A Querex Data Investigation

The Pulse of Boston

An interactive journey through 848,051 crime incidents spanning a decade. Machine learning meets urban safety in this deep investigation of Boston's crime patterns, predictions, and the future of public safety.

SCROLL
848K
Incidents Analyzed
12
Police Districts
10
Years of Data
0.65
DART AUC-ROC

"In the data, we find not just numbers, but the heartbeat of a city."

This investigation uses advanced analytics, machine learning, and optimization algorithms to understand crime patterns in Boston. From the spatial geography of risk to the temporal rhythms of danger, we reveal what the data tells us about public safety—and how we can predict and prevent crime before it happens.

Using LightGBM gradient boosting, iGraph network analysis, and OR-Tools vehicle routing optimization, we've built a comprehensive picture of crime in one of America's oldest cities.

The Investigation

The Big Picture

An introduction to Boston's crime landscape. Understanding the scale, scope, and patterns across 1.98 million incident records from 2015-2025.

The Geography of Fear

Mapping crime across 12 districts. Using iGraph network analysis to reveal spatial relationships and district connectivity patterns.

The Clockwork City

When does crime strike? Uncovering temporal patterns with cyclical encoding. Peak activity at 3 PM, variations by day of week.

The Algorithm

LightGBM DART model predicts violent crime with 0.6497 AUC-ROC. Feature importance reveals spatial features dominate at 49.4%.

The Optimization

OR-Tools VRP solver computes optimal patrol routes. 3 patrol units cover all 12 high-risk districts with 311 total distance units.

Methodology

Complete technical documentation: GBDT vs DART vs GOSS model comparison, feature engineering pipeline, cyclical encoding for temporal features, and temporal train/test validation strategy.

Credits

Data Source
Boston Police Department
Analysis
Querex Data Science
3D Visualization
Blender + Three.js
Published
January 2026
LightGBM MCP iGraph MCP OR-Tools MCP Blender MCP Three.js MCP Statistics