Introduction

• Crime data provides crucial insights for public safety planning, community awareness, and resource allocation.

• In this assignment, we explore open data from the Boston Police Department to identify patterns in criminal activity. Using R, we examine trends over time, highlight common offenses, assess district-level variation, and map crime concentrations.

• Our goal is to turn raw data into clear, visual stories that inform and guide decision-making.

• This project presents an exploratory analysis of crime data recorded between 2015 and 2018, aiming to uncover meaningful patterns across time, location, and crime types.

• By examining trends in overall crime volume by year and month, we identify key shifts in criminal activity, including a notable peak in 2017 followed by a decline.

• The analysis highlights the most common types of crimes—such as motor vehicle incidents, larceny, and medical assistance calls—and investigates how these vary seasonally and geographically. Particular attention is given to shooting incidents, with monthly trends and smoothing techniques used to reveal fluctuations over time.

• Geographic and district-level breakdowns further reveal crime hotspots and disparities in crime distribution across regions. Together, these insights support data-driven strategies for law enforcement resource allocation and policy planning aimed at improving community safety.

Yearly Crime Trend

• Crime rose significantly from 2015 to 2017, peaking in 2017.
• A noticeable decline occurred in 2018.
• Helps track effectiveness of interventions or policy shifts.

Top 10 Crime Types

• Motor Vehicle Accident Response” is the most frequent crime type.
• Medical and drug-related issues also appear prominently in the top 10.
• This breakdown helps prioritize resources toward high-frequency categories.

Crimes by Month

• July and August have the highest crime numbers, suggesting seasonal trends.
• February consistently shows the lowest counts, likely due to fewer days.
• Helps plan resource deployment across the year.

Shooting Incidents Over Time

• Monthly shooting incidents fluctuate sharply, suggesting sporadic spikes.
• The loess trendline shows a gentle rise followed by a drop post-2018.
• Useful for identifying patterns or need for intervention during specific months.

Crimes by District

• B2 and C11 districts report the most crimes, possibly due to population density or socioeconomic factors.
• Districts with lighter shades have notably fewer incidents.
• Great for geographic prioritization and area-specific intervention.

Geographic Crime Density

• Dense clusters appear in specific urban regions, suggesting crime hotspots.
• Warmer tones indicate areas needing high police presence or community programs.
• A spatial overview helps in allocating ground-level enforcement more effectively.

Conclusion

This crime data analysis provides valuable insights into the nature, distribution, and trends of criminal activity from 2015 to 2018. The study reveals a significant rise in total reported crimes leading up to 2017, followed by a measurable decline in 2018, suggesting potential shifts in enforcement strategies or reporting practices. Monthly patterns show that crimes tend to peak during the summer months, while February consistently records the fewest incidents. Analyzing the most frequent offense categories—such as motor vehicle accidents, larceny, and medical assistance—highlights recurring challenges for public safety efforts. A separate examination of shooting incidents shows fluctuations over time and emphasizes the importance of ongoing monitoring. District-wise analysis exposes disparities in crime volume, identifying high-risk zones that may benefit from targeted interventions. Finally, the geographic heat map provides a visual representation of urban crime density, pinpointing specific hotspots. Together, these findings support more informed, strategic decision-making in policing, community safety planning, and policy development.

• Overall Crime Trend: Crime incidents have fluctuated over the years, showing periods of increase and decline.
  
• Common Crime Types: Theft, Assault, and Drug Violations rank among the top reported offenses.
  
• Seasonality: Crime rates peak during certain months, indicating seasonal patterns in criminal activity.
  
• Violent Crimes: Shootings show concerning trends over time, requiring focused attention.
  
• Geographic Hotspots: Certain police districts consistently report higher crime volumes.
  
• Crime Density: Spatial analysis reveals concentrated crime clusters, highlighting priority areas for resource allocation and prevention efforts.

References

• Boston Police Department. (n.d.). CRIME INCIDENT REPORTS (AUGUST 2015 - TO DATE) (SOURCE: NEW SYSTEM). https://data.boston.gov/dataset/crime-incident-reports-august-2015-to-date-source-new-system

• Tennekes, M. (2018). tmap: Thematic maps in R. Journal of Statistical Software, 84(6), 1–39. https://doi.org/10.18637/jss.v084.i06

• Wickham, H. (2016). ggplot2: Elegant graphics for data analysis (2nd ed.). Springer. https://doi.org/10.1007/978-3-319-24277-4

• Wickham, H., & Grolemund, G. (2016). R for data science: Import, tidy, transform, visualize, and model data. O’Reilly Media. https://r4ds.hadley.nz/

• Cheshire, J., & Batty, M. (2012). The visual analysis of urban crimes using space–time cube and density maps. Environment and Planning B: Urban Analytics and City Science, 39(5), 867–883. https://doi.org/10.1068/b38155