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.

169,181 papers · 148 categories

Trend · papers per month

20405979 · May 202019922001200920182026
48 results for real-time crime forecasting

Model predicts crime distribution in real-time, superior to existing methods.

problem Accurate real-time crime forecasting is difficult due to sparse and weak historical data.
method Adapted spatial temporal residual network to predict crime distribution in Los Angeles.
result The proposed model outperforms existing approaches in crime prediction accuracy.

Method predicts crime hotspots with high resolution.

problem Forecasting sparse spatiotemporal events like crime.
method Combines RKHS methods with autoregressive smoothing kernels.
result Significantly outperforms baseline models for sparse events.

Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors. Compared to many predictable events, crime is sparse. At different spatio-temporal scales, crime distributions display dramatica…

2017-07-09abs ↗pdf ↗

A deep neural network framework for forecasting sparse spatio-temporal data.

problem Forecasting sparse spatio-temporal data with real-time interactions.
method Coupling self-exciting point process and graph structured recurrent neural network.
result More accurate real-time forecasting of crime and traffic data.

New approach predicts crime and terrorism events with high accuracy and transparency.

problem Predicting crime and terrorism events with high accuracy and interpretability.
method Granger Network inference for local transport rules learning.
result Achieved AUC of ~90% for crime predictions and ~80% for terrorism predictions.

This thesis evaluates the quality of binary classification models in crime forecasting tools.

problem Quality assessment of binary classification models in crime forecasting tools.
method Binary classifier approach to evaluate AUCAUC and PPVkPPV_k.
result The PPVkPPV_k deviates significantly from AUCAUC in crime forecasting models.

Predictive policing models can be biased by differential crime reporting rates.

problem Bias in predictive policing models due to differential crime reporting.
method Simulation based on Bogotá, Colombia's victimization and crime reporting data.
result Differential crime reporting rates can lead to misallocation of police patrols.

Deep neural networks improve real-time power system state estimation and forecasting.

problem Real-time monitoring of power grids with large-scale renewable generation and electric vehicles.
method Developed a novel model-specific DNN for real-time PSSE and used deep RNNs for forecasting.
result Improved performance compared to existing alternatives, including Gauss-Newton PSSE solver.

The paper introduces a US crime index to assess financial losses from property and cyber crimes.

problem Lack of indices evaluating crime's financial impact on investments.
method Developed an index-based insurance portfolio using FBI financial losses data.
result Real estate, ransomware, and government impersonation are major risk contributors.

Paper aims to use AI for detecting financial crimes, focusing on money laundering.

problem Financial institutions need better technologies to detect and predict financial crimes.
method Study recent works, develop a novel model for money laundering detection.
result Demonstrates a model for detecting money laundering cases with minimal human intervention.

ALPE improves mid-price forecasting in HFT with real-time data.

problem Real-time mid-price forecasting in high-frequency trading.
method Adaptive Learning Policy Engine (ALPE) using RL and adaptive epsilon decay.
result ALPE outperforms other models in mid-price forecasting.

LAD-BNet improves real-time energy forecasting on edge devices.

problem Real-time energy forecasting on edge devices for smart grid optimization and intelligent buildings.
method Hybrid neural architecture combining temporal lag exploitation and TCN with dilated convolutions.
result 14.49% MAPE at 1-hour horizon with 18ms inference time on Edge TPU, 8-12x faster than CPU.

New method combines model forecasts and real-time observations for hourly wind speed predictions.

problem Filling the six-hour gap between weather model runs for accurate hourly wind speed forecasts.
method Combines quasi-real-time observed wind speed and weather model predictions using a novel Ensemble Model Output Statistics (EMOS) strategy.
result Successfully improved wind speed predictions compared to observed data from SYNOP stations.

DeepCSO model forecasts CSO events from multiple sewer structures in near real-time.

problem Forecasting Combined Sewer Overflow (CSO) events at a citywide level.
method Multi-task deep learning model combining data-driven and deterministic methods.
result Deep learning model outperforms traditional methods in CSO event forecasting.

The study improves crime prediction using Foursquare and streetlight data with demographic info.

problem Improving crime prediction models using diverse data sources.
method Combining Foursquare and streetlight data with demographic info for crime prediction.
result The proposed model enhances classification performance in crime prediction.

Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime. Discovered crime data (e.g., arrest counts) are used to help update the model, and the process is repeated. Such systems have been empirically shown to be susceptible to runaway feedback l…

2017-06-29abs ↗pdf ↗

Machine learning predicts COVID-19 activity in China.

problem Real-time forecasting of COVID-19 activity in Chinese provinces.
method Combines mechanistic disease models with digital traces (internet searches, news alerts). Uses clustering and data augmentation techniques.
result Stable and accurate forecasts 2 days ahead of current time, outperforming baseline models in 27 out of 32 provinces.

This review explores probabilistic forecasting methods in evolving energy markets.

problem Volatility and uncertainty in renewable energy markets require probabilistic forecasting for risk assessment.
method Traces evolution from Bayesian and distribution-based approaches to conformal prediction.
result Probabilistic forecasting offers a more comprehensive approach to risk assessment and market participation.

CRIMED optimizes regret in bandits with unbounded stochastic corruption.

problem Minimizing regret in bandits with arbitrary unbounded corruptions.
method Introduces CRIMED, an asymptotically-optimal algorithm for Gaussian distributions with known variance.
result Achieves exact lower bound on regret for Gaussian distributions with high corruption probability.

Paper proposes a federated graph learning platform to improve financial crime detection.

problem Current financial crime detection methods are ineffective and costly.
method Federated graph learning platform combining federated learning and graph learning.
result Federated model outperforms local model by 20%.

Automated system forecasts safety and security issues in internet-connected devices.

problem Challenges in real-time large-scale forecasting by human experts.
method Developed a scalable and versatile forecasting system using models and methods.
result Automated short and long-term forecasts detect safety and security issues in internet-connected devices.

Paper proposes an efficient method for calibrating spatio-temporal forecasts.

problem Real-world spatio-temporal forecasting challenges like signal anomalies and distributional shifts.
method Learning with Calibration (ST-TTC) for real-time bias correction.
result ST-TTC improves spatio-temporal forecasting accuracy with reduced computational cost.

Generative adversarial network improves geosteering in fluvial reservoirs.

problem Improving geosteering in complex reservoirs with high uncertainties.
method Generative adversarial deep neural network (GAN) trained to model fluvial successions.
result Reduces uncertainty and correctly predicts geological features up to 500 meters ahead of drill-bit.

OneShotSTL efficiently decomposes time series online, improving speed and accuracy.

problem Real-time analysis of time series data with low processing delay.
method Online seasonal-trend decomposition algorithm with O(1) update time complexity.
result 1,000 times faster than batch methods with comparable accuracy.

Study uses RNN for real-time crypto price prediction and trading optimization.

problem High volatility in cryptocurrency markets makes traditional forecasting models unreliable.
method Data collection, preprocessing, model refinement, and backtesting.
result Improved accuracy in real-time crypto price prediction and optimized trading strategies.

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.

Deep neural networks reduce weather forecast uncertainty estimation costs.

problem Accurate estimation of weather forecast uncertainty using ensemble prediction systems.
method Modified 3D U-Net architecture and models incorporating temporal data.
result Deep neural networks can estimate weather forecast uncertainty with fewer simulations.

New model forecasts long-memory series with time-varying parameters.

problem Forecasting long-memory series with dynamic parameters.
method Proposes a new long-memory model with a time-varying fractional parameter, driven by predictive likelihood score.
result Validated through Monte Carlo experiment and real data applications.