+ All Categories
Home > Technology > Crime Early Warning: Automated Data Mining of CAD and RMS

Crime Early Warning: Automated Data Mining of CAD and RMS

Date post: 12-Jan-2015
Category:
Upload: azavea
View: 1,030 times
Download: 2 times
Share this document with a friend
Description:
The genesis of HunchLab was the idea to mine law enforcement agencies' CAD and RMS databases to detect unusual levels of activity in particular areas and then send alerts to the appropriate police staff. While crime analysis tools often are aiming to display what has happened, the concept of a geographic early warning system, such as within HunchLab, tries to answer the question: "what is unusual that is happening?" http://www.azavea.com/products/hunchlab/features/early-warning/
Popular Tags:
46
340 N 12 th St, Suite 402 Philadelphia, PA 19107 215.925.2600 [email protected] www.azavea.com/hunchlab Crime Early Warning Systems Automated Data Mining of CAD and RMS Databases
Transcript
Page 1: Crime Early Warning: Automated Data Mining of CAD and RMS

340 N 12th St, Suite 402Philadelphia, PA 19107

[email protected]

www.azavea.com/hunchlab

Crime Early Warning Systems

Automated Data Mining of CAD and RMS Databases

Page 2: Crime Early Warning: Automated Data Mining of CAD and RMS

About Us

Robert CheethamPresident & [email protected]

Jeremy HeffnerHunchLab Product [email protected]

Page 3: Crime Early Warning: Automated Data Mining of CAD and RMS

Agenda

• Company Background• The Backstory• HunchLab

– Concept of Early Warning / Data Mining– Demonstration of Hunches– Underlying Statistics

• Q&A

Page 4: Crime Early Warning: Automated Data Mining of CAD and RMS

About Azavea

• Founded in 2000

• 27 people

• Based in Philadelphia

– Also Boston & Minneapolis

• Geospatial + web + mobile

– Software development

– Spatial analysis services

Page 5: Crime Early Warning: Automated Data Mining of CAD and RMS

Clients & Industries

• Public Safety• Municipal Services• Public Health• Human Services• Culture • Elections & Politics• Land Conservation• Economic Development

Page 6: Crime Early Warning: Automated Data Mining of CAD and RMS

Azavea & Governments

Page 7: Crime Early Warning: Automated Data Mining of CAD and RMS

The Backstory

Page 8: Crime Early Warning: Automated Data Mining of CAD and RMS

How Phila PD uses GIS

Customized Map Products

Weekly CompStat Meetings

Web Crime Analysis

Page 9: Crime Early Warning: Automated Data Mining of CAD and RMS

Complainant

CAD

Verizon911

911 Operator

RadioDispatcher

Police Officer

District48 Desk

INCT

Daily download& Geocoding Routines

Incident ReportCompleted by Officer District X

District Y

District Z

Maps distributedThrough Intranet,

Printing, CompStat

INCT & PARS – main database sources

over 5,000 incidents daily, over 2 million annually

PARS

Page 10: Crime Early Warning: Automated Data Mining of CAD and RMS

The Context

1,500,000 people

7,000 police officers

1,000 civilian employees

2,000,000 new incidents / year

3 crime analysts

Page 11: Crime Early Warning: Automated Data Mining of CAD and RMS

What we did

• Weekly Compstat• Lots of maps• Automation of map creation• Web-based systems

Page 12: Crime Early Warning: Automated Data Mining of CAD and RMS

… but what if we could…

Accelerate the cycle Proactively notify Automate the process

Page 13: Crime Early Warning: Automated Data Mining of CAD and RMS

Prototype

ArcViewVB & MapObjects

MS SQL Server

Crime Incidents Database

Shapefiles

and

GRIDs

Process Documentation

.ini file

Page 14: Crime Early Warning: Automated Data Mining of CAD and RMS
Page 15: Crime Early Warning: Automated Data Mining of CAD and RMS

… but there was a problem …

Page 16: Crime Early Warning: Automated Data Mining of CAD and RMS

It was crap … sort of.

Page 17: Crime Early Warning: Automated Data Mining of CAD and RMS

We needed ….

1. Better Statistics

2. Notification

3. Very Straightforward

Page 18: Crime Early Warning: Automated Data Mining of CAD and RMS
Page 19: Crime Early Warning: Automated Data Mining of CAD and RMS

web-based crime analysis, early warning, and risk forecasting

Page 20: Crime Early Warning: Automated Data Mining of CAD and RMS

Crime Analysis

– Mapping (spatial / temporal densities)

– Trending

– Intelligence Dashboard

Early Warning

– Statistical & Threshold-based Hunches (data mining)

– Alerting

Risk Forecasting

– Near Repeat Pattern

– Load Forecasting

Page 21: Crime Early Warning: Automated Data Mining of CAD and RMS

Crime Analysis – What has happened?

– Mapping (spatial / temporal densities)

– Trending

– Intelligence Dashboard

Early Warning – What is out of the ordinary?

– Statistical & Threshold-based Hunches (data mining)

– Alerting

Risk Forecasting – What is likely to happen?

– Near Repeat Pattern

– Load Forecasting

Page 22: Crime Early Warning: Automated Data Mining of CAD and RMS

Early Warning

Page 23: Crime Early Warning: Automated Data Mining of CAD and RMS

Early Warning

• Geographic Early Warning System– A system to alert staff of an unusual situation in a

particular location– Ingests data sets to automatically “cook on” and only

involves staff when a statistically unusual situation is found

HunchLab Database

Operational Database Alerting

System

Geostatistical Engine

Operational DatabaseOperational Databases

Page 24: Crime Early Warning: Automated Data Mining of CAD and RMS

Data Mining

• What do we mean by data mining?– The process of “cooking on” the data to reveal

something new (unusual)• Benefits

– Automated discovery process– Can examine large data sets without additional staff

time• Major crime incidents• Minor crime incidents

– Near real-time alerts• Limitations

– Can’t determine why something unusual is happening, only that it is happening

Page 25: Crime Early Warning: Automated Data Mining of CAD and RMS

Early Warning

bit.ly/crimespikedetector

Page 26: Crime Early Warning: Automated Data Mining of CAD and RMS

Demo

Page 27: Crime Early Warning: Automated Data Mining of CAD and RMS

What is a Hunch?

• A proposed hypothesis, saved into the system, and continually tested for validity

• Incident Attribute Requirements– Location (x, y)– Time (timestamp)– Classification

• Hunch Attributes– Location (area)– Time (recent / historic periods)– Classification

• Analyses– Statistical Hunch– Threshold Hunch

Page 28: Crime Early Warning: Automated Data Mining of CAD and RMS

Hunch Parameters: Location

• Address & Radius• Precinct/County/Country• Custom Drawn Area• Mass Hunch

Page 29: Crime Early Warning: Automated Data Mining of CAD and RMS

Hunch Parameters: Time

• Statistical Hunch– Recent Past– Historic Past

Page 30: Crime Early Warning: Automated Data Mining of CAD and RMS

Hunch Parameters: Classification

• Category• Time of Day• Narrative

Page 31: Crime Early Warning: Automated Data Mining of CAD and RMS

Hunch Helper

Page 32: Crime Early Warning: Automated Data Mining of CAD and RMS

Email Alert

Page 33: Crime Early Warning: Automated Data Mining of CAD and RMS

Hunch Details

Page 34: Crime Early Warning: Automated Data Mining of CAD and RMS

The Statistics

Page 35: Crime Early Warning: Automated Data Mining of CAD and RMS

What do we know?

• Hunch– Geographic region (that we care about)– Recent time frame (to alert on) – Historic time frame (to compare against)– Classification (that we are interested in)

Page 36: Crime Early Warning: Automated Data Mining of CAD and RMS

What do we know?

• Hunch– Geographic region (that we care about)– Recent time frame (to alert on) – Historic time frame (to compare against)– Classification (that we are interested in)

Within Hunch Outside of Hunch

Recent past ? ?

Historic past ? ?

Page 37: Crime Early Warning: Automated Data Mining of CAD and RMS

Hypergeometric Distribution

• Arises when selecting items at random from a heterogenous pool without replacement– Example

• A bag contains 45 black marbles and 5 white marbles• What is the chance of picking 4 white marbles when we

draw 10 marbles?

Tony SmithUniversity of Pennsylvania

Drawn Not Drawn

White Marbles

4 1

Black Marbles

6 39

Page 38: Crime Early Warning: Automated Data Mining of CAD and RMS

Hypergeometric Distribution

Drawn Not Drawn Total

White Marbles

4 = k 1 = m – k 5 = m

Black Marbles

6 = n-k 39 = N + k – n - m

45 = N – m

Total 10 = n 40 = N - n 50 = N

en.wikipedia.org/wiki/Hypergeometric_distribution

Page 39: Crime Early Warning: Automated Data Mining of CAD and RMS

What do we know?

• Hunch– Geographic region (that we care about)– Recent time frame (to alert on) – Historic time frame (to compare against)– Classification (that we are interested in)

Within Hunch Outside of Hunch

Recent past ? ?

Historic past ? ?

Page 40: Crime Early Warning: Automated Data Mining of CAD and RMS

What do we know?

• Valid Hunch– The current condition (and all worse conditions) is

unlikely to simply be due to chance

Page 41: Crime Early Warning: Automated Data Mining of CAD and RMS

Demo

Page 42: Crime Early Warning: Automated Data Mining of CAD and RMS

Research Topics

Page 43: Crime Early Warning: Automated Data Mining of CAD and RMS

Research Topics

• Mobile Interfaces• Analysis

– Real-time Functionality• Consume real-time data streams & conduct ongoing

analysis

Page 44: Crime Early Warning: Automated Data Mining of CAD and RMS

Research Topics

• Risk Forecasting– Load forecasting enhancements

• Machine learning-based model selection• Weather and special events

– Combining short and long term risk forecasts– Risk Terrain Modeling

Page 45: Crime Early Warning: Automated Data Mining of CAD and RMS

Q&A

Page 46: Crime Early Warning: Automated Data Mining of CAD and RMS

Contact Us

Robert CheethamPresident & [email protected]

Jeremy HeffnerHunchLab Product [email protected]


Recommended