The paper predicts stock trends from news headlines using NLP.
problem Predicting stock trends from news headlines.
method Statistical and deep learning models with NLP techniques.
result Improved accuracy in predicting DJIA trends.
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 “news trends”
Study detects emerging trends in financial news articles about Microsoft.
problem Challenges in identifying trends in long-form financial news articles.
method Topic modeling and term frequency for keyword similarity analysis.
result Demonstrates the influence of the pandemic on Microsoft.
Two new plots confirm trend following and risk premia findings.
problem Confirming trend following and risk premia strategies over new data.
method Presenting two additional plots to corroborate findings.
result New data fully corroborates trend following and risk premia findings.
X-Trend quickly adapts to new financial regimes, increasing Sharpe ratio by 18.9%.
problem Adapting to rapidly changing financial market conditions.
method Few-shot learning and cross-attention mechanism.
result X-Trend increases Sharpe ratio by 18.9% over a neural forecaster and 10-fold over a conventional strategy.
Two new methods improve time series analysis by capturing trend information.
problem Missing important information, especially trend, in high-dimensional time series.
method Two new approaches: 1) Relative mean value of each segment, 2) Binary string representing trend.
result Improves accuracy and effectiveness in similarity measurement and anomaly detection.
Power Assisted Trend Followingq-fin.TR
Develops a new trend power indicator using DSP techniques.
problem Determining the strength and reversibility of trends.
method Derives a novel indicator using digital signal processing.
result Accuracy of the new indicator correlates with PNL performance.
Paper uses financial news for stock trend forecasting using deep multiple instance learning.
problem Forecasting stock trends from financial news articles.
method Developed a flexible and adaptive multi-instance learning model for bags of instances (financial news articles) on trading days.
result Outstanding trend prediction accuracy compared to state-of-the-art approaches.
New insights into trend following strategies show strong convexity in CTA performance.
problem Explaining the positive convexity of CTA performance.
method Revisits trend following strategies and measures long-term and short-term realized variance.
result Shows strong convexity in CTA performance, stronger than anticipated.
Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreakscs.SI
Study uses news trends to predict infectious disease outbreaks.
problem Predicting infectious disease outbreaks using news reports.
method Supervised temporal topic models to transform news articles into trends.
result Temporal topic trends from disease news capture outbreak dynamics.
Enhanced trend-following strategy using network momentum for commodity futures.
problem Improving systematic trend-following in commodity futures markets.
method Combines univariate and cross-sectional trend indicators, including network momentum.
result Statistically significant improvements in portfolio performance metrics.
Much information available on the web is copied, reused or rephrased. The phenomenon that multiple web sources pick up certain information is often called trend. A central problem in the context of web data mining is to detect those web sources that are first to publish information which will give rise to a trend. We p…
Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Predictioncs.SI
Deep learning predicts stock trends from chaotic online news.
problem Predicting stock trends from volatile and non-stationary stock market data.
method Hybrid Attention Networks and self-paced learning mechanism.
result Demonstrated effectiveness in predicting stock trends from online news.
Study uncovers financial trends from cross-lingual news data.
problem Understanding financial dynamics across diverse global economies.
method Sentiment analysis, NER, and semantic textual similarity for news articles.
result Meaningful correlation between stock price movements and cross-linguistic news sentiments.
Google Trends data improves economic forecasts of private consumption.
problem Improving economic forecasts of private consumption.
method Machine learning techniques applied to categorized Google search data.
result Google data can identify patterns to generate a leading indicator in real time.
ST-GAN predicts stock trends using financial news and data.
problem Predicting financial trends in stock markets.
method ST-GAN combines NLP and technical indicators using GAN technology.
result Significant improvement over existing models in stock price forecasting.
The paper introduces a new method to identify trends in noisy signals efficiently.
problem Identifying unknown underlying trends in noisy signals, especially with abrupt changes and outliers.
method Developed the Adaptive Trend Filter and an enhanced coordinate descent algorithm.
result The method can consistently identify components in the underlying trend and multiple level-shifts.
Predict stock trends using news sentiment and technical indicators in Spark.
problem Predicting the stock market trend is challenging due to multiple influencing factors.
method Created a machine learning classification problem with features from technical indicators and news sentiment scores.
result Random Forest model achieved 63.58% test accuracy in Spark.
New framework adds trend information to Adam-type optimizers for faster convergence.
problem Efficiently optimizing complex cost surfaces in deep learning.
method Integrates trend information into Adam-type optimizers for adaptive step size and gradients.
result Framework outperforms conventional Adam and AMSGrad methods on various datasets.
New model estimates species population trends from citizen science data.
problem Interannual confounding in citizen science data.
method Double Machine Learning framework to estimate population change and propensity scores for confounding adjustment.
result Spatially detailed trend estimates from citizen science data with low error rates.
REST framework predicts stock trends by considering stock-specific and related-stock events.
problem Predicting stock trends using event information from news, social media, and discussion boards.
method REST framework addresses two main shortcomings of existing event-driven methods: stock-specific event influence and related-stock event influence.
result REST framework achieves higher investment returns compared to baselines.
Study found bias in drug effectiveness due to secular trend, adjusting for it was difficult.
problem Secular trend bias in drug effectiveness study.
method Built a machine learning causal inference model to identify subpopulations and adjust for bias using two methods.
result Bias remained even after adjusting for secular trend, suggesting other unmeasured factors.
Transformer model predicts stock trends using technical data and sentiment analysis.
problem Lack of accurate long-term stock trend prediction using traditional models.
method Developed a Transformer-based model integrating technical stock data and sentiment analysis.
result Transformer model shows significant improvement in directional accuracy over RNNs, especially for longer sequence lengths.
A new SOHP filter improves trend estimation in economic time series.
problem Improving trend estimation in nonlinear economic time series.
method Recursive application of one-sided HP filter on updated cyclical components, combined with an incremental HP filtering algorithm.
result Better performance of SOHP filter compared to other HP-type filters on real economic data.
Volatility conditional on price trendscond-mat.other
The influence of the past price behaviour on the realized volatility is investigated in the present article. The results show that trending (drifting) prices lead to increased (decreased) realized volatility. This ``volatility induced by trend'' constitutes a new stylized fact. The past price behaviour is measured by a…
A new framework forecasts stock trends by mining shared information from concepts.
problem Forecasting stock trends using static concept information limits accuracy.
method Proposes a graph-based framework that mines concept-oriented shared information from both predefined and hidden concepts.
result Improves stock trend forecasting performance through dynamic concept relevance and hidden concept information.
Additive trend filtering uses discrete total variation to build piecewise polynomials.
problem Estimating functions with piecewise polynomial components.
method Trend filtering with localized total variation regularization.
result Additive trend filtering achieves optimal error rates and is computationally efficient.
We examine several recently suggested methods for the detection of long-range correlations in data series based on similar ideas as the well-established Detrended Fluctuation Analysis (DFA). In particular, we present a detailed comparison between the regular DFA and two recently suggested methods: the Centered Moving A…
We study trend filtering, a recently proposed tool of Kim et al. [SIAM Rev. 51 (2009) 339-360] for nonparametric regression. The trend filtering estimate is defined as the minimizer of a penalized least squares criterion, in which the penalty term sums the absolute th order discrete derivatives over the input points…
Forecast future volatilities and correlations based on current trends.
problem Predict future volatilities and correlations in financial markets.
method Use cubic and quadratic polynomials of current trend strengths.
result Accurate quantification of trend effects on volatilities and correlations.
Explains the difference between EMA and moving EMA, focusing on market trend indicators.
problem Understanding the difference between exponential moving average and moving exponential average.
method Explains the mathematical tools and definitions of trend indicators.
result Discusses the properties of the MACD indicator and its use in market trend analysis.
Bitcoin's attention is linked to Google Trends data, not general uncertainty.
problem Bitcoin's correlation with Google Trends data was previously misunderstood.
method Analyzed bidirectional relationships between Bitcoin returns and Google Trends attention over six days.
result Information flows from Bitcoin volatility to Google Trends attention, not the other way.
RobustTrend filters time series trends robustly against outliers and abrupt changes.
problem Extracting accurate trend signals from noisy, potentially abrupt-changing time series.
method Uses Huber loss for outlier suppression and a combination of first and second order differences for regularization.
result Our algorithm outperforms existing methods in synthetic and real-world datasets.
Study finds stock search trends correlate with developing economies' stock indices.
problem Predicting stock indices closing from web search trends.
method Collected and analyzed stock-specific internet search trends and corresponding index close values.
result Global search trends correlate more with developing economies, less with south Asian exchanges.
It is hypothesized that price charts can be empirically decomposed into two components as random and non random. The non random component, which can be treated as approximately regular behavior of the prices (trend) in an epoch, is a geometric line. Thus, the random component fluctuates around the non random component …
A new method for joint noise removal and trend estimation from sparse signals.
problem Jointly removing noise and estimating trends from sparse signals.
method PENDANTSS combines SOOT/SPOQ penalties with BEADS algorithm in a Trust-Region block alternating variable metric forward-backward approach.
result Outperforms comparable methods in deconvolving analytical chemistry signals.
Study shows RNNs are effective for trend detection in time series.
problem Detecting trends in noisy time series data.
method Empirical investigation of standard RNNs for trend detection using simulated data.
result Standard RNNs structures outperform other estimators in trend detection.
This study improves user segmentation for online news recommendation systems.
problem Challenges in building modern recommender systems due to dynamic environments and data sparsity.
method Trend-responsive unsupervised user segmentation using multi-armed bandits.
result Significant improvements in online A/B tests compared to global-optimization algorithms.
Deep neural nets predict stock market trend changes using lagged correlations.
problem Predicting directional trend changes in financial time series with noisy data.
method Lagged correlations and deep neural networks with step-wise linear regressions and exponential smoothing.
result Deep learning approach achieves state-of-the-art accuracy in predicting stock market trend changes.
The study examines how polynomial trends affect DMA methods for nonstationary time series.
problem Effects of polynomial trends on detrending moving average analysis.
method Investigation of three DMA methods (BDMA, CDMA, FDMA) under various polynomial trends.
result CDMA method outperforms BDMA and FDMA in the presence of polynomial trends.
Re-evaluating Short- and Long-Term Trend Factors in CTA Replication: A Bayesian Graphical Approachcs.AI
This paper uses Bayesian models to analyze CTA returns across short and long-term trends.
problem The relative merits and interactions of short- and long-term trend systems in CTA replication remain controversial.
method Dynamic decomposition of CTA returns into short-term trend, long-term trend, and market beta factors using a Bayesian graphical model.
result The blend of horizons shapes the strategy's risk-adjusted performance.
New string and D2-brane models improve financial market trend forecasting.
problem Improving time series forecasting for financial markets.
method Introducing string and D2-brane models to analyze currency rates and their stability.
result New models enhance the accuracy of time series forecasting for currency exchange pairs.
Paper uses AI to predict market trends better than traditional methods.
problem Traditional trend following and momentum investing are limited.
method Uses deep learning and AI techniques for market trend prediction.
result Improves asset manager performance by increasing returns and reducing drawdowns.
Develops algorithms to estimate trends in global temperature variability.
problem Estimating trends in cloud reflectance temperature variability.
method Two novel algorithms for dense, gridded observations over space and time.
result Evaluation of methods with simulated and real-world data.
STMT predicts compounds in unknown areas with trend reflection.
problem Predicting properties of unknown compounds in the extrapolation area.
method Stochastic Threshold Model Trees (STMT) that reflects data trends.
result STMT improves prediction accuracy for one compound in the extrapolation area.
Introduces a new theoretical framework for exponential smoothing.
problem Theoretical foundation and robustness of simple exponential smoothing.
method Stochastic gradient ascent to optimize Gaussian log-likelihood functions.
result Simple exponential smoothing converges to the trend of a trend-stationary process.
Ethereum trends analyzed through blockchain transactions and Google searches.
problem Identifying market manipulation in crypto prices.
method Big data analysis of Ethereum transactions, smart contracts, and search volumes.
result Big players manipulate crypto markets after price drops.
Paper optimizes trend-following portfolios using autocorrelation models.
problem Developing an optimal trend-following portfolio strategy.
method Introduces a unifying theoretical setting with autocorrelation models for covariance matrices of trends and risk premia. Specifies practical models for covariance matrices. Decomposes optimal portfolio into four basic components.
result Empirical backtests confirm overperformance of the proposed optimal portfolio.
Deep learning models struggle with new data in stock price trend prediction.
problem Stock price trend prediction using Deep Learning models.
method Examination of fifteen state-of-the-art DL models on LOB data, using LOBCAST framework.
result All models show significant performance drop with new data, questioning their market applicability.