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.
CASTNet forecasts opioid overdoses using crime patterns.
problem Forecasting opioid overdose occurrences.
method Community-attentive spatio-temporal networks incorporating multi-head attention.
result Superior forecasting performance and interpretable community contributions.
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…
Deep learning predicts crime counts with high accuracy.
problem Forecasting crime counts in city partitions.
method Used deep neural networks trained on crime data and additional datasets.
result Predicted crime counts with 75.6% and 65.3% accuracy for Chicago and Portland.
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 AUC and PPVk. result The PPVk deviates significantly from AUC in crime forecasting models. 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.
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.
New model detects crime linkages from text, time, and space.
problem Detecting crime linkages from limited information.
method Spatio-temporal-textual Hawkes processes with text embeddings.
result Joint modeling of space, time, and text enhances crime linkage detection.
Predict crime using urban metrics with machine learning.
problem Predict crime using urban metrics and handle multicollinearity.
method Random forest regressor for crime prediction and clustering of urban indicators.
result Urban indicators like unemployment and illiteracy are most important for predicting homicides.
Deep learning improves crime prediction accuracy.
problem Improving crime prediction accuracy using deep learning.
method Comparative study of 10 deep learning methods on crime data.
result Deep learning methods outperform existing methods in crime prediction.
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.
Detects crime series using RBM embeddings from crime narratives.
problem Detecting related crime series from crime records.
method Unsupervised learning of latent feature embeddings using Gaussian-Bernoulli RBM.
result Related cases are closer in feature space, unrelated cases are far apart.
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.
Paper predicts crimes using historical data and machine learning.
problem Predicting and preventing crime activities.
method Supervised learning with decision tree, k-nearest neighbor, Random Forest, and Adaboost algorithms.
result The system predicts crimes with better accuracy using historical data.
The paper models crime risk using Foursquare check-ins and mobility data.
problem Understanding and predicting crime risk in urban areas.
method Directed graph of aggregated movement data, region risk factor derivation, DIFFER features.
result Reliable correlations between DIFFER features and crime count observed.
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.
New algorithm embeds crime events using RBMs with feature selection.
problem Capturing complex crime data features for event embedding.
method Regularized RBMs with ℓ1 penalty for feature selection. result Improved event embedding with interpretable selected features.
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…
This study predicts crime trends in Denver using machine learning.
problem Predicting crime patterns to aid law enforcement and resource allocation.
method Statistical analysis, data visualization, and various classification algorithms.
result Ensemble Model 4 achieved the highest accuracy in predicting crime.
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%.
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.
Paper explores how unsupervised learning reduces financial crime risks.
problem Identifying high-risk financial groups from complex data.
method Combines clustering and dimensionality reduction techniques.
result KPCA outperforms other techniques in reducing financial crime risks.
Complex financial instruments allow insider trading without actual trades.
problem How to commit insider trading without executing a trade.
method Use of financial instruments to replicate the economic effect of trading.
result Insider trading can be committed without an actual trade.
Law responds to adversarial machine learning threats.
problem Adversarial machine learning attacks and their legal implications.
method Scenarios and legal analysis of adversarial ML attacks.
result Some attacks are more likely to result in liability.
New fair-by-design model reduces bias in recidivism prediction.
problem Discriminatory bias in recidivism prediction models.
method Prototype-based, locally learned, data distribution extraction.
result Reduces bias and provides interpretable rules.
Nested model averaging improves high-dimensional linear regression performance.
problem High-dimensional linear regression with predictor ordering impact.
method Combining model averaging with regularized estimators on the solution path.
result Nested model averaging with lasso and SLOPE outperforms competing methods.
Machine learning improves risk assessment for gender-based violence victims.
problem Accurately predicting recidivism risk in gender-based crime victims.
method Applied machine learning techniques to create models predicting recidivism risk.
result Proposed ML method outperforms classical statistical methods.
New model helps identify suspect footwear from crime scene prints.
problem Identifying a suspect's footwear from crime scene prints among thousands of similar shoes.
method Developed a hierarchical Bayesian model with spatially varying coefficients.
result Improved accuracy and reliability in forensic shoe print analysis.
New method reconstructs networks from spatiotemporal data.
problem Network reconstruction from spatiotemporal data.
method Multivariate Hawkes processes using both temporal and spatial information.
result Spatiotemporal approach yields improved network reconstruction.
Algorithm learns fair allocations in unknown group frequencies.
problem Fairness in resource allocation problems.
method Efficient learning algorithm in a censored feedback model.
result Algorithm converges to optimal fair allocation.
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.
We propose an efficient method for estimating covariate effects in doubly-stochastic spatial models.
problem Computational demands and restrictive assumptions in existing doubly-stochastic spatial models.
method Penalized regression method for estimating covariate effects in doubly-stochastic point processes.
result Consistency and asymptotic normality of the covariate effect estimates achieved despite model misspecification.
Survey of robust clustering methods for hotspot detection.
problem Detecting false positives in spatial hotspot mapping.
method Statistically rigorous clustering techniques.
result Survey of models and algorithms for robust clustering.
We observe standard transfer learning can improve prediction accuracies of target tasks at the cost of lowering their prediction fairness -- a phenomenon we named discriminatory transfer. We examine prediction fairness of a standard hypothesis transfer algorithm and a standard multi-task learning algorithm, and show th…
Paper develops a non-parametric model to estimate influence networks in high-dimensional time series.
problem Estimating influence networks in high-dimensional time series with many variables.
method Non-parametric sparse additive model (SpAM) using β and φ-mixing properties of Markov chains and empirical process techniques for RKHSs.
result Sharp upper bounds on mean-squared error for estimating influence networks.
New framework models time-uncertain point processes for better event prediction.
problem Uncertainty in event times in point processes.
method Formulated and discretized continuous-time Hawkes processes with time grid, enabling optimization methods for inference.
result Parameter recovery with O(1/k) convergence rate using gradient descent and VI. The paper proposes a machine learning framework for detecting DeFi fraud across multiple blockchain chains.
problem Early detection of financial crimes in decentralized finance (DeFi) ecosystems.
method Extracting features from different blockchain chains, employing XGBoost and Neural Network for fraud detection.
result Introduction of novel DeFi-related features significantly improves fraud detection accuracy.
A recent paper of Arnold, Falk, and Winther [Bull AMS, 47 (2010)] showed that a large class of mixed finite element methods can be formulated naturally on Hilbert complexes, where using a Galerkin-like approach, one solves a variational problem on a finite-dimensional subcomplex. In a seemingly unrelated research direc…
Maximal correlation framework improves fairness in machine learning algorithms.
problem Ensuring fairness in machine learning algorithms.
method Introducing maximal correlation framework for fairness constraints and deriving regularizers.
result The approach provides smooth performance-fairness tradeoff curves and competitive performance.
Optimal reconciliation keeps some forecasts unchanged in hierarchical forecasting.
problem Keeping some forecasts unchanged in hierarchical forecasting.
method Formulates a method to keep some forecasts unchanged in a hierarchical forecasting system.
result Preserves unbiasedness and non-negativity of forecasts.
Paper proposes a framework for probabilistic load forecasting by integrating point forecasts.
problem Short-term load forecasting for power systems energy management.
method Two-stage framework: first stage for point forecasting, second stage for probabilistic forecasting using feature integration.
result Numerical results show effectiveness of the proposed approach in hour-ahead load forecasting.
Combining forecasts of 16 ED causes improves accuracy and stability.
problem Forecasting accuracy and stability for ED admissions is poor due to model uncertainty and limited data.
method High-dimensional forecast combinations of 16 cause-specific ED forecasts using extensive covariates.
result Forecast combinations yield forecast accuracies of 3.81%-23.54% across causes, outperforming individual models in 50% of scenarios.
Conditional forecasts improve performative prediction accuracy.
problem Performative predictions undermine standard forecasting methods.
method Condition forecasts on covariates to make them forecast-invariant.
result Proper scoring rules fail under conditioning, but two solutions are identified.
We present a novel subset scan method to detect if a probabilistic binary classifier has statistically significant bias -- over or under predicting the risk -- for some subgroup, and identify the characteristics of this subgroup. This form of model checking and goodness-of-fit test provides a way to interpretably detec…
Study improves seasonal forecasts using deep learning.
problem Challenges in generating large forecast ensembles and limited observations for verification.
method Developed a probabilistic deep neural network model.
result Demonstrated favorable skill compared to state-of-the-art dynamical forecast systems.