Scientific and technical

Linking commercial burglaries by modus operandi: tests using regression and ROC analysis

One of the most common types of crime, burglary often results in serious psychological trauma and has financial consequences. Predicting burglaries is a challenging task due to their high degree of randomness. In this study, we propose predicting burglaries based on various contextual factors and incorporating these factors in a unique deep learning framework – DeePrison (DEEp learning framework for Predicting buRglarIes baSed On multiple coNtextual factors). DeePrison is able to capture the dependencies between burglaries and their different contextual factors with respect to time and space and thus provide accurate burglary prediction. Our framework incorporates multiple contextual factors derived from different sources, such as socio-demographic attributes from the US Census Bureau and weather conditions generated from the US National Weather Service. We highlight the contribution of unique contextual factors, such as historical records of criminals’ behavioral patterns. We demonstrate our method’s performance, using two large real-world datasets of burglary records from different areas in the world: Israel and New York City. DeePrison significantly outperforms the state-of-the-art solutions for different types of regions, with different granularity levels, obtaining an F1 score and AUC above 0.64 and 0.73 respectively.

Crime linkage is a difficult task and is of great significance to maintaining social security. It can be treated as a binary classification problem. Some crimes are difficult to determine whether they are serial crimes under the existing evidence, so the two-way decisions are easy to make mistakes for some case pairs. Here, the three-way decisions based on the decision-theoretic rough set are applied and its key issue is to determine thresholds by setting appropriate loss functions. However, sometimes the loss functions are difficult to obtain. In this paper, a method to automatically learn thresholds of the three-way decisions without the need to preset explicit loss functions is proposed. We simplify the loss function matrix according to the characteristic of crime linkage, re-express thresholds by loss functions, and investigate the relationship between overall decision cost and the size of the boundary region. The trade-off between the uncertainty of the boundary region and the decision cost is taken as the optimization objective. We apply multiple traditional classification algorithms as base classifiers, and employ real-world cases and some public datasets to evaluate the effect of our proposed method. The results show that the proposed method can reduce classification errors.

Offender profiling is an investigative tool used by police, consultants, and academics to identify the most likely personality, behavioral, and demographic characteristics that an offender will possess, based on an analysis of their crime scene behaviors. While offender profiling has been popularized by TV shows and movies such as Criminal Minds, Silence of the Lambs, Mindhunter, and more, the accuracy and real-world impact of OP is largely unknown. The goal of this chapter is to provide an overview of the history and current status of offender profiling, and to summarize the research on predominant offender profiling methods. This chapter also reviews the accuracy and applied impact of each approach to offender profiling, and highlights the need for an evidence-based offender profiling technique, based upon statistical and scientific methods. A discussion of the future of offender profiling, particularly in terms of scientific research and evaluations, and the implications for law enforcement investigations, are also provided, with recommendations made to improve the field of offender profiling in the future.

Crime linkage is a challenging task in crime analysis, which is to find serial crimes committed by the same offenders. It can be regarded as a binary classification task detecting serial case pairs. However, most case pairs in the real world are nonserial, so there is a serious class imbalance in the crime linkage. In this paper, we propose a novel random forest based on the information granule. The approach does not resample the minority class or the majority class but concentrates on indistinguishable case pairs at the classification boundary. The information granule is used to identify case pairs that are difficult to distinguish in the dataset and constructs a nearly balanced dataset in the uncertainty region to deal with the imbalanced problem. In the proposed approach, random trees come from the original dataset and the above mentioned nearly balanced dataset. A real-world robbery dataset and some public imbalanced datasets are employed to measure the performance of the approach. The results show that the proposed approach is effective in dealing with class imbalances, and it can be extended to combine with other methods solving class imbalances.

The traditional machine learning systems lack a pathway for a human to integrate their domain knowledge into the underlying machine learning algorithms. The utilization of such systems, for domains where decisions can have serious consequences (e.g. medical decision-making and crime analysis), requires the incorporation of human experts' domain knowledge. The challenge, however, is how to effectively incorporate domain expert knowledge with machine learning algorithms to develop effective models for better decision making.

In crime analysis, the key challenge is to identify plausible linkages in unstructured crime reports for the hypothesis formulation. Crime analysts painstakingly perform time-consuming searches of many different structured and unstructured databases to collate these associations without any proper visualization. To tackle these challenges and aiming towards facilitating the crime analysis, in this paper, we examine unstructured crime reports through text mining to extract plausible associations. Specifically, we present associative questioning based searching model to elicit multi-level associations among crime entities. We coupled this model with partition clustering to develop an interactive, human-assisted knowledge discovery and data mining scheme.

The proposed human-centered knowledge discovery and data mining scheme for crime text mining is able to extract plausible associations between crimes, identifying crime pattern, grouping similar crimes, eliciting co-offender network and suspect list based on spatial-temporal and behavioral similarity. These similarities are quantified through calculating Cosine, Jacquard, and Euclidean distances. Additionally, each suspect is also ranked by a similarity score in the plausible suspect list. These associations are then visualized through creating a two-dimensional re-configurable crime cluster space along with a bipartite knowledge graph.

This proposed scheme also inspects the grand challenge of integrating effective human interaction with the machine learning algorithms through a visualization feedback loop. It allows the analyst to feed his/her domain knowledge including choosing of similarity functions for identifying associations, dynamic feature selection for interactive clustering of crimes and assigning weights to each component of the crime pattern to rank suspects for an unsolved crime.

We demonstrate the proposed scheme through a case study using the Anonymized burglary dataset. The scheme is found to facilitate human reasoning and analytic discourse for intelligence analysis.