{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

LeeLeeKek-CrimePredictionUsingBusinessesAndHousingValuesInSanFrancisco[1]

LeeLeeKek-CrimePredictionUsingBusinessesAndHousingValuesInSanFrancisco[1]

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Crime Prediction using Businesses and Housing Values in San Francisco James Jung Lee, Joel Kek, Yik Lun Lee Introduction Predictive policing is the idea of using technology and data analytics to proactively predict and preempt crime, hence allowing police departments to do their work in more intelligent ways. In the Police Chief Magazine, Los Angeles Police Department’s Chief of Detectives Charlie Beck describes predictive policing as a combination of “directed, information­based patrolling, rapid response supported by fact­based prepositioning of assets, and proactive, intelligence­based tactics, strategy, and policy”. [1] With police departments nationwide facing budget cuts and manpower shortages, the idea of using existing police resources more effectively has taken off rapidly. [2] While the effectiveness of predictive policing has yet to be rigorously proven, efforts have been bearing fruit so far. For example, by using predictive policing software in the Foothill neighborhood, the LAPD managed to reduce property crimes there by 12%, as compared to a 0.5% rise in surrounding neighborhoods. [3] In our study, we atte mpt to develop a predictive model where we can input certain conditions about an area in San Francisco, i.e business density, housing values, etc, and try to predict the overall crime rate of that area. It is important to note that instead of using real­time data, we attempt to use more general, static factors of a region. This is useful for police departments that want to attempt predictive policing but lack access to real­time data. Even for police departments that have access to real­time data, this research allows them to understand what indicators might be useful in determining optimal allocations of resources in the future. Method Model Our aim is to predict the number of crime incidents in a certain area given a certain features specific to the area. We treat this as a binary classification problem, where for the target variable we define “high crime rate” as the occurrence of a threshold number of crimes over some period of time (in our data, over 12 months). The types of crime included in our data are aggravated assault, battery, burglary,
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 5

LeeLeeKek-CrimePredictionUsingBusinessesAndHousingValuesInSanFrancisco[1]

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon bookmark
Ask a homework question - tutors are online