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

1122 · Jun 202019922001200920172026
26 results for 4H timeframe

Understanding how funding and 4H context regulate crypto markets.

problem Analyzing the chaotic appearance of financial markets.
method Observing interactions between market context and capital conditions in the 4H timeframe.
result Ranges in crypto markets are strategic positioning by informed participants, not indecision.

Neural nets analyze crypto markets for multi-timeframe trading.

problem High-frequency trading in cryptocurrency markets.
method Multi-timeframe trend analysis and high-frequency direction prediction networks.
result Positive risk-adjusted returns through machine learning.

We prove that any complete surface with constant mean curvature in a homogeneous space E(κ,τ) which is transversal to the vertical Killing vector field is, in fact, a vertical graph. As a consequence we get that any orientable, parabolic, complete, immersed surface with constant mean curvature H in E(κ,τ) (different fr…

2012-06-07abs ↗pdf ↗

Researchers develop optimal methods to estimate rough volatility parameters.

problem Statistical inference for rough volatility models with fractional Brownian motion.
method Established minimax lower bounds and designed wavelet-based procedures.
result Optimal speed of convergence n1/(4H+2)n^{-1/(4H+2)} for estimating HH.

We compute the eta function η(s)η(s) and its corresponding ηη-invariant for the Atiyah-Patodi-Singer operator D\mathcal{D} acting on an orientable compact flat manifold of dimension n=4h1n =4h-1, h1h\ge 1, and holonomy group FZ2rF\simeq \mathbb{Z}_{2^r}, rNr\in \mathbb{N}. We show that η(s)η(s) is a simple entire function tim…

2014-07-28abs ↗pdf ↗

For each k2k\geq2, we construct two families of surfaces with constant mean curvature HH for H[0,1/2]H\in[0,1/2] in Σ(κ)×RΣ(κ)\times\R where κ+4H20κ+4H^2\leq0. The surfaces are invariant under 2π/k2π/k-rotations about a vertical fiber of Σ(κ)×RΣ(κ)\times\R, have genus zero, and a finite number of ends. The first family generalizes the no…

2013-06-02abs ↗pdf ↗

LLMs struggle to outperform markets over long periods and diverse stocks.

problem Overstated effectiveness of LLM-based investing strategies due to biases.
method FINSABER framework for systematic backtests over two decades and 100+ symbols.
result Previously reported LLM advantages deteriorate significantly under broader evaluation.

This paper proposes a multi-scale Markov-Switching GARCH model for EUR/USD volatility.

problem Non-stationary financial volatility requires models that capture changing market conditions across multiple timescales.
method Triple-timeframe Markov-Switching GARCH (MS-GARCH) framework with AR(1)-MS-GARCH models and TVTP for short horizons.
result The proposed model produces statistically distinct regimes and superior volatility forecasting performance.

This thesis builds a real-time VaR calculation workflow for crypto derivatives.

problem Managing risk in volatile cryptocurrency markets.
method Applied EMWA, GARCH, and HAR models to forecast volatility; used delta-gamma-theta approach and Cornish-Fisher expansion.
result Real-time VaR estimates with millisecond calculation latencies.

Novel algorithm identifies nonlinear Granger causal relationships using kernel ridge regression.

problem Identification of nonlinear Granger causal relationships.
method Flexible plug-in architecture with kernel ridge regression using radial basis function.
result Kernel ridge regression in mlcausality achieves competitive AUC scores and more finely calibrated p-values.

Bayesian nonparametric model predicts user activity and intervention success.

problem Predicting user activity and intervention success in online experiments.
method Bayesian nonparametric approach to model user heterogeneity and derive user activity predictions.
result The proposed method outperforms existing approaches in predicting user activity and intervention success.

Study improves cryptocurrency price prediction using neural networks and technical indicators.

problem Improving cryptocurrency price prediction accuracy.
method Integrates technical indicators, Transformer neural network, and BiLSTM.
result Demonstrates superior performance in predicting cryptocurrency prices.

Study predicts cryptocurrency price movements using Twitter sentiment analysis.

problem Predicting short-term price movements of cryptocurrencies.
method Conditional examination of return and excess return rates following tweet publication.
result Statistically significant increases in return rates within the first three minutes after tweet publication.

Study para-CR structures in 5D with degenerate Levi form, revealing geometric conditions for conic graphs and Lorentzian ODEs.

problem Investigate invariant properties of para-CR structures in 5D with degenerate Levi form.
method Analyze basic invariants and their vanishing conditions to establish geometric interpretations and necessary conditions.
result Vanishing of the third basic invariant N(G,H)0N(G,H) \equiv 0 implies contact projective geometries on quotient spaces.

This paper uses LLMs to improve equity stock ratings by ingesting diverse financial and news data.

problem Challenges in traditional stock rating methods, including data overload, inconsistencies, and delayed reactions.
method Application of LLMs to generate multi-horizon stock ratings using various datasets.
result LLMs enhance the accuracy and consistency of stock ratings, outperforming traditional methods in forward returns.

During the last two years, Europe has been facing a debt crisis, and Greece has been at its center. In response to the crisis, drastic actions have been taken, including the halving of Greek debt. Policy makers acted because interest rates for sovereign debt increased dramatically. High interest rates imply that defaul…

2012-09-27abs ↗pdf ↗

Deep learning predicts fluid flow in porous media, accelerating simulations by orders of magnitude.

problem Accurate simulation of fluid flow in complex porous media requires excessive computational resources.
method Combining deep learning with direct simulation, using Gated U-Net CNNs trained on datasets of 2D and 3D porous media.
result Deep learning predictions can reach over 90% accuracy for permeability estimation and accelerate simulations by orders of magnitude.