Paper improves volatility forecasting for new issues and spin-offs.
problem Forecasting volatility with limited historical data.
method Multi-source transfer learning approach.
result Transfer learning approach outperforms alternative models.
New tool helps analyze complex financial data.
problem Difficulty in comprehending high-dimensional financial data.
method Topological Data Analysis Ball Mapper algorithm.
result Shows new way to see detail in financial data.
New geometric methods improve optimization and data science problems.
problem Improving optimization and data science problems.
method Geometric tools for high-dimensional optimization and statistical data science.
result New algorithms and statistical guarantees for optimization and data science.
When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Con…
New method estimates root-directed tree from extreme data.
problem Discovering causality in river networks from extreme flow data.
method Qualitative max-linear Bayesian network approach to estimate bivariate scores and root-directed spanning tree.
result The new estimator is consistent under max-linear Bayesian network model with noise.
New trees-based models handle correlated data better.
problem Standard trees-based models ignore correlation structure.
method Explicitly accounts for correlation structure in splitting criterion, stopping rules, and fitted values.
result New approach superior to standard models in simulations and real data.
Improved stock price prediction using attention modules and news sentiment.
problem Predicting stock prices with non-stationary and non-parametric data.
method α_{t}-RIM architecture with attention modules and exponentially smoothed recurrent neural network.
result The αt-RIM outperforms state-of-the-art models in predicting unseen data. New algorithm combines new and historical data with different input dimensions for linear regression.
problem Combining new and historical data with different input dimensions for improved accuracy.
method Proposes a transfer learning algorithm with rigorous theoretical robustness analysis.
result Achieves state-of-the-art performance on 9 real-life datasets.
A new method for projecting multimodal data to a common subspace for one-class classification.
problem Classifying data from multiple sources with varying features.
method Iterative transformation to a common subspace, separate transformations for each modality, regularization strategies.
result Outperforms competing methods across multiple datasets.
New methods distill data for deep networks efficiently.
problem Reduction of training data cost and inconvenience.
method Generative teaching networks, gradient matching, Implicit Function Theorem.
result New methods are computationally more efficient and improve model performance.
A new, fast kernel test for large data.
problem Efficient kernel two-sample tests for high-dimensional, large-scale data.
method A new kernel-based test that is computationally efficient and robust to high dimensions.
result The new test performs well across various alternatives and dimensions.
New method rebalances evolving data streams incrementally.
problem Incremental rebalancing of evolving data streams.
method Proposes a new streaming approach for rebalancing data streams online.
result Outperforms existing approaches in rebalancing data streams.
Symbolic data analysis (SDA) is an emerging area of statistics concerned with understanding and modelling data that takes distributional form (i.e. symbols), such as random lists, intervals and histograms. It was developed under the premise that the statistical unit of interest is the symbol, and that inference is requ…
We propose a new class of metrics on sets, vectors, and functions that can be used in various stages of data mining, including exploratory data analysis, learning, and result interpretation. These new distance functions unify and generalize some of the popular metrics, such as the Jaccard and bag distances on sets, Man…
In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model and the new data to improve performance. However, deep neural networks are prone t…
A new sampling method balances imbalanced data using gamma distribution.
problem Imbalanced class distribution in data causes bias in classification algorithms.
method Intelligent resampling of minority class instances via gamma distribution.
result The proposed method outperforms existing techniques on 12 out of 24 datasets.
A new framework predicts stock movements using news sentiment and relational data.
problem Predicting stock prices from textual information is challenging due to market uncertainty and natural language complexity.
method Multi-Graph Recurrent Network (MGRN) combining textual sentiment from financial news and relational data.
result The model outperforms benchmarks in predicting stock movements.
Paper uses news data to model asset correlations without market data.
problem Traditional risk models rely on market data; this paper offers an alternative.
method Uses encoder-only language models to embed news data, then calculates asset return distributions and covariance through Energy Distance.
result Established connections between distributional differences and excess returns co-movements using Energy Distance.
A new method converts neural networks to function space for scalable sequential learning.
problem Challenges in gradient-based deep learning for sequential data.
method Dual parameterization of neural networks from weight to function space.
result Efficient scaling, knowledge retention, and new data incorporation.
FININ predicts financial markets by modeling news interactions and influence.
problem Complex diffusion of financial news into market prices.
method FININ is a novel model that captures news links and interactions, integrating market data and news articles.
result FININ outperforms advanced models with a 0.429 and 0.341 improvement in daily Sharpe ratio for S&P 500 and NASDAQ 100 respectively.
Paper explores different models for fake news detection.
problem Detecting fake news with various models.
method Used machine learning algorithms and pretrained features like TFIDF, CV, and W2V.
result Developed models for better fake news detection.
New gait segmentation method identifies users and adversaries with high accuracy.
problem Simultaneous identification of users and adversaries from accelerometer data.
method Geometric features and a new similarity metric for time series analysis.
result 98.79% accuracy for 6 classes (user-adversary identification) and 99.06% for binary (user only identification).
In spite of remarkable success of the convolutional neural networks on semantic segmentation, they suffer from catastrophic forgetting: a significant performance drop for the already learned classes when new classes are added on the data, having no annotations for the old classes. We propose an incremental learning met…
Enhances LLMs for predicting stock movements by considering news dissemination and context.
problem Lack of consideration for news dissemination and insufficient contextual data in LLMs for stock price prediction.
method Clusters news for reach assessment, enriches prompts with specific data and instructions, fine-tunes an LLM using the dataset.
result Improves prediction accuracy by 8% compared to existing methods.
New method constructs flat initial data for Einstein's equations.
problem Constructing asymptotically flat initial data for Einstein's equations.
method Explicit solution operators with localization properties.
result Improved decay rate and nontrivial initial data construction.
A new method for real-time anomaly detection in flight data.
problem Challenges in clustering dynamically growing flight data for anomaly detection.
method Incremental Gaussian Mixture Model (GMM) using EM algorithm.
result Significantly reduced processing time and memory usage compared to offline methods.
Machine learning finds new natural laws from noisy data.
problem Discovery of natural laws relies on human inspiration.
method Recursive-LASSO-based symbolic regression (RLS) method.
result Data-driven formulation of natural laws from noisy data.
Adaptive XGBoost improves accuracy on evolving data streams by updating the ensemble dynamically.
problem Concept drift in evolving data streams.
method Adapts XGB to update the ensemble with new data, maintaining consistency with current concept.
result Improves classification accuracy on evolving data streams compared to other methods.
Bayesian nonparametric model learns new categories without predefined limits.
problem Learning new categories unseen in labeled training data.
method Hierarchical Dirichlet process and latent Dirichlet allocation for automatic category inference.
result Nonparametric approach yields comparable performance to parametric methods with pre-specified new categories.
Generative algorithms learn high-dimensional data efficiently and generate new samples.
problem Learning from scarce high-dimensional data.
method Lipschitz-regularized gradient flows and particle-based algorithms.
result Correctly transports gene expression data points with high dimensionality.
Reweighting training data to better represent new tasks.
problem Deploying machine learning models to new tasks is challenging due to training data distribution.
method Formulate an exponential tilt distribution shift model and learn train data importance weights to minimize KL divergence.
result The learned train data weights improve target performance evaluation, fine-tuning, and model selection.
We consider classifiers for high-dimensional data under the strongly spiked eigenvalue (SSE) model. We first show that high-dimensional data often have the SSE model. We consider a distance-based classifier using eigenstructures for the SSE model. We apply the noise reduction methodology to estimation of the eigenvalue…
Online news media provides aggregated news and stories from different sources all over the world and up-to-date news coverage. The main goal of this study is to have a solution that considered as a homogeneous source for the news and to represent the news in a new conceptual framework. Furthermore, the user can easily …
Organizations adapt ML models to new data types using existing resources.
problem Adapting ML models to new data types in evolving applications.
method Utilize organizational resources like statistics, knowledge bases, and existing services to create a common feature space.
result Reduces model development time from months to days.
New method learns various data manipulation schemes for model training.
problem Improving model training with data manipulation.
method Adapts RL reward learning algorithm for data manipulation learning.
result Significant improvement in classification performance.
We propose an approach to reduce the bias of ridge regression and regularization kernel network. When applied to a single data set the new algorithms have comparable learning performance with the original ones. When applied to incremental learning with block wise streaming data the new algorithms are more efficient due…
Quantum analysis tags news for sentiment and entities.
problem Identifying bias in news reporting.
method Continuous data collection, NER and sentiment analysis.
result A corpus of tagged news articles for public use.
Normal-bundle bootstrap generates new data preserving geometric structure.
problem Probabilistic models often exhibit salient geometric structure.
method NBB method decomposes probability measure into manifold and normal spaces, estimates manifold as density ridge, and generates new data by bootstrapping projection vectors.
result NBB generates new data that preserves the geometric structure of a given data set.
Adversarial validation detects concept drift in user targeting systems.
problem Concept drift in user targeting automation systems deteriorates model performance over time.
method Adversarial validation approach to detect and adapt to concept drift.
result Adversarial validation effectively addresses concept drift in user targeting systems.
New benchmark for EEG-eye movement reconstruction from functional data.
problem Reconstructing eye movements from EEG data.
method Functional neural networks and open challenges for evaluation.
result Baseline results for consumer-grade and research-grade hardware.
In this paper we focus our attention on the exploitation of the information contained in financial news to enhance the performance of a classifier of bank distress. Such information should be analyzed and inserted into the predictive model in the most efficient way and this task deals with all the issues related to tex…
CPML efficiently learns new metrics for categorical data.
problem Metric learning for categorical data.
method CPML (categorical projected metric learning) using Schatten p-norms.
result CPML provides efficient metric learning with improved accuracy.
Paper proves new inequalities for Einstein-Maxwell data sets.
problem Establishing area-charge inequalities for Einstein-Maxwell initial data sets.
method Applying Gromov's μ-bubble technique in a new geometric context.
result Novel rigidity theorems for noncompact Einstein-Maxwell data sets.
New method for imputing missing data in multi-view data.
problem Large missing data sets in multi-view data.
method Stacked penalized logistic regression (StaPLR) in a dimension-reduced space.
result New method performs competitively with lower computational cost.
New framework predicts 5-year glucose values with missing data.
problem Significant missing data in longitudinal glucose studies.
method Reproducing Kernel Hilbert Spaces (RKHS) with missing responses analysis.
result Identifies new factors affecting long-term glucose evolution.
A new drift detection method based on autoregressive models.
problem Concept drift in real-world data leads to decreased model performance.
method Autoregressive based drift detection method (ADDM).
result ADDM outperforms state-of-the-art drift detection methods.
Generative replay extends sound classification models to new classes without old data.
problem Incrementally refining a sound classifier with new data causes previously learned tasks to degrade.
method Developed a generative replay procedure to generate training data in place of older datasets.
result Generative replay with 4% of old data performs as well as keeping 20% of old data.
New approach for principal curves on spherical data.
problem Dimension reduction of spherical data.
method Projection of data onto a continuous curve on a sphere.
result Stationary principal curves on a sphere.