Crime isn't a topic most people want to use mental energy to think about. We want to avoid harm, protect our loved ones, and hold on to what we claim is ours. So how do we remain vigilant without digging too deep into the filth that is crime? Data, of course. The focus of our study is to explore possible trends between crime and communities in the city of Calgary. Our purpose is visualize Calgary criminal behaviour in order to help increase awareness for both citizens and law enforcement. Through the use of our visuals, individuals can make more informed decisions to improve the overall safety of their lives. Some of the main concerns of the study include: how crime rates increase with population, which areas in Calgary have the most crime, and if crime adheres to time-sensative patterns.

Description: This dataset contains detailed records of crimes reported across various regions from 2020 to the present. It provides valuable insights into crime trends, patterns, and changes in crime rates over time. The data is suitable for researchers, data analysts, law enforcement agencies, and policymakers looking to analyze crime dynamics or develop predictive models to enhance public safety measures.

Applications:

Trend Analysis: Identify seasonal or yearly patterns in crime rates.

Predictive Modeling: Develop machine learning models to forecast high-risk areas.

Policy Planning: Support policymakers in designing targeted crime prevention strategies.

Visualization Projects: Create heatmaps, dashboards, and visual reports for crime data.

Prelude

This dataset is a cleaned version of the Chicago Crime Dataset, which can be found here. All rights for the dataset go to the original owners. The purpose of this dataset is to display my skills in visualizations and creating dashboards. To be specific, I will attempt to create a dashboard that will allow users to see metrics for a specific crime within a given year using filters and metrics. Due to this, there will not be much of a focus on the analysis of the data, but there will be portions discussing the validity of the dataset, the steps I took to clean the data, and how I organized it. The cleaned datasets can be found below, the Query (which utilized BigQuery) can be found here and the Tableau dashboard can be found here.

About the Dataset

Important Facts

The dataset comes directly from the City of Chicago's website under the page "City Data Catalog." The data is gathered directly from the Chicago Police's CLEAR (Citizen Law Enforcement Analysis and Reporting) and is updated daily to present the information accurately. This means that a crime on a specific date may be changed to better display the case. The dataset represents crimes starting all the way from 2001 to seven days prior to today's date.

Reliability

Using the ROCCC method, we can see that: * The data has high reliability: The data covers the entirety of Chicago from a little over 2 decades. It covers all the wards within Chicago and even gives the street names. While we may not have an idea for how big the sample size is, I do believe that the dataset has high reliability since it geographically covers the entirety of Chicago. * The data has high originality: The dataset was gained directly from the Chicago Police Dept. using their database, so we can say this dataset is original. * The data is somewhat comprehensive: While we do have important information such as the types of crimes committed and their geographic location, I do not think this gives us proper insights as to why these crimes take place. We can pinpoint the location of the crime, but we are limited by the information we have. How hot was the day of the crime? Did the crime take place in a neighborhood with low-income? I believe that these key factors prevent us from getting proper insights as to why these crimes take place, so I would say that this dataset is subpar with how comprehensive it is. * The data is current: The dataset is updated frequently to display crimes that took place seven days prior to today's date and may even update past crimes as more information comes to light. Due to the frequent updates, I do believe the data is current. * The data is cited: As mentioned prior, the data is collected directly from the polices CLEAR system, so we can say that the data is cited.

Processing the Data

Cleaning the Dataset

The purpose of this step is to clean the dataset such that there are no outliers in the dashboard. To do this, we are going to do the following: * Check for any null values and determine whether we should remove them. * Update any values where there may be typos. * Check for outliers and determine if we should remove them.

The following steps will be explained in the code segments below. (I used BigQuery for this so the coding will follow BigQuery's syntax) ```

Examining the dataset

There are over 7.5 million rows of data

Putting a limit so it does not take a long time to run

SELECT * FROM portfolioproject-350601.ChicagoCrime.Crime LIMIT 1000;

Seeing which points are null

There are 85,000 null points so we can exclude them as it's not a significant amount since it is only ~1.3% of the dataset

Most of the null points are in the lat and long, which we will need later

Because we don't have the full address, we can't estimate the lat and long in SQL so we will have to delete the rows with Null Data

SELECT * FROM portfolioproject-350601.ChicagoCrime.Crime WHERE unique_key IS NULL OR case_number IS NULL OR date IS NULL OR primary_type IS NULL OR location_description IS NULL OR arrest IS NULL OR longitude IS NULL OR latitude IS NULL;

Deleting all null rows

DELETE FROM portfolioproject-350601.ChicagoCrime.Crime WHERE
unique_key IS NULL OR case_number IS NULL OR date IS NULL OR primary_type IS NULL OR location_description IS NULL OR arrest IS NULL OR longitude IS NULL OR latitude IS NULL;

Checking for any duplicates in the unique keys

None to be found

SELECT unique_key, COUNT(unique_key) FROM `portfolioproject-350601.ChicagoCrime....

This dataset contains official crime records reported in Los Angeles City from January 2020 to December 2023.

The data provides valuable information about reported crimes, including the date, area, crime details, victim information, premises, weapons used, and status.

If you find this dataset valuable, don't forget to hit the upvote button! 😊💝

Checkout my top datasets

• Top Spotify Songs in 73 Countries
• Wages by Education in the USA
• Amazon Products Dataset (1.4M Products)
• TMDB 950K Movies
• Amazon Kindle Books (130K Books)

Interesting Task Ideas:

1. Analyze the temporal patterns of crimes in different areas of Los Angeles City.
2. Identify the most common crimes.
3. Explore the correlation between victim age and crime types.
4. Investigate the crime rates in different areas of the city.
5. Examine the relationship between premises and specific crime codes.
6. Visualize the distribution of crimes on a map of Los Angeles City.
7. Analyze the relationship between crime status and occurrence location.
8. Use machine learning techniques to predict crime categories based on available features.

In a world of increasing crime, many organizations are interested in examining incident details to learn from and prevent future crime. Our client, based in Los Angeles County, was interested in this exact thing. They asked us to examine the data to answer several questions; among them, what was the rate of increase or decrease in crime from 2020 to 2023, and which ethnicity or group of people were targeted the most.

Our data was collected from Kaggle.com at the following link:

https://www.kaggle.com/datasets/nathaniellybrand/los-angeles-crime-dataset-2020-present

It was cleaned, examined for further errors, and the analysis performed using RStudio. The results of this analysis are in the attached PDF entitled: "crime_data_analysis_report." Please feel free to review the results as well as follow along with the dataset on your own machine.

The RMS Crime Incidents dataset consists of crime reports from the Detroit Police Department Records Management System (RMS). This data reflects criminal offenses reported in the City of Detroit that DPD was involved in from December 2016 to present. Note that records are included in the dataset based on when an incident is reported which could result in an occurrence date before December 2016. Incident data is typically entered into mobile devices by the officer in the field when responding to an incident. Incidents that occurred in Detroit but in a location that is under the jurisdiction of the Michigan State Police (MSP) or Wayne State University Police Department (WSUPD), such as on an expressway, Belle Isle, or around Wayne State University, are included only if the incident is handled by DPD. Such records are reviewed in a monthly audit to ensure that the incidents are counted by one and only one agency (MSP or DPD). This data is updated daily. For each crime incident, one or more offense charges are recorded, and each row in the dataset corresponds with one of these charges. An example could be a domestic assault where property was also vandalized. Offense charges that occurred at the same crime incident share a common incident number. For each offense charge record (rows)details include when and where the incident occurred, the nature of the offense, DPD precinct or detail, and the case investigation status. Locations of incidents associated with each call are reported based on the nearest intersection to protect the privacy of individuals.RMS Crime Incident data complies with Michigan Incident Crime Reporting (MICR) standards. More information about MICR standards is available via the MICR Website. The Manual and Arrest Charge Code Card may be especially helpful. There may be small differences between RMS Crime Incident data shared here and data shared through MICR given data presented here is updated here more frequently which results in a difference in a cadence of status updates. Additionally, this dataset includes crime incidents that following an investigation are coded with a case status of ‘Unfounded’. In most cases, this means that the incident occurred outside the jurisdiction of DPD or otherwise was reported in error. The State of Michigan, through the MICR program, reports data to the National Incident-Based Reporting System (NIBRS).Yearly Datasets for RMS Crime Incidents have been added to the ODP. This is to improve the user's experience in handling the large file size of the records in the comprehensive dataset. You may download each year separately, which significantly reduces the size and records for each file. In addition to the past years, we have also included a year-to-date dataset. This captures all RMS Crime Incidents from January 1, 2025, to present.Should you have questions about this dataset, you may contact the Commanding Officer of the Detroit Police Department's Crime Data Analytics at 313-596-2250 or CrimeIntelligenceBureau@detroitmi.gov.

Crime Analytics Tool Market Outlook

The global crime analytics tool market size was valued at approximately USD 5.4 billion in 2023 and is projected to reach around USD 12.1 billion by 2032, growing at a CAGR of 9.5% during the forecast period. The substantial growth in the crime analytics tool market can be attributed to the increasing adoption of advanced technologies by law enforcement agencies and the rising incidences of crime globally, which necessitates more sophisticated methods of crime prevention and analysis.

One of the main growth factors driving the crime analytics tool market is the rapid technological advancements in big data analytics and artificial intelligence (AI). These technologies are being increasingly integrated into crime analytics tools, providing law enforcement agencies with powerful capabilities to analyze vast amounts of data quickly and accurately. Additionally, the proliferation of smart city initiatives across the globe is further fueling the demand for these tools, as they play a crucial role in enhancing the security infrastructure of urban environments. The ability of crime analytics tools to predict and prevent criminal activities by analyzing patterns and trends is proving to be invaluable in maintaining public safety.

Another significant driver of market growth is the increasing collaboration between public and private sectors in enhancing security measures. With the rise in cybercrimes and terrorism, both government agencies and private security firms are investing heavily in advanced crime analytics solutions. This collaboration is not only improving the overall effectiveness of crime prevention strategies but also driving innovations within the market. Furthermore, the growing awareness among law enforcement agencies about the benefits of crime analytics tools, such as improved response times and resource allocation, is contributing to the market's expansion.

The integration of Internet of Things (IoT) devices and surveillance systems with crime analytics tools is also propelling the market forward. IoT devices generate massive amounts of data that can be analyzed to gain insights into potential threats and criminal activities. By incorporating data from various sources such as CCTV footage, social media, and other digital platforms, crime analytics tools can provide a comprehensive overview of the security landscape, aiding in more effective decision-making. This holistic approach to crime prevention is becoming increasingly essential in today's interconnected world.

Regionally, North America holds the largest market share due to the early adoption of advanced technologies and the presence of several key players in the region. The strong focus on homeland security and substantial investments in public safety infrastructure are also contributing factors. Europe follows closely, with significant growth driven by stringent regulations and increasing efforts to combat organized crime. The Asia Pacific region is expected to witness the highest CAGR during the forecast period, fueled by rapid urbanization, increasing crime rates, and significant government investments in smart city projects. Latin America and the Middle East & Africa are also expected to see notable growth, driven by improving economic conditions and heightened security concerns.

Component Analysis

The crime analytics tool market is segmented into three primary components: software, hardware, and services. The software component dominates the market, driven by the increasing demand for advanced analytical solutions capable of processing large datasets and generating actionable insights. Crime analytics software includes various applications such as predictive analytics, data mining, and visualization tools that enable law enforcement agencies to identify crime patterns and trends effectively. The continuous advancements in AI and machine learning algorithms are further enhancing the capabilities of these software solutions, making them indispensable tools for modern crime prevention.

Hardware components, although smaller in market share compared to software, play a crucial role in the overall crime analytics ecosystem. This segment includes surveillance cameras, sensors, and other IoT devices that collect real-time data essential for comprehensive crime analysis. The integration of high-definition cameras, facial recognition systems, and biometric devices with crime analytics software is significantly improving the accuracy and efficiency of crime detection and prevention efforts. As the demand for robust security infrastructure continues to rise,

Investigator(s): Federal Bureau of Investigation Since 1930, the Federal Bureau of Investigation (FBI) has compiled the Uniform Crime Reports (UCR) to serve as periodic nationwide assessments of reported crimes not available elsewhere in the criminal justice system. With the 1977 data, the title was expanded to Uniform Crime Reporting Program Data. Each year, participating law enforcement agencies contribute reports to the FBI either directly or through their state reporting programs. ICPSR archives the UCR data as five separate components: (1) summary data, (2) county-level data, (3) incident-level data (National Incident-Based Reporting System [NIBRS]), (4) hate crime data, and (5) various, mostly nonrecurring, data collections. Summary data are reported in four types of files: (a) Offenses Known and Clearances by Arrest, (b) Property Stolen and Recovered, (c) Supplementary Homicide Reports (SHR), and (d) Police Employee (LEOKA) Data (Law Enforcement Officers Killed or Assaulted). The county-level data provide counts of arrests and offenses aggregated to the county level. County populations are also reported. In the late 1970s, new ways to look at crime were studied. The UCR program was subsequently expanded to capture incident-level data with the implementation of the National Incident-Based Reporting System. The NIBRS data focus on various aspects of a crime incident. The gathering of hate crime data by the UCR program was begun in 1990. Hate crimes are defined as crimes that manifest evidence of prejudice based on race, religion, sexual orientation, or ethnicity. In September 1994, disabilities, both physical and mental, were added to the list. The fifth component of ICPSR's UCR holdings is comprised of various collections, many of which are nonrecurring and prepared by individual researchers. These collections go beyond the scope of the standard UCR collections provided by the FBI, either by including data for a range of years or by focusing on other aspects of analysis. NACJD has produced resource guides on UCR and on NIBRS data.

The global market for crime analytics tools is experiencing robust growth, driven by the increasing need for efficient law enforcement and proactive crime prevention strategies. The rising adoption of advanced technologies like artificial intelligence (AI), machine learning (ML), and big data analytics is transforming crime analysis, enabling predictive policing, improved resource allocation, and faster response times. This market is segmented by application (police stations, schools, research institutes) and deployment type (cloud-based, on-premises). Cloud-based solutions are gaining traction due to their scalability, cost-effectiveness, and ease of access. Key players like LexisNexis, IBM, and Motorola Solutions are driving innovation and market penetration through their comprehensive software suites and services. The North American market currently holds a significant share, owing to advanced technological infrastructure and increased government spending on public safety. However, the Asia-Pacific region is projected to witness rapid growth in the coming years, fuelled by rising urbanization, increasing crime rates, and the adoption of sophisticated crime analytics solutions. While data privacy concerns and the high initial investment costs present certain restraints, the overall market outlook remains optimistic. The forecast period (2025-2033) indicates continued expansion, driven by factors like improved data integration capabilities, the growing availability of crime-related datasets, and the increasing sophistication of analytical algorithms. The competitive landscape is characterized by both established players and emerging technology providers. The market is poised for further consolidation as companies expand their product portfolios and geographical reach. The development of specialized solutions tailored to specific crime types and geographical regions will be a key growth driver. Furthermore, the integration of crime analytics with other smart city initiatives will unlock new opportunities for market expansion. Government initiatives aimed at enhancing public safety and promoting the use of technology in law enforcement will also contribute to market growth.

The global crime analytics software market is expected to grow at CAGR of 8.2% for the forecast period 2023-2030.

Growing demand for effective crime prevention and reduction techniques due to rising crime rate is expected to drive the growth of the crime analytics software market
North America dominates the crime analytics software market

Key Dynamics of Crime Analytics Software Market.

Key Drivers of Crime Analytics Software Market.

Increasing Urban Crime Rates and Concerns for Public Safety: As urban populations expand and criminal activities become more sophisticated, law enforcement agencies face mounting pressure to take proactive measures. The use of crime analytics software facilitates real-time monitoring, predictive policing, and data-driven decision-making, all aimed at enhancing public safety and optimizing resource allocation.

Government and Law Enforcement Agency Adoption: Across various regions, governments are making significant investments in smart policing infrastructure. Crime analytics tools are being incorporated into national security and policing frameworks to identify patterns, anticipate threats, and enable quicker responses. Such investments are a major driver of market growth.

Advancements in AI, Big Data, and Geospatial Technologies: The advancement of artificial intelligence, machine learning, and GIS technologies significantly boosts the capabilities of crime analytics software. These innovations support real-time crime mapping, recognition of behavioral patterns, and the generation of actionable insights, which contribute to more effective crime prevention and resolution.

Key Restrains for Crime Analytics Software Market.

Concerns Regarding Data Privacy and Ethics: The utilization of personal data for predictive analytics raises critical issues related to surveillance, bias, and civil liberties. Any misuse or lack of transparency in data collection and analysis can result in legal challenges and public discontent.

High Costs of Implementation and Integration: The deployment of crime analytics systems necessitates substantial investment in hardware, software, training, and data infrastructure. For smaller municipalities or agencies with constrained budgets, the significant initial and ongoing expenses may hinder or restrict adoption.

Challenges of Inconsistent Data Sources and System Fragmentation: Crime data is frequently sourced from various entities—law enforcement, public safety, social media, etc.—which may not adhere to standardization or interoperability. This fragmentation can impede data accuracy and the overall effectiveness of crime analysis platforms.

Key Trends in Crime Analytics Software Market.

Increasing Adoption of Predictive Policing Models: Law enforcement agencies are progressively utilizing predictive analytics to identify potential crime hotspots and strategically deploy officers. These models analyze historical crime data, along with factors such as time, location, and environmental conditions, to predict incidents and mitigate crime rates.

Integration with Body Cameras and Surveillance Systems: Crime analytics systems are being combined with live video feeds, CCTV networks, and body-worn cameras. This integration facilitates real-time monitoring, evidence gathering, and automated identification of suspects, thereby improving overall situational awareness.

Expansion of Cloud-Based and Mobile Solutions: Cloud-based and mobile-compatible crime analytics applications provide remote access, enable collaboration across different jurisdictions, and offer real-time data updates. These solutions are becoming increasingly favored due to their scalability, cost-effectiveness, and enhanced operational flexibility for law enforcement agencies.

The COVID-19 impact on the Crime Analytics Software Market.

The COVID-19 pandemic has had a significant impact on the crime analytics software market, resulting in both challenges and opportunities for the industry. The most immediate impact of the pandemic was the widespread imposition of travel restrictions, lockdowns, and quarantines. Due to the lockdowns, social distancing measures, and changes in daily routines, the burglary and street-level crimes have noticed some reduction. Crime analytics software would have been crucial in identifying and analysing these shifts. Remote work became essential during the pandemic, including for law enforcement agencies....

This dataset reflects reported incidents of crime (with the exception of murders where data exists for each victim) that have occurred in the City of Chicago over the past year, minus the most recent seven days of data. Data is extracted from the Chicago Police Department's CLEAR (Citizen Law Enforcement Analysis and Reporting) system. In order to protect the privacy of crime victims, addresses are shown at the block level only and specific locations are not identified. Should you have questions about this dataset, you may contact the Research & Development Division of the Chicago Police Department at 312.745.6071 or RandD@chicagopolice.org. Disclaimer: These crimes may be based upon preliminary information supplied to the Police Department by the reporting parties that have not been verified. The preliminary crime classifications may be changed at a later date based upon additional investigation and there is always the possibility of mechanical or human error. Therefore, the Chicago Police Department does not guarantee (either expressed or implied) the accuracy, completeness, timeliness, or correct sequencing of the information and the information should not be used for comparison purposes over time. The Chicago Police Department will not be responsible for any error or omission, or for the use of, or the results obtained from the use of this information. All data visualizations on maps should be considered approximate and attempts to derive specific addresses are strictly prohibited.

The Chicago Police Department is not responsible for the content of any off-site pages that are referenced by or that reference this web page other than an official City of Chicago or Chicago Police Department web page. The user specifically acknowledges that the Chicago Police Department is not responsible for any defamatory, offensive, misleading, or illegal conduct of other users, links, or third parties and that the risk of injury from the foregoing rests entirely with the user. The unauthorized use of the words "Chicago Police Department," "Chicago Police," or any colorable imitation of these words or the unauthorized use of the Chicago Police Department logo is unlawful. This web page does not, in any way, authorize such use. Data is updated daily Tuesday through Sunday. The dataset contains more than 65,000 records/rows of data and cannot be viewed in full in Microsoft Excel. Therefore, when downloading the file, select CSV from the Export menu. Open the file in an ASCII text editor, such as Wordpad, to view and search. To access a list of Chicago Police Department - Illinois Uniform Crime Reporting (IUCR) codes, go to http://bit.ly/rk5Tpc.

Gain critical insights into crime trends, risk assessment, and public safety with our comprehensive Crime Dataset. Designed for law enforcement agencies, researchers, and analysts, this dataset provides structured and reliable crime data to support investigations, policy-making, and crime prevention strategies.

Dataset Features

Crime Reports: Access detailed records of reported crimes, including incident type, date, time, and location. Law Enforcement Data: Extract information on arrests, case statuses, and law enforcement responses. Geospatial Crime Mapping: Analyze crime distribution across different regions, cities, and neighborhoods. Trends & Patterns: Identify crime trends over time, including seasonal fluctuations and high-risk areas. Demographic Insights: Understand crime demographics, including offender and victim profiles.

Customizable Subsets for Specific Needs Our Crime Dataset is fully customizable, allowing you to filter data based on crime type, location, time period, or law enforcement jurisdiction. Whether you need broad coverage for national crime analysis or focused data for local risk assessment, we tailor the dataset to your needs.

Popular Use Cases

Crime Risk Assessment & Prevention: Identify high-crime areas, assess risk factors, and develop crime prevention strategies. Law Enforcement & Investigations: Support law enforcement agencies with structured crime data for case analysis and intelligence gathering. Urban Planning & Public Safety: Use crime data to inform city planning, improve public safety measures, and allocate resources effectively. AI & Predictive Analytics: Train AI models for crime forecasting, anomaly detection, and predictive policing. Policy & Legal Research: Analyze crime trends to support policy-making, legal studies, and criminal justice reforms.

Whether you're analyzing crime trends, supporting law enforcement, or developing predictive models, our Crime Dataset provides the structured data you need. Get started today and customize your dataset to fit your research and security objectives.

The Regional Crime Analysis GIS (RCAGIS) is an Environmental Systems Research Institute (ESRI) MapObjects-based system that was developed by the United States Department of Justice Criminal Division Geographic Information Systems (GIS) Staff, in conjunction with the Baltimore County Police Department and the Regional Crime Analysis System (RCAS) group, to facilitate the analysis of crime on a regional basis. The RCAGIS system was designed specifically to assist in the analysis of crime incident data across jurisdictional boundaries. Features of the system include: (1) three modes, each designed for a specific level of analysis (simple queries, crime analysis, or reports), (2) wizard-driven (guided) incident database queries, (3) graphical tools for the creation, saving, and printing of map layout files, (4) an interface with CrimeStat spatial statistics software developed by Ned Levine and Associates for advanced analysis tools such as hot spot surfaces and ellipses, (5) tools for graphically viewing and analyzing historical crime trends in specific areas, and (6) linkage tools for drawing connections between vehicle theft and recovery locations, incident locations and suspects' homes, and between attributes in any two loaded shapefiles. RCAGIS also supports digital imagery, such as orthophotos and other raster data sources, and geographic source data in multiple projections. RCAGIS can be configured to support multiple incident database backends and varying database schemas using a field mapping utility.

Investigator(s): United Nations Office at Vienna, R.W. Burnham, Helen Burnham, Bruce DiCristina, and Graeme Newman The United Nations Surveys of Crime Trends and Operations of Criminal Justice Systems (formerly known as the United Nations World Crime Surveys) series was begun in 1978 and is comprised of five quinquennial surveys covering the years 1970-1975, 1975-1980, 1980-1986, 1986-1990, and 1990-1994. The project was supported by the United States Bureau of Justice Statistics, and conducted under the auspices of the United Nations Criminal Justice and Crime Prevention Branch, United Nations Office in Vienna. Data gathered on crime prevention and criminal justice among member nations provide information for policy development and program planning. The main objectives of the survey include: to conduct a more focused inquiry into the incidence of crime worldwide, to improve knowledge about the incidence of reported crime in the global development perspective and also international understanding of effective ways to counteract crime, to improve the dissemination globally of the information collected, to facilitate an overview of trends and interrelationships among various parts of the criminal justice system so as to promote informed decision-making in its administration, nationally and cross-nationally, and to serve as an instrument for strengthening cooperation among member states by putting the review and analysis of national crime-related data in a broader context. The surveys also provide a valuable source of charting trends in crime and criminal justice over two decades.

This study examines the relationship between socio-economic factors and crime distribution using a dataset that includes variables such as unemployment rates, literacy rates, per capita income, and population density. The analysis explores how these factors influence crime rates across different regions, comparing urban and rural areas to identify variations in crime patterns due to economic and social disparities. Additionally, the study investigates cultural and psychological influences on criminal activities. The findings offer valuable insights for policymakers to develop more effective crime prevention strategies.This dataset supports the manuscript ‘Crime and Socio-Economic Inequalities: Leveraging Deep Learning and Generative AI for Comprehensive Analysis.’ It includes:- CrimeEconomicsData.csv: Original dataset with 114 observations across 10 socio-economic variables (Per Capita Income, Population Density, Unemployment, Literacy Rate, Happiness Index, Crime Rate).- supplementary_data.zip: Contains: - table_ii_metrics.csv: Performance metrics (Accuracy, Precision, Recall, F1-Score, ROC-AUC) for machine learning and deep learning models in Table II. - figure_2_confusion_matrices.csv: Confusion matrix data for each model, supporting Figure 2’s visualizations. - README.txt: Description of the files and their purpose.Preprocessed datasets are not included, as preprocessing steps (e.g., mean imputation, standardization, PCA) are detailed in the manuscript and can be replicated using CrimeEconomicsData.csv.

The data are provided are the Maryland Statistical Analysis Center (MSAC), within the Governor's Office of Crime Control and Prevention (GOCCP). MSAC, in turn, receives these data from the Maryland State Police's annual Uniform Crime Reports.

The Law Enforcement Agency Reported Crime Analysis Tool (LEARCAT) dashboard enables users to examine crime information (incident-based data ) reported by participating law enforcement agencies to the FBI’s National Incident-Based Reporting System (NIBRS). The FBI’s Uniform Crime Reporting Program (UCR) defines an incident as one or more offenses committed by the same offender, or group of offenders, acting in concert at the same time and place. A single incident can contain multiple victims, victim types, crimes, and arrests. The NIBRS data are not nationally representative and law enforcement participation varies by state.

Evidence about the relationship between lighting and crime is mixed. Although a review of evidence found that improved road / street lighting was associated with reductions in crime, these reductions occurred in daylight as well as after dark, suggesting any effect was not due only to changes in visual conditions. One limitation of previous studies is that crime data are reported in aggregate and thus previous analyses were required to make simplifications concerning types of crimes or locations. We will overcome that by working with a UK police force to access records of individual crimes. We will use these data to determine whether the risk of crime at a specific time of day is greater after dark than during daylight. If no difference is found, this would suggest improvements to visual conditions after dark through lighting would have no effect. If however the risk of crime occurring after dark was greater than during daylight, quantifying this effect would provide a measure to assess the potential effectiveness of lighting in reducing crime risk after dark. We will use a case and control approach to analyse ten years of crime data. We will compare counts of crimes in ‘case’ hours, that are in daylight and darkness at different times of the year, and ‘control’ hours, that are in daylight throughout the year. From these counts we will calculate odds ratios as a measure of the effect of darkness on risk of crime, using these to answer three questions: 1) Is the risk of overall crime occurring greater after dark than during daylight? 2) Does the risk of crime occurring after dark vary depending on the category of crime? 3) Does the risk of crime occurring after dark vary depending on the geographical area?