of the variance in Sharpe decay across factors.

Testing procedures for predictive regressions with lagged autoregressive variables imply a suboptimal inference in presence of small violations of ideal assumptions. We propose a novel testing framework resistant to such violations, which is consistent with nearly integrated regressors and applicable to multi-predictor…

2016-12-15abs ↗pdf ↗

Paper analyzes high-dimensional portfolio risks and finds empirical out-of-sample relative loss is more reliable.

problem Analyzing risks in high-dimensional portfolios using empirical variance.
method Derives asymptotic behavior of out-of-sample variance and relative loss in high-dimensional settings.
result Empirical out-of-sample relative loss is more reliable than variance in high-dimensional portfolios.

Study finds traditional technical indicators underperform in high-frequency trading, suggesting risk management over prediction.

problem Inadequately explored effectiveness of technical indicators in high-frequency trading, particularly at minute-level frequency.
method Evaluation of random forest models with traditional technical indicators on minute-level SPY data.
result In-sample performance is superior to out-of-sample, with risk-adjusted metrics not outperforming a simple buy-and-hold strategy.

Study sets a nontrivial upper limit on return forecasting accuracy.

problem Establishing a practical upper limit for return forecasting accuracy.
method Defined a coin-flip oracle model to theoretically outperform practical models and used its RextOOS2R^2_{ ext{OOS}} as an upper bound.
result Theoretical upper bound on RextOOS2R^2_{ ext{OOS}} is a quadratic function of directional accuracy.

Study integrates machine learning with SAA for optimizing decisions based on uncertain parameters and covariates.

problem Optimizing decisions under uncertain parameters and covariates.
method Data-driven frameworks integrating machine learning prediction models within SAA for scenario generation.
result Consistent and asymptotically optimal solutions under certain conditions, with finite sample guarantees.

The paper predicts responses on out-of-sample nodes using latent positions on unknown curves.

problem Predicting responses on out-of-sample nodes with latent positions on unknown curves.
method Manifold learning and graph embedding technique using latent positions.
result Convergence guarantees for predicting responses on out-of-sample nodes.

New insights into ridge regression with correlated data, improving risk prediction.

problem Understanding and predicting risk in ridge regression with correlated samples.
method Random matrix theory and free probability for asymptotic analysis; modified GCV estimator (CorrGCV) for unbiased prediction.
result GCV estimator fails for out-of-sample risk with correlated data; CorrGCV provides an unbiased estimator.

We consider the problem of vertex classification for graphs constructed from the latent position model. It was shown previously that the approach of embedding the graphs into some Euclidean space followed by classification in that space can yields a universally consistent vertex classifier. However, a major technical d…

2013-05-21abs ↗pdf ↗

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.