Crime Prediction Model Research Articles

DuroNet

Urban crime is an ongoing problem in metropolitan development and attracts general concern from the international community. As an effective means of defending urban safety, crime prediction plays a crucial role in patrol force allocation and public safety. However, urban crime data is a macro result of crime patterns overlapped by various irrelevant factors that cause inhomogeneous noises—local outliers and irregular waves. These noises might obstruct the learning process of crime prediction models and result in a deviation of performance. To tackle the problem, we propose a novel paradigm of <underline>Du</underline>al-<underline>ro</underline>bust Enhanced Spatial-temporal Learning <underline>Net</underline>work (DuroNet), an encoder-decoder architecture that possesses an adaptive robustness for reducing the effect of outliers and waves. The robustness is mainly reflected on two aspects. One is a locality enhanced module that employs local temporal context information to smooth the deviation of outliers and dynamic spatial information to assist in understanding normal points. The other is a self-attention-based pattern representation module to weaken the effect of irregular waves by learning attentive weights. Finally, extensive experiments are conducted on two real-world crime datasets before and after adding Gaussian noises. The results demonstrate the superior performance of our DuroNet over the state-of-the-art methods.

Spatio-Temporal Crime Predictions by Leveraging Artificial Intelligence for Citizens Security in Smart Cities

Smart city infrastructure has a significant impact on improving the quality of humans life. However, a substantial increase in the urban population from the last few years poses challenges related to resource management, safety, and security. To ensure the safety and security in the smart city environment, this paper presents a novel approach by empowering the authorities to better visualize the threats, by identifying and predicting the highly-reported crime zones in the smart city. To this end, it first investigates the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to detect the hot-spots that have a higher risk of crime occurrence. Second, for crime prediction, Seasonal Auto-Regressive Integrated Moving Average (SARIMA) is exploited in each dense crime region to predict the number of crime incidents in the future with spatial and temporal information. The proposed HDBSCAN and SARIMA based crime prediction model is evaluated on ten years of crime data (2008-2017) for New York City (NYC). The accuracy of the model is measured by considering different time scenarios such as the year-wise, (i.e., for each year), and for the total considered duration of ten years using an 80:20 ratio. The 80% of data was used for training and 20% for testing. The proposed approach outperforms with an average Mean Absolute Error (MAE) of 11.47 as compared to the highest scoring DBSCAN based method with MAE 27.03.

Applied Machine Learning in Social Sciences: Neural Networks and Crime Prediction

This study proposes a crime prediction model according to communes (areas or districts in which the city of Buenos Aires is divided). For this, the Python programming language is used, due to its versatility and wide availability of libraries oriented to Machine Learning. The crimes reported (period 2016–2019) that occurred in the city of Buenos Aires selected to test the model are: homicides, theft, injuries, and robberies. With this, it is possible to generate a crime prediction model according to the city area based on the SEMMA (Sample, Explore, Modify, Model, and Assess) model and after data manipulation, standardization and cleaning; clustering is performed using K-means and subsequently the neural network is generated. For prediction, it is necessary to provide the model with the information corresponding to the predictive characteristics (predict); these characteristics being according to the developed neural network model: year, month, day, time zone, commune, and type of crime.

Facial expression-based analysis on emotion correlations, hotspots, and potential occurrence of urban crimes

Thanks to the development of the Internet of things (IoT) and edge computing, the smart cameras across cities provide a massive amount of image samples with time and location labels, laying a solid basis for deep mining of image information and in-depth decision analysis. Therefore, this paper proposes to convert the images with spatiotemporal labels into quantifiable data on emotions, and apply them to crime prediction. Firstly, human emotions were divided into three categories: negative, neutral, and positive. Then, facial expression recognition (FER) was employed to quantify the portrait data. The emotion features thus acquired were imported to the crime prediction model, enhancing the model’s explanatory power. Finally, our method was compared with kernel density estimation (KDE) on six typical crimes. The results show that introducing emotion data helps to reveal the interaction between emotions and crimes and improve the performance of crime prediction.

Urban Crime Risk Prediction Using Point of Interest Data

Geographical information systems have found successful applications to prediction and decision-making in several areas of vital importance to contemporary society. This article demonstrates how they can be combined with machine learning algorithms to create crime prediction models for urban areas. Selected point of interest (POI) layers from OpenStreetMap are used to derive attributes describing micro-areas, which are assigned crime risk classes based on police crime records. POI attributes then serve as input attributes for learning crime risk prediction models with classification learning algorithms. The experimental results obtained for four UK urban areas suggest that POI attributes have high predictive utility. Classification models using these attributes, without any form of location identification, exhibit good predictive performance when applied to new, previously unseen micro-areas. This makes them capable of crime risk prediction for newly developed or dynamically changing neighborhoods. The high dimensionality of the model input space can be considerably reduced without predictive performance loss by attribute selection or principal component analysis. Models trained on data from one area achieve a good level of prediction quality when applied to another area, which makes it possible to transfer or combine crime risk prediction models across different urban areas.

Nonparametric spatiotemporal analysis of violent crime. A case study in the Rio de Janeiro metropolitan area

This paper analyzes the spatiotemporal pattern of gunfire reports collected by the collaborative mobile app Fogo Cruzado in the Rio de Janeiro metropolitan area (Brazil). We apply nonparametric first and second-order inference tools to characterize gunfire behavior, and test whether gunfire patterns meet the assumptions of crime prediction models, such as kernel hotspot maps or self-exciting point process. The kernel intensity estimator describes the spatial distribution of gunfire and identifies chronic hotspots. The nonparametric test for comparison of first-order intensities found differences between gunfires with and without fatalities or police presence. The recently developed log-ratio based first-order separability test found that the spatial distribution of gunfire, fatalities and police presence varied over time. Finally, spatiotemporal inhomogeneous K-tests detected clustering between gunfire events, fatalities and police presence. These results suggest that a self-exciting point process with nonseparable background component is an acceptable model for future development of a suitable approach to forecast gunfire hotspots in Rio de Janeiro.

Spatial crime distribution and prediction for sporting events using social media

ABSTRACT Sporting events attract high volumes of people, which in turn leads to increased use of social media. In addition, research shows that sporting events may trigger violent behavior that can lead to crime. This study analyses the spatial relationships between crime occurrences, demographic, socio-economic and environmental variables, together with geo-located Twitter messages and their ‘violent’ subsets. The analysis compares basketball and hockey game days and non-game days. Moreover, this research aims to analyze crime prediction models using historical crime data as a basis and then introducing tweets and additional variables in their role as covariates of crime. First, this study investigates the spatial distribution of and correlation between crime and tweets during the same temporal periods. Feature selection models are applied in order to identify the best explanatory variables. Then, we apply localized kernel density estimation model for crime prediction during basketball and hockey games, and on non-game days. Findings from this study show that Twitter data, and a subset of violent tweets, are useful in building prediction models for the seven investigated crime types for home and away sporting events, and non-game days, with different levels of improvement.

Predicting Criminal Behavior with Lévy Flights Using Real Data from Bogotá

I use residential burglary data from Bogota, Colombia, to fit an agent-based model following truncated L´evy flights (Pan et al., 2018) elucidating criminal rational behavior and validating repeat/near-repeat victimization and broken windows effects. The estimated parameters suggest that if an average house or its neighbors have never been attacked, and it is suddenly burglarized, the probability of a new attack the next day increases, due to the crime event, in 79 percentage points. Moreover, the following day its neighbors will also face an increment in the probability of crime of 79 percentage points. This effect persists for a long time span. The model presents an area under the Cumulative Accuracy Profile (CAP) curve, of 0.8 performing similarly or better than state-of-the-art crime prediction models. Public policies seeking to reduce criminal activity and its negative consequences must take into account these mechanisms and the self-exciting nature of crime to effectively make criminal hotspots safer.

Anisotropic Diffusion for Improved Crime Prediction in Urban China

As a major social issue during urban development, crime is closely related to socioeconomic, geographic, and environmental factors. Traditional crime prediction models reveal the spatiotemporal dynamics of crime risks, but usually ignore the environmental context of the geographic areas where crimes occur. Therefore, it is difficult to enhance the spatial accuracy of crime prediction. We propose the use of anisotropic diffusion to include environmental factors of the evaluated geographic area in the traditional crime prediction model, thereby aiming to predict crime occurrence at a finer scale regarding spatiotemporal aspects and environmental similarity. Under different evaluation criteria, the average prediction accuracy of the proposed method is 28.8%, improving prediction accuracy by 77.5%, as compared to the traditional methods. The proposed method can provide strong policing support in terms of conducting targeted hotspot policing and fostering sustainable community development.

A crime prediction model based on spatial and temporal data

In a world where data has become precious thanks to what we can do with it like forecasting the future, the fight against crime can also benefit from this technological trend. In this work, we propose a crime prediction model based on historical data that we prepare and transform into spatiotemporal data by crime type, for use in machine learning algorithms and then predict, with maximum accuracy, the risk of having crimes in a spatiotemporal point in the city. And in order to have a general model not related to a specific type of crime, we have described our risk by a vector of n values that represent the risks by type of crime.

Mining large-scale human mobility data for long-term crime prediction

Traditional crime prediction models based on census data are limited, as they fail to capture the complexity and dynamics of human activity. With the rise of ubiquitous computing, there is the opportunity to improve such models with data that make for better proxies of human presence in cities. In this paper, we leverage large human mobility data to craft an extensive set of features for crime prediction, as informed by theories in criminology and urban studies. We employ averaging and boosting ensemble techniques from machine learning, to investigate their power in predicting yearly counts for different types of crimes occurring in New York City at census tract level. Our study shows that spatial and spatio-temporal features derived from Foursquare venues and checkins, subway rides, and taxi rides, improve the baseline models relying on census and POI data. The proposed models achieve absolute R^{2} metrics of up to 65% (on a geographical out-of-sample test set) and up to 89% (on a temporal out-of-sample test set). This proves that, next to the residential population of an area, the ambient population there is strongly predictive of the area’s crime levels. We deep-dive into the main crime categories, and find that the predictive gain of the human dynamics features varies across crime types: such features bring the biggest boost in case of grand larcenies, whereas assaults are already well predicted by the census features. Furthermore, we identify and discuss top predictive features for the main crime categories. These results offer valuable insights for those responsible for urban policy or law enforcement.

Street crime prediction model based on the physical characteristics of a streetscape: Analysis of streets in low-rise housing areas in South Korea

Previous crime prediction research focusing on regional characteristics is lacking in terms of the examination of physical characteristics of individual crime scenes. This study, therefore, presents a street crime prediction model by analysing streetscape features within an actual field of vision for a low-rise housing area in South Korea, which serves as a gauge for potential offenders to carry out crime. First, we performed logistic regression to analyse the correlation between street crime opportunities and the elements of streets to derive an equation for predicting street crime using selected variables. Next, we created a crime prediction map based on a geographic information system that contains attribute data on these physical characteristics and presented a street crime prediction model based on the derived prediction equation. Finally, to test the prediction model, we compared actual crime data from the selected area with the results obtained from the prediction model. The test results showed that the prediction model classified 11 out of 29 actual crime spots as crime occurrence; among the 312 non-crime spots, 257 were classified as non-crime occurrence. Based on these test results, we confirm that the occurrence of street crime is affected by the physical characteristics within the actual field of vision and discuss the improvement of the prediction model.

Prediction of crime occurrence from multi-modal data using deep learning.

In recent years, various studies have been conducted on the prediction of crime occurrences. This predictive capability is intended to assist in crime prevention by facilitating effective implementation of police patrols. Previous studies have used data from multiple domains such as demographics, economics, and education. Their prediction models treat data from different domains equally. These methods have problems in crime occurrence prediction, such as difficulty in discovering highly nonlinear relationships, redundancies, and dependencies between multiple datasets. In order to enhance crime prediction models, we consider environmental context information, such as broken windows theory and crime prevention through environmental design. In this paper, we propose a feature-level data fusion method with environmental context based on a deep neural network (DNN). Our dataset consists of data collected from various online databases of crime statistics, demographic and meteorological data, and images in Chicago, Illinois. Prior to generating training data, we select crime-related data by conducting statistical analyses. Finally, we train our DNN, which consists of the following four kinds of layers: spatial, temporal, environmental context, and joint feature representation layers. Coupled with crucial data extracted from various domains, our fusion DNN is a product of an efficient decision-making process that statistically analyzes data redundancy. Experimental performance results show that our DNN model is more accurate in predicting crime occurrence than other prediction models.

A risk probability-map generation model on multimedia services environment

The rapid growth of modern society has been a double-edged sword; it has led to positive results such as income growth due to the diversification of our society, but also negative results such as an increase in crime. For this reason, cities are confronting a wide range of issues. Social issues, especially criminal offenses, stir up more fear of crime among residents. The rapid societal penetration of digital devices such as smart phones, along with an increase in IT knowledge, has made our lives more convenient. However, cyber-crime and violent crime taking advantage of these benefits are also increasing. There is an increasing need for crime prevention and crime prediction in order to solve these problems, and many studies on crime are under way as part of our effort to respond to various changes in our society using a variety of prediction tools. Thus, in this study, a combined risk probability map generation model was suggested by predicting crime frequency through a Markov Chain Analysis, quantifying risks through objective classification of urban spaces and applying attribute-specific risk indexes and interpretation keys across the entire scope of the study. The crime prediction model based on risk probability map suggested in this study facilitates multimedia services using mobile devices such as smartphones and thus can be used to optimally plan patrol routes of police officers in zones vulnerable to crimes as well as placement of surveillance systems, which will in turn contribute to relieving many citizens' anxiety about crime. Our model's approach is too small environment in this research time. But we will try to more experiment environment is big such as town and state next research time.

Predicting crime using Twitter and kernel density estimation

Twitter is used extensively in the United States as well as globally, creating many opportunities to augment decision support systems with Twitter-driven predictive analytics. Twitter is an ideal data source for decision support: its users, who number in the millions, publicly discuss events, emotions, and innumerable other topics; its content is authored and distributed in real time at no charge; and individual messages (also known as tweets) are often tagged with precise spatial and temporal coordinates. This article presents research investigating the use of spatiotemporally tagged tweets for crime prediction. We use Twitter-specific linguistic analysis and statistical topic modeling to automatically identify discussion topics across a major city in the United States. We then incorporate these topics into a crime prediction model and show that, for 19 of the 25 crime types we studied, the addition of Twitter data improves crime prediction performance versus a standard approach based on kernel density estimation. We identify a number of performance bottlenecks that could impact the use of Twitter in an actual decision support system. We also point out important areas of future work for this research, including deeper semantic analysis of message content, temporal modeling, and incorporation of auxiliary data sources. This research has implications specifically for criminal justice decision makers in charge of resource allocation for crime prevention. More generally, this research has implications for decision makers concerned with geographic spaces occupied by Twitter-using individuals.

The value of 5-HTT gene polymorphism for the assessment and prediction of male adolescence violence

To establish an adolescent violence crime prediction model, and to assess the value of serotonin transporter (5-HTT) gene polymorphism for the assessment and prediction of violent crime. Investigative tools were used to analyze the difference in personality dimensions, social support, coping styles, aggressiveness, impulsivity, and family condition scale between 223 adolescents with violence behavior and 148 adolescents without violence behavior. The distribution of 5-HTT gene polymorphisms (5-HTTLPR and 5-HTTVNTR) was compared between the two groups. The role of 5-HTT gene polymorphism on adolescent personality, impulsion and aggression scale also was also analyzed. Stepwise logistic regression was used to establish a predictive model for adolescent violent crime. Significant difference was found between the violence group and the control group on multiple dimensions of psychology and environment scales. However, no statistical difference was found with regard to the 5-HTT genotypes and alleles between adolescents with violent behaviors and normal controls. The rate of prediction accuracy was not significantly improved when 5-HTT gene polymorphism was taken into the model. The violent crime of adolescents was closely related with social and environmental factors. No association was found between 5-HTT polymorphisms and adolescent violence criminal behavior.