Machine learning plays a key role in present day crime detection, analysis and prediction. The goal of this work is to propose methods for predicting crimes classified into different categories of severity. We implemented visualization and analysis of crime data statistics in recent years in the city of Boston. We then carried out a comparative study between two supervised learning algorithms, which are decision tree and random forest based on the accuracy and processing time of the models to make predictions using geographical and temporal information provided by splitting the data into training and test sets. The result shows that random forest as expected gives a better result by 1.54% more accuracy in comparison to decision tree, although this comes at a cost of at least 4.37 times the time consumed in processing. The study opens doors to application of similar supervised methods in crime data analytics and other fields of data science

This research paper contributes to the literature of deterrence theory in general, and in particular with respect to white-collar crime, offering valuable inside by using a unique data set of fraud and violation of trust incidents for Paraguay. Descriptive evidence show a clear and continuous misallocation of funds and human capital, and therefore providing less efficient services for the public. Regression analysis suggests that clearance rate exerts a highly significant effect in deterring fraud but results are not clear for violation of trust incidents. Despite the limitations of available data, results confirm deterrence theory in Paraguay. However, to more than two-thirds of victims, not even the attempt was made to seek justice. As a side-result, it seems that a soft on crime strategy, induced from the former German penal code, has led to an increasing share of pre-trial diversion and therefore enhancing white-collar crimes like fraud and violation of trust due to impunity.

This paper presents a theoretically and methodologically grounded GIS-based model for the measurement and mapping of an index of living conditions in urban residential areas across Sweden. Further, the model is compared and evaluated using the Swedish Police’s assessment of crime-exposed areas. The results indicate that geographically measured vulnerable living conditions overlap to a large extent with the areas assessed to be crime-exposed by the Swedish Police. Over 61% of the police-defined crime-exposed areas are characterized by vulnerable living conditions. The results also show that the overlap is not perfect and that there are vulnerable areas that are not included in the police’s assessment of crime-exposed areas, but which are nonetheless characterized by vulnerable living conditions that could negatively affect the development of crime. It is also proposed that the model and the mapped index of living conditions provide a more well-grounded scientific basis for the police's assessment work. As a first step, the Swedish police have implemented the model and the mapped index in the work process employed in their annual identification of crime-exposed or at-risk areas. In addition to assisting the police, the model and the mapped index could also be used to support other societal actors working with vulnerable areas.

Around one billion people live in informal settlements, globally, including over half of Nairobi, Kenya’s three million residents. The purpose of this study was to explore women’s fear of victimization within Mathare, an informal settlement in Nairobi, Kenya and how fear of victimization influences behavior. Fifty-five in-depth interviews were conducted with women in 2016. A modified grounded theory approach guided data collection and analysis. Findings suggest fear of victimization is a serious concern in informal settlements. Women have found ways to adopt their behaviors that allow them to continue to function and protect their children despite fearing victimization, but at a potential cost to their health and well-being. Thus, there is a critical need for more research focused on social, economic, structural, community, infrastructure, technological, and individual strategies to prevent violence, enhance residents’ sense of safety, and, subsequently, minimize women’s fear of victimization in informal settlements.

Mate crime is a specific subset of hate crime in which the perpetrator is known to the victim. To date, there is very little research into the perception and experience of mate crime in autism. The aim of the current study was to examine perceptions of friendship and mate crime in autistic adults, using semi-structured interviews. Five adults were interviewed about their experiences of social interactions, friendships and mate crime. Participants described distancing themselves from the ‘disability’ label whilst growing up to avoid condescension and being perceived as vulnerable, whilst learning to camouflage their social difficulties. Feelings of anxiety were associated with socialising, and participants valued relationships that did not place too many overwhelming demands on their time or energy. Finally, all participants had prior experiences of bullying. They understood the concept of mate crime but were unsure as to whether they would be able to identify it in their own lives if it occurred. However they could identify potential support networks in close friends and family. Results highlight the importance of further research into positive and negative aspects of social relationships in autistic adults, and the need to provide support to those who are socially vulnerable.

The purpose of this study was to identify potential causes of violence and crime in informal settlements and residents’ strategies for response and prevention to these issues, as perceived by women living in Mathare informal settlement in Nairobi, Kenya. A total of 55 in-depth interviews were conducted with women living in the informal settlement in 2015-2016. A modified grounded theory approach was used to guide data collection and analysis. The most common contributor to violence and crime identified by women in Mathare informal settlement was idle youth, but leadership and government challenges, corruption and/or inadequacy of police, community barriers, tribalism, and lack of protective infrastructure also emerged as contributing factors. Despite facing many economic, environmental, and day-to-day challenges, women in Mathare identified violence and crime as predominant issues; thus, developing effective response and prevention strategies to these issues in informal settlements is paramount. Women suggest there are many strategies and initiatives to reduce and prevent violence and crime in informal settlements, but also identified barriers to implementing them. Findings suggest there is a need for trust-building between formal and informal organizations and institutions, systems of accountability, and long-term investment to foster sustainable and effective violence and crime response and interventions in these settlements.

After brings about a brief review of the theoretical explanations and researches on the reasons for being a victim, this article is organized into two sections. The first presents a comparative analysis of the data for 1999 and 2016 in terms of perceptions, profiles and most significant sociodemographic and socioeconomic variables. The second one shows an explanatory analysis based on a multivariate logistical regression model using as an independent variable lifestyle of the population and socioeconomic variables, and as dependent variables individual’s susceptibility to becoming a victim of certain crimes. The results points towards an explanatory model of victimization in which sociodemographic variables play an increasingly less important role while variables related to lifestyle and subjective perceptions make a significant contribution to greater understanding of the nature of being the victim of a crime.

Prior research shows that individuals who have exhibited antisocial behavior are in poorer health than their same-aged peers. A major driver of poor health is aging itself, yet research has not investigated relationships between offending trajectories and biological aging. We tested the hypothesis that individuals following a life-course persistent (LCP) antisocial trajectory show accelerated aging in midlife. Trajectories of antisocial behavior from age 7 to 26 years were studied in the Dunedin Multidisciplinary Health and Development Study, a population-representative birth cohort (N=1037). Signs of aging were assessed at age 45 years using previously validated measures including biomarkers, clinical tests, and self-reports. First, we tested whether the association between antisocial behavior trajectories and midlife signs of faster aging represented a decline from initial childhood health. We then tested whether decline was attributable to tobacco smoking, antipsychotic medication use, debilitating illnesses in adulthood, adverse exposures in childhood (maltreatment, socioeconomic disadvantage) and adulthood (incarceration), and to childhood self-control difficulties. Study members with a history of antisocial behavior had a significantly faster pace of biological aging by midlife, and this was most evident among individuals following the LCP trajectory (β, .22, 95%CI, .14, .28, p.001). This amounted to 4.3 extra years of biological aging between ages 25-45 years for Study members following the LCP trajectory compared to low-antisocial trajectory individuals. LCP offenders also experienced more midlife difficulties with hearing (β, -.14, 95%CI, -.21, -.08, p.001), balance (β, -.13, 95%CI, -.18, -.06, p.001), gait speed (β, -.18, 95%CI, -.24, -.10, p.001), and cognitive functioning (β, -.25, 95%CI, -.31, -.18, p.001). Associations represented a decline from childhood health. Associations persisted after controlling individually for tobacco smoking, antipsychotic medication use, midlife illnesses, maltreatment, socioeconomic status, incarceration, and childhood self-control difficulties. However, the cumulative effect of these lifestyle characteristics together explained why LCP offenders have a faster Pace of Aging than their peers. While older adults typically age-out of crime, LCP offenders will likely age-into the healthcare system earlier than their chronologically same-aged peers. Preventing young people from offending is likely to have substantial benefits for health, and people engaging in a LCP trajectory of antisocial behaviors might be the most in need of health promotion programs. We offer prevention and intervention strategies to reduce the financial burden of offenders on health care systems and improve their wellbeing.

While the use of crime data has been widely advocated in the literature, its availability is often limited to large urban cities and isolated databases tend not to allow for spatial comparisons. This paper presents an efficient machine learning framework capable of predicting spatial crime occurrences, without using past crime as a predictor, and at a relatively high resolution: the U.S. Census Block Group level. The proposed framework is based on an in-depth multidisciplinary literature review allowing the selection of 188 best-fit crime predictors from socio-economic, demographic, spatial, and environmental data. Such data are published periodically for the entire United States. The selection of the appropriate predictive model was made through a comparative study of different machine learning families of algorithms, including generalized linear models, deep learning, and ensemble learning. The gradient boosting model was found to yield the most accurate predictions for violent crimes, property crimes, motor vehicle thefts, vandalism, and the total count of crimes. Extensive experiments on real-world datasets of crimes reported in 11 U.S. cities demonstrated that the proposed framework achieves an accuracy of 73 and 77% when predicting property crimes and violent crimes, respectively.

Online identity-based theft is known to be one of the most serious and growing threats to victims, such as individuals and organizations, over the last 10 years due to the enormous economic damage these crimes have caused. The availability of personal information on the Internet has increased the chances of this cyber-crime. Online identity theft crime is the result of a combination of cyber-crimes on the one hand and lack of awareness and training of users on the other hand to protect personal data on the other. Education and awareness, which also contributes to early detection, is the strongest tool for consumers to safeguard themselves from online identity fraud. This paper provides a comprehensive explanation of online identity theft, the various approaches that thieves use to attack individuals and organizations and the types of fraud involved in this cyber-crime. The aim of this research is to evaluate the need for a reformulation of the concept of identity theft in order to be compatible with the evolution of behaviors and fraud.

The number of SIEM introduction is increasing in order to detect threat patterns in a short period of time with a large amount of structured/unstructured data, to precisely diagnose crisis to threats, and to provide an accurate alarm to an administrator by correlating collected information. However, it is difficult to quickly recognize and handle with various attack situations using a solution equipped with complicated functions during security monitoring. In order to overcome this situation, new detection analysis process has been required, and there is an effort to increase response speed during security monitoring and to expand accurate linkage analysis technology. In this paper, reflecting these requirements, we design and propose profiling auto-generation model that can improve the efficiency and speed of attack detection for potential threats requirements. we design and propose profiling auto-generation model that can improve the efficiency and speed of attack detection for potential threats.

The use of crime mapping has been used by the police to inform deployment of resources for many decades. Such approaches are commonly used to underpin crime control strategies designed to prevent or reduce acquisitive crimes such as domestic burglary. In recent decades there has been a shift away from simple hot spot identification to more complex geospatial mapping methodologies, such as near repeat analysis which was developed through research regarding burglary victimisation. One of these newly emerging methodologies is built upon the ecological, optimal forager theory (OFT). Research using this theory to examine domestic burglary offending intimated potential for positive results in predicting areas at risk of future crime. This led to a number of police services using crime analysis methodologies built upon OFT to underpin their deployment of resources in an effort to prevent or reduce domestic burglary through increased capable guardianship. However, to date, there has been no detailed examination of how the police services implemented such approaches. As such, this study seeks to fill this gap by examining OFT strategies implemented within 5 police services. By interviewing participants directly involved in the programs the study gathers views and perspectives of its relative success. As a result, we identify that participants felt the strategies produced limited impact on recorded burglary crime. We discuss how despite some positive by-products of the strategies, failure to comprehensively apply the theoretical foundations of OFT, and a variety of implementation failures have undermined the various programs, ultimately impacting their effectiveness.

Pattern recognition has long been regarded as key role for crime prevention and reduction. Crime analysts and policy makers can formulate effective strategies and allocate resources with reference to spatial and temporal pattern of crime. In order the combat and prevent severe crime in New York City (NYC), this study analyzed Felony Crime data of NYC in previous 5 years (2015 2020) and discovered criminal hotspots pattern and temporal patterns with open criminal complaint data provided by New York Police Department (NYPD). This study adapt a human computer interactive appraoch to draw patterns from crime data, whereas computations and visualization are performed by Python libraries, and human to inform the decision of visualization methods, computational parameters and direction of this exploratary analysis. Density based clustering algorithms, Grid Thematic Mapping and Density Heatmap are displayed to identify hotspots and demonstrates their associations with spatial features. Timeline analysis on moments of crime occurance demonstrates seasonality where crimes are mostly commited, while aoristic analysis showed hours of day when crime is mostly committed considering their timespan. Lastly, 3D visualization improved recognition of the displacement of hotspot over time, and suggested long term hotspots in NYC in 3 D visualization. This inform strategic plans for police deployment.

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 is posing challenges related to resource management, safety, and security. In order to ensure safe mobility and security in the smart city environment, this paper proposes a novel Artificial Intelligence (AI) based approach empowering the authorities to better visualize the threats and to help them identify the highly-reported crime zones yielding greater predictability of crime hot-spots in a 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 crimes to be committed. Second, for crime prediction, Seasonal Auto-Regressive Integrated Moving Average (SARIMA) exploited in each dense crime region to predict the number of crimes 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 period scenarios i.e. (a) year-wise, i.e., for each year and (b) for the whole period of ten years, using an 80:20 ratio where 80\% data was used for training and 20\% data was used for testing. The proposed approach outperforms with an average Mean Absolute Error (MAE) of 11.47.

Simulated crime scene investigation is an essential component of forensic science education, but its implementation poses challenges relating to cost, accessibility and breadth of experience. Virtual reality (VR) is an emerging technology which offers exciting prospects for teaching and learning, especially for imparting practical skills. We document here a multidisciplinary experimental study in which a bespoke VR crime scene app was designed and implemented, after which it was tested by both undergraduate student and staff/postgraduate student cohorts. Through both qualitative and quantitative analyses, we demonstrate that VR applications support learning of practical crime scene processing skills. VR-based practical sessions have the potential to add value to forensic science courses through offering cost-effective practical experience and the ability to work in isolation, in a variety of different scenarios. Both user groups reported high levels of satisfaction with the process and reports of adverse effects (motion sickness) were minimal. With reference to user feedback, we proceed to evaluate the scalability and development challenges associated with large-scale implementation of VR as an adjunct to forensic science education.

Dogs are considered property under UK law, while current discourses of pet ownership place canine companions as part of an extended family. This means sentences for those who steal dogs are not reflective of a dogs’ sentience and agency, rather reflecting the same charges for those who steal a laptop or wallet. This is particularly problematic as dog theft is currently on the rise in England and Wales and led to public calls to change the law. Recognizing that a more robust analysis of dog theft crime statistics is required, we gathered dog theft data for 2015, 2016 and 2017 from 37 of 44 police forces through FOI requests. This paper uses this data to examine how dog theft crime statistics are constructed; assesses the strengths and weaknesses of this data; and categorizes, maps and measures dog theft changes temporally per police force in England and Wales. Our findings reveal there has been an increase in dog theft crimes, 1,294 in 2015, 1,525 in 2016 (+17.85%), and 1,678 in 2017 (+10.03%); and a decrease in court charges related to dog theft crimes, 62 (4.7%) in 2015, 48 (3.14%) in 2016, 37 (2.2%) in 2017. There were police force inconsistencies in recording dog theft crime which meant some data was unusable or could not be accessed or analysed. There is a need for a qualitative study to understand dog theft crime in different areas, and standardised approach to recording the theft of a dog by all forces across England and Wales.

The full impact of COVID-19 on policing, crime and disorder is slowly being fully unraveled. However, there remains a number of areas of policing that are yet to be examined in detail. Two of these areas include the impact on the intrinsically linked, volume of police recorded intelligence reports, and the use of stop and search. In this study we examine them symbiotically and frame them in the context of the intelligence led policing model, in particular in an effort to understand how national lockdowns in the United Kingdom affected both proactive policing approaches and the underpinning intelligence cycle. To achieve this, we use data from freedom of information requests regarding the annual levels of recorded police intelligence over a 10-year period for 20 police services. To supplement this, we examine overall national monthly volumes of stop and search activity over a 5-year period. Finally, we then use a case study approach of 3 police services to further explore changes in the conduct of stop and search such as the officer defined ethnicity, grounds for search and disposal outcomes. The findings indicate that both recorded intelligence reports and stop and search increased dramatically during periods of lockdown, despite widespread decreases in crime and social mobility. Changes in proportional impact are identified for White and Black citizens, searches for controlled drugs and the no further action disposal, but these are not consistent across police services. Potential causes and implications are then discussed and again, framed within the context of the impact on the intelligence led policing model and wider policing environment.

Streets are primary elements through which the character of urban neighborhoods are experienced and expressed. The “sense of safety” in neighborhood streets is paramount to social and psychological wellbeing of its residents and visitors. The intention of this study was to explore environmental and social cues of a neighborhood, which evoke fear of crime, which will help designers to prevent the generation of such negative feelings and promote more safe and comfortable spaces in our cities. This study used interviews, group discussions and observations to identify fear-generating factors with a sample of participants in the multi ethnic neighborhood of Kotahena in Colombo, Sri Lanka. Field data was analyzed through visual documentation and photographic surveys. Moreover, group discussions, interviews and personal observations were used to synergize the study objectives. The findings inform that fear of crime on streets is influenced by both environmental and social cues to varying degrees. Feelings of fear were associated with gender, ethnicity and less familiarity with the place as participants were from an ethnic minority within the community. Literature has emphasized that fear of crime has a connection to actual crime locations. The research findings, however, indicate that fear of crime spots identified by the residents do not have a direct relationship to the actual crime locations.

The language we use to describe the past can have a strong influence on the audience’s interpretation of our story. In our experiment, we explore, using 3 different conditions, how the framing and language of an accident report can affect the audience’s proposed solutions to manage the problems found. We find that the approach used to create an accident report can have a powerful influence on the audience’s decision making. Whether we are describing an accident in a similar manner to a crime, using a systems approach or we are accepting of multiple stories which are not linear or coherent, the methods we use to capture and communicate the story have a profound impact on the actions decided upon by the reader.

Human footprint is having a unique set of ridges unmatched by any other human being, and therefore it can be used in different identity documents for example birth certificate, Indian biometric identification system AADHAR card, driving license, PAN card, and passport. There are many instances of the crime scene where an accused must walk around and left the footwear impressions as well as barefoot prints and therefore it is very crucial to recovering the footprints to identify the criminals. Footprint-based biometric is a considerably newer technique for personal identification. Fingerprints, retina, iris and face recognition are the methods most useful for attendance record of the person. This time world is facing the problem of global terrorism. It is challenging to identify the terrorist because they are living as regular as the citizens do. Their soft target includes the industries of special interests such as defense, silicon and nanotechnology chip manufacturing units, pharmacy sectors. They pretend themselves as religious persons, so temples and other holy places, even in markets is in their targets. These are the places where one can obtain their footprints easily. The gait itself is sufficient to predict the behaviour of the suspects. The present research is driven to identify the usefulness of footprint and gait as an alternative to personal identification.

Nonparametric assessments of police technical and scale efficiency is challenging because of the stochastic nature of criminal behavior and because of the subjective dependence on multiple decision criteria, which can lead to a more or less efficiency prospect depending on the regulation, necessity, or organizational objective. There is a trade-off between efficiency and effectiveness in many police performance assessments, i.e., efficient departments (producing more clear-ups with a given resource) are crime-specialized or cannot reproduce those good results effectively on more severe or complex occurrences. This study proposes a combined methodology for carrying out efficiency and effectiveness analysis of Police departments. A conditional non-parametric approach, which allows to include crime as an external factor in the analysis, is combined with a non-compensatory ranking based on the PROMETHEE II methodology for the approach illustrated on the multidimensional efficiency and effectiveness comparison of 145 Pernambuco (Brazil)'s police departments. The application results offer compelling perspectives for public administrations concerning the strategic prioritization of units for rewards or interventions.

Maintaining a healthy cyber society is a big challenge due to the users’ freedom of expression and behaving. It can be solved by monitoring and analyzing the users’ behavior and taking proper actions towards them. This research aims to present a platform that monitors the public content on Twitter by extracting tweet data. After maintaining the data, the users’ interactions are analyzed using Graph Analysis methods. Then the users’ behavioral patterns are analyzed by applying Metadata Analysis, in which the timeline of each profile is obtained; also, the time-series behavioral features of users are investigated. Then in the Abnormal Behavior Detection Filtering component, the interesting profiles are selected for further examinations. Finally, in the Contextual Analysis component, the contents will be analyzed using natural language processing techniques; A binary text classification model (SVM + TF-IDF with 88.89% accuracy) for detecting if the tweet is related to crime or not. Then, a sentiment analysis method is applied to the crime-related tweets to perform aspect-based sentiment analysis (DistilBERT + FFNN with 80% accuracy); because sharing positive opinions about a crime-related topic can threaten society. This platform aims to provide the end-user (Police) suggestions to control hate speech or terrorist propaganda.