1. Abstract

Crime analysis plays an important role in understanding public safety issues and identifying patterns in criminal activities. Law enforcement agencies use data analysis techniques to monitor crime rates, identify high-risk areas, and develop strategies to reduce crime. With the help of business intelligence tools such as Power BI, large crime datasets can be analysed and visualized effectively.

This project focuses on analysing crime data from Chicago using Power BI. The dataset used in this project is a public real-world dataset containing records of crime incidents reported in the city of Chicago. The data is collected for three different years: 2014, 2015, and 2016. By analysing these datasets, the project aims to compare crime patterns across different years.

The data contains various attributes such as date, time, location, type of crime, arrest status, district number, and geographical coordinates. Before performing analysis, the data is cleaned using Power Query Editor by splitting date and time, removing unnecessary columns, and verifying missing values.

After preprocessing, Power BI visualizations are created to analyse crime types, locations where crimes occur most frequently, and the number of arrests made. The project demonstrates how data visualization can help understand crime patterns and support better decision-making for public safety.

2.Objectives

The main objectives of this project are:

1. To analyse crime data from Chicago for the years 2014, 2015, and 2016.
2. To compare crime statistics across multiple years.
3. To identify the most common types of crimes.
4. To analyse the locations where crimes occur most frequently.
5. To examine arrest records related to different crimes.
6. To perform data cleaning and preprocessing using Power Query Editor.
7. To create meaningful visualizations using Power BI dashboards.

3. Existing System

In traditional crime analysis systems, data is often analysed using manual methods or basic tools such as spreadsheets and static reports. These approaches make it difficult to analyse large crime datasets and detect patterns.

Limitations of the Existing System

1. Manual analysis requires significant time and effort.
2. Large crime datasets are difficult to process manually.
3. Limited visualization capabilities.
4. Difficult to compare crime trends across multiple years.
5. Lack of interactive dashboards for decision-making.

Because of these limitations, modern business intelligence tools like Power BI are required to analyse crime datasets efficiently.

4. Proposed System

The proposed system uses Power BI to analyse crime incidents in Chicago across multiple years.

In this system:

1. Crime datasets from 2014, 2015, and 2016 are imported into Power BI.
2. Data is cleaned using Power Query Editor.
3. Date and time information are separated for better analysis.
4. Unnecessary columns such as identification codes are removed.
5. Important variables such as crime type, location description, arrest status, district number, and geographic coordinates are retained.
6. Relationships between the datasets are established.
7. Interactive visualizations are created to compare crime trends.

This system enables better understanding of crime patterns and helps identify high-risk locations.

5. Implementation Procedure

The implementation process includes the following steps:

Step 1: Data Collection

The crime dataset is obtained from a public data source containing real crime records from Chicago. The data is stored in three tables representing the years 2014, 2015, and 2016.

Step 2: Data Import

The datasets are imported into Power BI Desktop. The Transform Data option is used to open the Power Query Editor for preprocessing.

Step 3: Data Understanding

The dataset contains several important attributes including:

1. Date and Time – When the crime occurred
2. Block – Location block where the crime occurred
3. Primary Type – Category of crime
4. Description – Details about the crime incident
5. Location Description – Crime scene location
6. Arrest – Indicates whether an arrest was made
7. Domestic – Indicates whether the crime was domestic
8. District – Police district number
9. Latitude and Longitude – Geographic location of the crime

Step 4: Data Cleaning

Data preprocessing includes:

1. Splitting the date and time into separate columns
2. Removing unnecessary columns such as IUCR code, FBI code, and other unused identifiers
3. Checking and handling null values
4. Standardizing column names across all three datasets

 Step 5: Data Integration

The three datasets (2014, 2015, 2016) are prepared with identical column structures so that comparisons between years can be performed.

Relationships between the tables are established within Power BI.

Step 6: Data Visualization

Several visualizations are created to analyse the data, such as:

1. Crime counts by year
2. Most common crime types
3. Crime distribution across districts
4. Arrest vs non-arrest cases
5. Crime locations using latitude and longitude

 Step 7: Dashboard Creation

An interactive Power BI dashboard is created to display key crime insights including:

1. Crime trends across years
2. Location-based crime analysis
3. Arrest statistics
4. Crime category distribution

This dashboard allows users to explore crime data dynamically.

6. Software Requirements

The software used in this project includes:

1. Power BI Desktop – Data visualization and analysis
2. Power Query Editor – Data cleaning and transformation
3. Microsoft Excel / CSV files – Dataset storage format
4. Windows Operating System

7. Hardware Requirements

Minimum hardware requirements include:

1. Processor: Intel i3 or higher
2. RAM: 4 GB minimum (8 GB recommended)
3. Storage: 256 GB or higher
4. System: Laptop or Desktop computer
5. Advantages of the Project
6. Helps analyse real-world crime data efficiently.
7. Identifies crime trends across multiple years.
8. Helps detect areas with high crime rates.
9. Provides interactive dashboards for better visualization.
10. Supports law enforcement agencies in decision-making.
11. Simplifies large datasets into understandable insights.
12. Demonstrates the use of Power BI for public safety data analysis.