New model predicts stock volume patterns.
problem Predicting high frequency stock volume dynamics.
method Semi-Markov chain model for intraday volume changes.
result Model accurately reproduces volume evolution patterns.
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.
169,341 papers · 148 categories
Trend · papers per month
48 results for “financial volumes”
Discovering material information using hierarchical Reformer model on financial regulatory filingsq-fin.ST
Model predicts trade volume changes from financial filings.
problem Improving financial market understanding through machine learning.
method Hierarchical Reformer model trained on SEDAR filings.
result Model can predict trade volume changes without explicit training.
Study shows how liquidity and trading volume affect price spread in financial markets.
problem Understanding and optimizing price spread in financial markets.
method Analyzes the interplay between order liquidity and order impact, connects spread to microstructural parameters.
result Additional liquidity improves price accuracy and reduces spread up to a certain point, after which it deteriorates.
New model explains price, volume, and waiting times in financial markets.
problem Understanding price, volume, and waiting times in financial markets.
method Generalized semi-Markov chains with endogenous index process and copulae for dependence.
result Model accurately reproduces empirical evidence from Italian stock market data.
Modeling trading volume curves using hierarchical Poisson processes.
problem Predicting trading volume curves for financial instruments.
method Hierarchical Poisson process model based on hierarchical Dirichlet process with MCMC algorithm.
result Demonstrated scalability on NASDAQ stocks, including Apple.
Study proposes a new financial market representation for machine learning.
problem Complex analysis of financial time series for machine learning.
method Volume-price-based statistical approach.
result Proposed method outperforms price levels-based method on liquid markets.
Financial market prediction on the basis of online sentiment tracking has drawn a lot of attention recently. However, most results in this emerging domain rely on a unique, particular combination of data sets and sentiment tracking tools. This makes it difficult to disambiguate measurement and instrument effects from f…
Study shows significant changes in trading volume and volatility patterns after 2008 financial crisis.
problem Non-stationary intraday statistical properties of trading volume and volatility.
method Analysis of blue chip equities trading volume and volatility over 2003-2014, split into semesters.
result Trading volume and volatility patterns changed significantly after 2008, with faster morning recovery and steeper afternoon.
Model non-stationary financial data using log-normal distributions and Langevin equations.
problem Modeling non-stationary volume-price distributions in finance.
method Model non-stationary volume-price distributions with a log-normal distribution. Derive Langevin equations from the series of log-normal parameters.
result Reconstructed statistics of volume-price distributions fit well empirical data.
The importance of considering the volumes to analyze stock prices movements can be considered as a well-accepted practice in the financial area. However, when we look at the scientific production in this field, we still cannot find a unified model that includes volume and price variations for stock assessment purposes.…
We compute volumes of complex convex shapes to predict financial crises.
problem Detecting financial crises by analyzing portfolio dependencies.
method Exact and approximate algorithms for volume computation of specific convex bodies.
result Practical algorithms can accurately predict financial crises.
Paper uses Transformers to predict intraday volume ratio with high accuracy.
problem Accurate prediction of intraday volume ratio for VWAP strategies.
method Transformer architecture with log-normal transformation and external features.
result Probabilistic forecasting captures mean and standard deviation of volume ratios.
LSTM predicts CSI300 volatility using search volume data.
problem Accurate prediction of financial market volatility.
method Long Short-Term Memory (LSTM) neural network applied to Baidu search volume data.
result LSTM outperforms GARCH model in CSI300 volatility forecasting.
Novel IMEX scheme solves financial PDEs with mixed derivatives.
problem Numerical approximations for financial PDEs with mixed derivatives.
method Second order finite volume IMEX Runge-Kutta scheme.
result Achieves true second order convergence with non-regular initial conditions.
In order to use the advanced inference techniques available for Ising models, we transform complex data (real vectors) into binary strings, by local averaging and thresholding. This transformation introduces parameters, which must be varied to characterize the behaviour of the system. The approach is illustrated on fin…
Study of volume dynamics at market spread in Bitcoin/USD.
problem Understanding the statistical properties of order volumes in financial markets.
method Examined the dynamical properties of volume available at the spread, focusing on mean reversion, asymmetry, and clustering.
result Evidence of mean reverting volume changes and strong asymmetries in sell and buy orders.
A dynamic herding model with interactions of trading volumes is introduced. At time , an agent trades with a probability, which depends on the ratio of the total trading volume at time to its own trading volume at its last trade. The price return is determined by the volume imbalance and number of trades. The …
On the distribution of high-frequency stock market traded volume: a dynamical scenariocond-mat.stat-mech
This manuscript reports a stochastic dynamical scenario whose associated stationary probability density function is exactly a previously proposed one to adjust high-frequency traded volume distributions. This dynamical conjecture, physically connected to superstatiscs, which is intimately related with the current nonex…
Modelling share volume traded in financial marketscond-mat.stat-mech
A simple analytically solvable model exhibiting a 1/f spectrum in an arbitrarily wide frequency range was recently proposed by Kaulakys and Meskauskas (KM). Signals consisting of a sequence of pulses show that inherent origin of the 1/f noise is Brownian fluctuations of the average intervent time between subsequent pul…
In this pre-print we explore the multi-fractal properties of 1 minute traded volume of the equities which compose the Dow Jones 30. We also evaluate the weights of linear and non-linear dependences in the multi-fractal structure of the observable. Our results show that the multi-fractal nature of traded volume comes es…
We study the daily trading volume volatility of 17,197 stocks in the U.S. stock markets during the period 1989--2008 and analyze the time return intervals between volume volatilities above a given threshold q. For different thresholds q, the probability density function P_q(τ) scales with mean interval <τ> as P_q(τ…
TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactionsq-fin.TR
TraderTalk uses LLMs to simulate human trading interactions in financial markets.
problem Simulating realistic human trading interactions in financial markets.
method Hybrid ABM with LLM-generated behaviors for detailed conversations.
result Successfully replicates trade-to-order volume ratios in financial markets.
Solves the challenge of retrieving item-specific financial information from Form 10-Q filings.
problem Retrieving item-specific information from Form 10-Q filings with varying formats and machine-readable hierarchy.
method Complements a rule-based algorithm with a Convolutional Neural Network (CNN) image classifier to itemize 10-Q files.
result Demonstrates a generalized pipeline for rapid data retrieval from a large volume of textual data.
Graph-based multi-view model predicts trading volume movement from various sources.
problem Lack of comprehensive understanding of trading volume movement from different sources.
method Graph-based approach incorporating long-term, short-term, and sudden event information.
result Our method outperforms strong baselines by a large margin.
Volume of the steady-state space of financial flows in a monetary stock-flow-consistent modelphysics.soc-ph
The volume of steady-state solutions in economic models is studied.
problem Understanding the fragility of economic circuits.
method Represented as a CSP, volume computed using operations research and metabolic network methods.
result Volume depends on constraints and reveals potential economic fragility.
Modeling price-mediated contagion in financial systems with capital requirements.
problem Understanding and quantifying the cost of capital requirements on financial stability.
method Developed a two-tier pricing structure and conditions for clearing prices, providing sensitivity analysis.
result Quantified the cost of regulation and value of bailouts in financial systems.
Study proposes deep learning for VWAP execution in crypto markets, outperforming traditional methods.
problem Challenges in achieving VWAP due to dynamic volume and price factors.
method Direct optimization of VWAP execution using deep learning, bypassing volume curve prediction.
result Deep learning approach consistently achieves lower VWAP slippage in volatile markets.
We live in a computerized and networked society where many of our actions leave a digital trace and affect other people's actions. This has lead to the emergence of a new data-driven research field: mathematical methods of computer science, statistical physics and sociometry provide insights on a wide range of discipli…
This is the third installment of the Financial Bubble Experiment. Here we provide the digital fingerprint of an electronic document in which we identify 27 bubbles in 27 different global assets; for 25 of these assets, we present windows of dates of the most likely ending time of each bubble. We will provide that docum…
Survey on nonlinear parabolic equations in finance.
problem Nonlinear extensions of the Black-Scholes theory.
method Qualitative and numerical analysis of nonlinear parabolic equations.
result Existence and uniqueness of solutions to nonlinear parabolic equations.
Trading large volumes of a financial asset in order driven markets requires the use of algorithmic execution dividing the volume in many transactions in order to minimize costs due to market impact. A proper design of an optimal execution strategy strongly depends on a careful modeling of market impact, i.e. how the pr…
This is the second installment of the Financial Bubble Experiment. Here we provide the digital fingerprint of an electronic document in which we identify 7 bubbles in 7 different global assets; for 4 of these assets, we present windows of dates of the most likely ending time of each bubble. We will provide that documen…
We introduce a new model in order to describe the fluctuation of tick-by-tick financial time series. Our model, based on marked point process, allows us to incorporate in a unique process the duration of the transaction and the corresponding volume of orders. The model is motivated by the fact that the "excitation" of …
Model predicts daily closing price distributions in call auctions.
problem Predicting price distributions in financial markets.
method Modeling price formation in call auctions with random orders and equilibrium equation.
result Model accurately predicts daily closing price distributions for financial indices.
CNN model predicts financial market movement with better performance.
problem Difficult to predict financial markets due to complex dynamics.
method Proposes a novel one-dimensional CNN model for financial market prediction.
result CNN model achieves more robust and profitable performance than previous approaches.
Paper optimizes a big data and ML risk monitoring system for financial markets.
problem Traditional risk monitoring methods are inadequate for modern financial markets due to data complexity and volume.
method Four-layer architecture integrating big data and advanced ML algorithms (LSTM, RF, GB).
result Significantly enhances efficiency and accuracy in risk management, especially in market crash risk detection.
LLMs improve financial analysis by processing large data sets.
problem Traditional financial analysis methods struggle with large data volumes.
method Integrating LLMs for enhanced data processing and analysis.
result LLMs offer new capabilities for real-time financial decision-making.
The paper models liquidity in financial markets with a continuous fundamental price.
problem Liquidity and price formation in financial markets with discrete order books.
method Adapting Madhavan et al. (1997) model to realistic order books with quote discretization and liquidity rebates.
result The fundamental price is continuous, efficient, and outside the quote interval, and can be estimated from volume imbalance.
The study examines how personal financial experiences shape investor behavior and market dynamics.
problem How do personal financial experiences affect investor behavior and market dynamics?
method Formalized experience-based learning in an OLG model, generating heterogeneity in beliefs, portfolio choices, and trade.
result The model produces new implications for asset holdings, trade volume, and investors' responses to financial crises.
Study reveals optimal price prediction through volume imbalance analysis.
problem Understanding the relationship between prices and volume imbalance in high-frequency trading.
method Developed a market-making model to analyze price-imbalance connection and solve optimization problems.
result Optimal quoting of predictive imbalance is confirmed, useful for financial regulation.
Study integrates deep learning with financial data for improved trading strategies.
problem Enhancing predictive performance in algorithmic trading and portfolio optimization.
method Developed embedding techniques to treat limit order book snapshots as image-based input channels.
result Achieved state-of-the-art performance in high-frequency trading algorithms.
Multivariate Hawkes processes analyze order dynamics in financial markets.
problem Complex interactions between order timing and size in financial markets.
method Multivariate Hawkes processes with nonparametric estimation.
result Simple volume-time independence models are inadequate for financial data.
Article explains why gambling is crucial for market efficiency.
problem Inefficiency of traditional market theories.
method Introduces gambling theory as a superior approach.
result Gambling theory can reveal profitable trading systems.
The observation of power laws in the time to extrema of volatility, volume and intertrade times, from milliseconds to years, are shown to result straightforwardly from the selection of biased statistical subsets of realizations in otherwise featureless processes such as random walks. The bias stems from the selection o…
In this article we study the dependence degree of the traded volume of the Dow Jones 30 constituent equities by using a nonextensive generalised form of the Kullback-Leibler information measure. Our results show a slow decay of the dependence degree as a function of the lag. This feature is compatible with the existenc…
This paper analyzes text in financial disclosures to improve financial analysis.
problem Insufficient analysis of unstructured text in financial disclosures.
method Reviews and explores methods in computational linguistics and NLP.
result Highlights limitations of sentiment metrics and suggests future research areas.
Employing a recent technique which allows the representation of nonstationary data by means of a juxtaposition of locally stationary patches of different length, we introduce a comprehensive analysis of the key observables in a financial market: the trading volume and the price fluctuations. From the segmentation proce…
Generates financial time series with stylized facts using diffusion models.
problem Generating realistic synthetic financial time series with statistical properties like fat tails, volatility clustering, and seasonality.
method Utilizes denoising diffusion probabilistic models (DDPMs) with wavelet transformation to convert and generate financial time series.
result Demonstrates that the proposed approach satisfies stylized financial time series properties.