Proposes a new model to accurately describe random series of events.
problem Accurately and parsimoniously characterize random series of events (RSEs).
method Burstiness Scale (BuSca) model, which views RSEs as a mix of Poissonian and self-exciting processes.
result BuSca accurately describes RSEs in diverse systems, even with only two parameters.
The aim here is to study the concept of pairing multifractality between time series possessing non-Gaussian distributions. The increasing number of rare events creates "criticality". We show how the pairing between two series is affected by rare events, which we call "coupled criticality". A method is proposed for stud…
Quantum model captures rare financial events not seen by Gaussian statistics.
problem Underestimation of rare financial events by Gaussian statistics.
method Quantum Bohmian Mechanics applied to multifractal random walk (MRW) models.
result Rare financial events generate a potential barrier in quantum potentials.
Fermat-Torricelli points help assess investment risks by smoothing series data.
problem Analyzing investment risks in series with large variance, nonlinear trends, or non-normal distributions.
method Construct Fermat-Torricelli points to reduce random component influence.
result Smoothing series by Fermat-Torricelli points reduces risk assessment errors.
Modeling event sequences with RNNs for predictive maintenance.
problem Predicting the intensity function of asynchronous event sequences.
method Use two RNNs: one for background and another for history effects.
result End-to-end training of the model for black-box event intensity prediction.
A cased-based reasoning method predicts rare events on strategic sites using satellite imagery.
problem Manual prediction of rare events on strategic sites is impractical due to large datasets.
method Case-based reasoning approach incorporating expert knowledge for irregular time series and small datasets.
result The method significantly outperforms random selection on challenging applications.
Proposes a test for shared information between time series and events.
problem Detecting extreme events in time series data.
method Non-parametric statistical test using multiple two-sample testing at increasing lags.
result Outperforms or matches related tests on various datasets.
Basic peculiarities of market price fluctuations are known to be well described by a recently developed random walk model in a temporally deforming quadric potential force whose center is given by a moving average of past price traces [Physica A 370, pp91-97, 2006]. By analyzing high-frequency financial time series of …
STRODE learns timings and dynamics from unlabeled time series data.
problem Learning dynamics of random event timings from unlabeled sensory inputs.
method Probabilistic Ordinary Differential Equation (STRODE) that samples from posterior point processes.
result Successfully infers event timings from synthetic and real-world datasets.
Dataset for rare event prediction in industrial multivariate time series.
problem Building a model to predict rare events in a multivariate time series dataset.
method The dataset is used to build a classification model for early prediction of rare events.
result The dataset can be used for various types of models including classification and exploration.
New deep learning method handles rare and imbalanced events in time series.
problem Challenges in event detection in time series data, especially rare and imbalanced events.
method Supervised regression-based deep learning approach that handles various types of events.
result Superior performance across diverse domains, particularly for rare events and imbalanced datasets.
Researchers analyze record statistics in correlated random walks and Lévy flights.
problem Understanding record statistics in correlated time series.
method Review of random walk models and Lévy flights, focusing on number of records and record ages.
result Effects of correlations on record statistics were observed and analyzed.
In this paper, we consider formal series associated with events, profiles derived from events, and statistical models that make predictions about events. We prove theorems about realizations for these formal series using the language and tools of Hopf algebras.
EvoNet predicts events in time-series data by evolving state graphs.
problem Predicting events in time-series data with interpretable patterns.
method Evolutionary State Graph (ESG) and EvoNet model.
result EvoNet outperforms baselines and provides insights into event predictions.
New approach predicts event probabilities for better event detection.
problem Class imbalance and inaccurate event detection in time series analysis.
method Regression-based approach to predict probability densities at event locations.
result Regression-based approaches outperform segmentation-based methods.
Paper proposes a hierarchical approach for early anomaly detection in time series data for critical health events.
problem Early detection of critical health events in intensive care units.
method A layered learning architecture that breaks the problem into pre-conditional and event layers.
result The proposed method outperforms state-of-the-art approaches for critical health episode prediction.
New method infers causality from short memory-less transition data.
problem Inferring causality from short time series data.
method Composition of Transitions (COT) and machine learning models.
result Highly accurate in inferring causal relationships from short data.
Proposes a model for multi-horizon probabilistic forecasting of time series influenced by asynchronous events.
problem Forecasting time series influenced by asynchronous events is challenging.
method Introduces Variational Synergetic Multi-Horizon Network (VSMHN), a deep conditional generative model combining deep point processes and variational recurrent neural networks.
result Produces accurate, sharp, and realistic probabilistic forecasts.
New method clusters hydrological and sediment data for storm event analysis.
problem Analyzing storm events for water quality constituents like turbidity.
method Multivariate time series clustering of river discharge and sediment data.
result Clusters differ from 2-D hysteresis loop classifications.
New algorithm detects unique events in time series data.
problem Detecting anomalous events in unknown properties.
method Model-free, unsupervised detection using Temporal Outlier Factor (TOF).
result TOF outperforms traditional outlier detection methods.
Paper tackles event classification for multi-variate time series data with heterogeneous variables.
problem Complex temporal dependencies and sparsity in multi-variate time series data.
method Proposes and compares three representation learning algorithms over symbolized sequences trained jointly with the rest of the network architecture.
result Demonstrates the effectiveness of the proposed approaches on three real-world datasets.
Estimates network structure from incomplete event data.
problem Estimating network structure from incomplete event data.
method Developed a novel approach using an unbiased estimator of the complete data log-likelihood function.
result Proposed a computationally efficient estimation algorithm.
Study categorizes time series anomaly detection metrics based on evaluation challenges.
problem Challenges in evaluating time series anomaly detection due to diverse application objectives and metric assumptions.
method Problem-oriented framework categorizing metrics into six dimensions based on evaluation challenges.
result Quantifies each metric's discriminative ability and reveals limitations of widely used metrics.
PHINN: A generative model for rare-event time series using persistent homology
problem Generating rare events in time series
method Flow-matching framework with dynamic Betti curves and persistence landscape loss
result Outperforms statistical and diffusion baselines in topological fidelity and tail coverage
Proposes a parsimonious graph spectral method for time series data.
problem Efficiently transmitting multivariate time series data.
method Graph spectral embedding with unsupervised, parsimonious encoding.
result Near-linear computational complexity and interpretable event structure.
Study infers tree topology from customer data using contrastive learning.
problem Inferring local network topology from customer data.
method Contrastive learning approach for binary event encoding from continuous time series.
result Preliminary results show potential for valuable encoder learning.
This paper evaluates anomaly detection methods for multivariate time series data.
problem Lack of systematic comparison of anomaly detection methods on multivariate time series data.
method Comprehensive evaluation of 10 models and 4 scoring functions on 10 datasets.
result Dynamic scoring functions outperform static ones, and the choice of scoring functions matters more than the model choice.
Study shows class imbalance and temporal coherence impact solar flare analysis.
problem Class imbalance and temporal coherence in rare-event analysis.
method Experiments on SWAN-SF dataset, including data and model manipulations.
result Temporal coherence invalidates randomness assumption, impacting sampling practices.
New method detects TC imagery patterns for rapid intensity change.
problem Detecting upcoming rapid intensity changes in TC satellite imagery.
method Nonparametric test of association between images and event labels using neural networks and bootstrap.
result Identifies archetypes of infrared imagery associated with elevated rapid intensification risk.
Simple algorithm approximates rare event frequencies.
problem Approximating the frequency of rare events.
method Iterative update of categorical click-distribution, resulting in a random walk on an n-dimensional simplex.
result The random walk corresponds to a biased Bernoulli convolution under certain conditions.
Shapelet transform improves time series classification for earthquake, wind, and wave events.
problem Autonomous detection of specific events from large time series datasets in civil engineering.
method Shapelet transform for local similarity in time series subsequences, combined with machine learning.
result Shapelet transform yields a new feature representation for time series signals in civil engineering.
Study predicts adverse events in Afghanistan using time series data.
problem Predicting the number of negative events in Afghanistan's theater of war.
method Regression analysis on time series data, non-conventional aggregation of districts, machine learning models.
result Predictive models show reasonable performance on historical data, but other variables do not improve prediction quality.
Predict and explain storage failures using RNNs with event extraction.
problem Predict and explain failures in storage environments from time series data.
method Extract anomalous spikes as events, then build an RNN classifier with attention mechanisms.
result Comparable accuracy to traditional RNNs with improved explainability.
A new method for modeling event sequences with ambiguous timestamps.
problem Handling event sequences with variable timestamps and time-shifts.
method Time-discounting convolution with dynamic pooling.
result Efficiently models event dependencies and robust against timestamp uncertainty.
Method estimates exogenous and endogenous factors from event times.
problem Estimating factors influencing event occurrence.
method Combines inhomogeneous Poisson and Hawkes processes, fits using free energy minimization.
result Four regimes identified based on factor detection.
Study finds strong long-range correlations in financial markets, especially over longer time scales.
problem Understanding long-range correlations in limit order book markets.
method Ultra-high frequency order book data from NASDAQ Nordic, detrended fluctuation analysis (DFA).
result Strong evidence of long-range correlation in inter-event durations, becoming stronger over longer time scales.
Used to investigate the presence of distinctive recurrent behaviours in natural processes, the recurrence plots can be applied to the analysis of economic data, and, in particular, to the characterization of exchange rates of currencies too. In this paper, we will show that these plots are able to characterize the peri…
Deep model forecasts correlated multivariate time series.
problem Forecasting correlated multivariate time series.
method Deep learning structural model using CNN-LSTM architecture.
result Model outperforms state-of-the-art methods in various time series data sets.
New method infers nonlinear Granger causality from time series data.
problem Inferring nonlinear Granger causality from time series data.
method Statistical Recurrent Units (SRUs) for modeling nonlinear interactions.
result The proposed economy-SRU model outperforms existing models in inferring Granger causality.
We suggest a novel method of clustering and exploratory analysis of temporal event sequences data (also known as categorical time series) based on three-dimensional data grid models. A data set of temporal event sequences can be represented as a data set of three-dimensional points, each point is defined by three varia…
Paper proposes an anomaly detection system for DBMS diagnosis.
problem Difficulty in detecting anomalies in DBMS due to increasing metrics.
method Uses deep autoencoder and statistical process control for anomaly detection, and time series similarity for event finding.
result Demonstrates effectiveness of the proposed model in detecting anomalies and finding related events.
Novel framework for spatio-temporal event analysis using Hawkes processes.
problem Inference of dynamics in spatio-temporal event sequences.
method Randomized Fourier feature-based transformations and gradient descent.
result Improved fitting capability in synthetic and real datasets.
New method explains anomalies in multivariate time series data.
problem Understanding and explaining anomalies in multivariate time series data.
method Counterfactual reasoning applied to MDI-detected anomalous intervals.
result Our method accurately identifies and explains anomalies in various extreme events.
Generates synthetic health data from patient visits.
problem Lack of longitudinal, event-based medical data.
method Transformed longitudinal data into summary statistics, trained GAN.
result Synthetic data closely resembles real data univariately.
Study rare-event simulation for neural networks and random forests.
problem Safety evaluation and robustness quantification of machine learning models.
method Importance sampling scheme integrating large deviations and sequential mixed integer programming.
result Efficiency guarantees and numerical demonstrations for various neural network architectures.
Extract real-world events from sensor data with minimal labels.
problem Challenges in extracting value from sensor-generated time series data.
method Identify features repeating in same temporal arrangement to isolate examples of real-world events.
result Up to 96% precision and recall in isolating diverse events like human actions and spoken words.
This paper is devoted to problem of detecting critical events at finiacial markets using methods of multifractal analysis. Namely, the local regularity of time-series is studied. As a result, one can find out a special behavior or signal of regularity before crashes. This spesial behaviour of local Hoelder exponents in…
Deep learning models combine text and time-series data for better taxi demand forecasts.
problem Accurate taxi demand forecasting in event areas.
method Two deep learning architectures using word embeddings, convolutional layers, and attention mechanisms.
result The models significantly reduce forecast error by fusing text and time-series data.