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.

168,695 papers · 148 categories

Trend · papers per month

62123185246 · May 202619922001200920172026
48 results for financial direction

Study uses VC correlation to uncover directional financial relationships.

problem Understanding causal relationships between financial variables.
method Volatility constrained correlation (VC correlation) method.
result Operating income is most influential, while market capitalization and revenue are most susceptible.

LLMs outperform human analysts in predicting earnings direction.

problem Evaluating financial statements without narrative or industry-specific information.
method Trained GPT4 on standardized, anonymous financial statements and instructed to predict earnings direction.
result LLMs predict earnings directionally with accuracy comparable to narrowly trained ML models.

Study uses MTD model to optimize portfolios by capturing complex financial asset relationships.

problem Capturing nonlinear and directional relationships in financial markets.
method Directed and weighted financial networks using Mixture Transition Distribution (MTD) model.
result Portfolio optimization with network-based assortativity measures outperforms classical methods.

We propose a new Directed Continuous-Time Random Walk (CTRW) model with memory. As CTRW trajectory consists of spatial jumps preceded by waiting times, in Directed CTRW, we consider the case with only positive spatial jumps. Moreover, we consider the memory in the model as each spatial jump depends on the previous one.…

2018-07-05abs ↗pdf ↗

Unified framework predicts S&P500 index direction using transfer learning and causal graph.

problem Predicting the movement of financial indices like S&P500.
method Transfer learning, causal graph, multidisciplinary knowledge, VAE network.
result 74.3% accuracy, 67% F1-score, 0.42 Matthew correlation on 12 years test period.

Multifractality is ubiquitously observed in complex natural and socioeconomic systems. Multifractal analysis provides powerful tools to understand the complex nonlinear nature of time series in diverse fields. Inspired by its striking analogy with hydrodynamic turbulence, from which the idea of multifractality originat…

2018-05-12abs ↗pdf ↗

Model predicts Bitcoin's future movements using multimodal pattern matching.

problem Challenges in predicting Bitcoin's volatile future movements.
method Ranking similar past chart patterns given current chart information.
result Improves directional prediction of Bitcoin's future movements.

Unified framework maps financial market dynamics using TE and KM, revealing directional information flow.

problem Challenges in traditional correlation analysis of financial markets, especially during crises.
method Combines Transfer Entropy (TE) and Kramers-Moyal (KM) expansion to analyze dynamic interactions among major indices.
result Increased directional information flow during crises, highlighting gold-dollar and oil-equity linkages.

The paper models financial order books using geometric shears and directional liquidity.

problem Understanding the geometry and dynamics of financial order books.
method Structural framework modeling liquidity as emergent observables, geometric shears, and directional imbalances.
result The geometry of financial order books can be described by a rigid drift and geometric shear, leading to a gamma-like profile of projected liquidity.

CSHT predicts financial returns from news using a novel transformer model on a sphere.

problem Financial forecasting from news and sentiment.
method Granger-causal hypergraph structure, Riemannian geometry, causally masked Transformer attention.
result CSHT outperforms baselines in return prediction, regime classification, and asset ranking.

Uses news sentiment scores for direct reinforcement trading in financial markets.

problem Incorporating news data into quantitative trading remains challenging.
method Directly uses news sentiment scores and raw data as inputs for reinforcement learning, processed by sequence models.
result Achieves superior performance compared to market benchmarks.

We detect and quantify asymmetries in volatility spillovers using the realized semivariances of petroleum commodities: crude oil, gasoline, and heating oil. During the 1987--2014 period we document increasing spillovers from volatility among petroleum commodities that substantially change after the 2008 financial crisi…

2014-05-10abs ↗pdf ↗

Study explores financial market linkages between Japan and US markets.

problem Inconsistency in empirical studies regarding financial market causal linkages.
method Causal discovery methods including VAR-LiNGAM and LPCMCI with domain knowledge.
result VAR-LiNGAM reveals causal influences among financial markets, while LPCMCI identifies potential latent confounders.

We show that any objective risk measurement algorithm mandated by central banks for regulated financial entities will result in more risk being taken on by those financial entities than would otherwise be the case. Furthermore, the risks taken on by the regulated financial entities are far more systemically concentrate…

2010-04-10abs ↗pdf ↗

CMTF improves financial market forecasting by fusing multiple data types.

problem Lack of effective integration of diverse financial data sources.
method Transformer-based deep learning framework with tensor interpretation and auto-training.
result CMTF outperforms classical and deep learning models in price direction classification.

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.

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.

The paper introduces a new method for detecting financial data outliers.

problem Detecting outliers in multivariate financial data.
method The approach uses the Cumulant Generating Function (CGF) to maximize projections on directions.
result The CGF maximization approach can be interpreted as an extension of principal component analysis.

Modeling financial contagion through bank networks, revealing solvency correlations.

problem Understanding how financial shocks propagate through interconnected banks.
method Simulated financial network of 100 banks, randomly generated with varying link probabilities, and shocks applied to 15 banks.
result Ranges of probability values and banks' solvency are positively correlated.

Geopolitical and geoeconomic shocks affect sovereign risk differently, with distinct transmission channels.

problem Understanding how geopolitical and geoeconomic shocks impact sovereign credit risk.
method Daily panel data of 42 economies over 2018-2025; semistructural framework; Shapley-Taylor decomposition; machine learning predictions; placebo and sign-restricted SVAR evidence.
result Geopolitical shocks primarily increase sovereign credit spreads through direct repricing, while geoeconomic shocks mainly affect spreads through financial conditions and policy uncertainty.

This study compares two neural models for financial forecasting, showing their superiority.

problem Improving financial market trend predictions using neural networks.
method Systematic comparison of N-HiTS and N-BEATS with conventional models.
result N-HiTS and N-BEATS enhance forecast accuracy and robustness in financial time series data.

Study compares nine deep learning architectures for multi-horizon financial forecasting.

problem Evaluating the performance of deep learning architectures for multi-horizon financial forecasting.
method Conducted 918 experiments across cryptocurrency, forex, and equity markets using nine architectures.
result ModernTCN achieves the best mean rank (1.333) with a 75 percent first-place rate.

FinDPO uses preference optimization to improve financial sentiment analysis models.

problem Financial sentiment analysis models often fail to generalize to unseen data.
method FinDPO uses Direct Preference Optimization (DPO) to align LLMs with human preferences.
result FinDPO achieves state-of-the-art performance and maintains positive returns under realistic trading conditions.

This paper reviews transfer learning for financial data predictions, highlighting its potential.

problem Accurate stock price prediction in financial time series is challenging due to noise and non-linear relationships.
method Transfer Learning applied to financial market predictions.
result Transfer Learning can improve financial prediction capability.