Predictive Policing

Predictive Policing
Crime Prevention Through Environmental Design

What Is Predictive Policing?
• Predictive policing is the application of analytical
techniques—particularly quantitative techniques—to
identify likely targets for police intervention and prevent
crime or solve past crimes by making statistical predictions.
• The use of statistical and geospatial analyses to forecast
crime levels has been around for decades.
• In recent years, however, there has been a surge of
interest in analytical tools that draw on very large data
sets to make predictions in support of crime prevention.
These tools greatly increase police departments’ reliance on
information technology (IT) to collect, maintain, and
analyze those data sets, however.

Predictive Policing
• Predictive policing is the application of
analytical techniques— particularly
quantitative techniques— to identify likely
targets for police intervention and prevent
crime or solve past crimes by making
statistical predictions.

Predictive Policing: Why Crime Is
“Predictable”
• There is a strong body of evidence to
support the theory that crime is predictable
(in the statistical sense)—mainly because
criminals tend to operate in their comfort
zone.
• That is, they tend to commit the type of
crimes that they have committed
successfully in the past, generally close to the
same time and location.

Predictive Policing:
Why Crime Is
“Predictable”

“Predictable”
• According to Jeff Brantingham, an anthropologist, Police
Department (LAPD) at the University of California, Los
Angeles,
• The naysayers want you to believe that humans are
too complex and too random— that this sort of math
can’t be done but humans are not nearly as random
as we think. In a sense, crime is just a physical
process, and if you can explain how offenders move
and how they mix with their victims, you can
understand an incredible amount.

“Predictable”
• For this study, we consolidated these theories into what we refer to as a
blended theory:
• Criminals and victims follow common life patterns; overlaps in those
patterns indicate an increased likelihood of crime.
• Geographic and temporal features influence the where and when of
those patterns.
• As they move within those patterns, criminals make “rational”
decisions about whether to commit crimes, taking into account such factors
as the area, the target’s suitability, and the risk of getting caught.
• The theoretical justification for predictive policing, then, is that we can
identify many of these patterns and factors through analytics and then can
steer criminals’ decisions to prevent crimes with tactical interventions.

“Predictable”

“Predictable”
• The blended theory best fits “stranger offenses,”
such as robberies, burglaries, and thefts.
• It is less applicable to vice and relationship violence,
both of which involve human connections that both
extend beyond limited geographic boundaries and lead
to decisions that do not fit into traditional “criminal
rational choice” frameworks.
• Nonetheless, alternative theories have been tested to
explain vice and relationship violence, leading to the
development of instruments and methods for
assessing risks in. these areas as well.

Objectives and Approach
• Predictive methods allow police to work more proactively
with limited resources.
• The objective of these methods is to develop effective
strategies that will prevent crime or make investigation
efforts more effective.

A Taxonomy of Predictive Methods
Predictive methods can be divided into four broad categories:
1. Methods for predicting crimes:
• These are approaches used to forecast places and times with
an increased risk of crime.
2. Methods for predicting offenders:
• These approaches identify individuals at risk of offending in
the future.
3. Method s for predicting perpetrators’ identities:
• These techniques are used to create profiles that accurately
match likely offenders with specific past crimes.
4. Methods for predicting victims of crimes:
• Similar to those methods that focus on offenders, crime
locations, and times of heightened risk, these approaches are
used to identify groups or, in some cases, individuals who are
likely to become victims of crime.

A Taxonomy of Predictive Methods

Methods For Predicting Offenders

Methods For Predicting Perpetrators’
Identities

Methods For Predicting Victims Of
Crimes

Prediction-Led Policing Process and
Prevention Methods
• Making “predictions” is only half of prediction-led
policing; the other half is carrying out
interventions, acting on the predictions that lead to
reduced crime (or at least solve crimes).

Prediction-Led Policing Process and
Prevention Methods
At the core of the process is a four-step cycle
• The first two steps are collecting and
analyzing crime, incident, and offender data
to produce predictions.
• The third step is conducting police
operations that intervene against the
predicted crime (or help solve past crimes).

The Prediction-Led Policing Process

The Prediction-Led Policing Process
• Generic intervention, crime-specific intervention,
and problem-specific intervention.
• Thus, providing information that fills the need for
situational awareness among officers and staff is a
critical part of any intervention plan.
• The interventions lead to a criminal response that
ideally reduces or solves crime (the fourth step).
• In the short term, an agency needs to do rapid
assessments to ensure that the interventions are
being implemented properly and that there are no
immediately visible problems.

Predictive Policing Myths
• “Predictive policing” has received a
substantial amount of attention in the media
and the research literature. However, some
myths about these techniques have also
propagated.
• This is partly a problem of unrealistic
expectations: Predictive policing has been so
hyped that the reality cannot live up to the
hyperbole.

Myth 1: The computer actually knows the
future.
• Some descriptions of predictive policing make it
sound as if the computer can foretell the future.
Although much news coverage promotes the meme
that predictive policing is a crystal ball, these
algorithms predict the risk of future events, not the
events themselves.
• The computer, as a tool, can dramatically simplify the
search for patterns, but all these techniques are
extrapolations from the past in one way or another.
• In addition, predictions are only as good as the
underlying data used to make them.

Myth 1: The computer actually knows
the future

Myth 2: The computer will do everything
for you
• Although it is common to promote software
packages as end-to-end solutions for predictive
policing, humans remain—by far—the most
important elements in the predictive policing
process.
• Even with the most complete software suites,
humans must find and collect relevant data, pre-
process the data so they are suitable for analysis,
design and conduct analyses in response to ever-
changing crime conditions.

Myth 2: The computer will do everything
for you

Myth 3: You need a high-powered (and
expensive) model
• Most police departments do not need the most expensive
software packages or computers to launch a predictive
policing program.
• Functionalities built into standard workplace software
(e.g., Microsoft Office) and geographic information
systems (e.g., ArcGIS) can support many predictive
methods. Although there is usually a correlation between the
complexity of a model and its predictive power, increases in
predictive power have tended to show diminishing returns.
• especially important for small departments, which often
have insufficient data to support large, sophisticated
models.

Myth 3: You need a high-powered
(and expensive) model

Myth 4: Accurate predictions automatically
lead to major crime reductions
• Predictive policing analysis is frequently
marketed as the path to the end of crime.
• The focus on the analyses and software can
obscure the fact that predictions, on their own, are
just that—predictions.
• Actual decreases in crime require taking action
based on those predictions. Thus, we
emphasize again that predictive policing is not
about making predictions but about the end-to-
end process.

Myth 4: Accurate predictions automatically
lead to major crime reductions

Making Predictions About Potential Crimes
• As with most forecasting methods, predicting
future criminal events—whether from a
tactical (next incident) or strategic (long-term)
perspective—involves studying data on past
crimes and victims, often using a variety of
methods but generally always looking for
patterns.
• The underlying assumption is that the past is
prologue—at least the more recent past (days
for tactical approaches, months to a few years
for strategic approaches).

• Although this is true for addressing the questions
of when, where, what, and who, the methods used
will differ with the context and the goal:
• Hot spot analysis, statistical regression, data
mining, and near-repeat methods are generally
used to identify where a crime will occur over a
specified time horizon (when, varying from a day to a
year, depending on the method and application)and
therefore who is likely to be a victim.

Making Predictions About Potential
Crimes

Hot Spot Analysis and Crime Mapping
• Hot spot methods predict areas of increased crime
risk based on historical crime data.
• Hot spot methods seek to take advantage of the
fact that crime is not uniformly distributed,
identifying areas with the highest crime volumes
or rates. The underlying assumption—and
prediction—is that crime will likely occur where
crime has already occurred: The past is prologue

• There are trade-offs when identifying hot
spots, however. If the areas identified are too
small, the results may exclude some areas of
interest. But if they are too large, they may not
be useful for allocating resources—and thus
may not be “actionable.”
• Very simple methods, such as grid mapping or
thematic mapping, are commonly used, but these
methods can be highly dependent on the initial
data set and the partitioning of the map.

Using Predictions to Support Investigations of
Potential Offenders
• There are two important caveats involving
predictions regarding potential offenders.
• The first is that, compared with predictions
related to spatiotemporal crime techniques,
methods for making predictions involving people are
much less mature.
• The second is that privacy and civil rights
considerations are paramount

Protecting Privacy Rights and Civil Liberties
• Assessing the “risk” associated with an individual—
whether of committing future crimes or of being a
suspect in past crimes—is highly contentious and
fraught with personal privacy concerns.
• The phrase predictive policing began appearing in
headlines shortly after the release of the Tom Cruise movie
Minority Report, which insinuated that the police and other
law enforcement authorities have the knowledge and power
to arrest (or at least detain) suspects before they have
committed a crime.
• As “predictive policing” was thrust into the headlines, many
citizens, including privacy rights activists, likened the
phrase to a significant loss of privacy in their lives.

• Discussions of this nature—about the balance
between personal privacy and the state’s need to
maintain public safety—are not new, but they have
become increasingly important with advances in
technology for data collection, processing, and
analysis.
• The trails of personal information left in a person’s
wake are nearly endless—emissions ranging from the
DNA in a skin flake to the digital exhaust willingly or
unknowingly produced by cell phones, computers, and
other technologies. How that personal information is
collected and used by a third party is a concern for
leaders and legal scholars in the policing community.

• Intelligence information sharing across law
enforcement agencies has become a critical
component of modern public safety
operations.

Privacy Resources for the Law Enforcement
Community
• A range of tools are in development that assess
a person’s risk of committing or observing a
crime based on certain behavioural patterns,
but police departments will want to proceed with
caution.
• Law enforcement officials must carefully consider
issues related Proper management of sensitive
data is a significant concern, and improper use
can have legal ramifications as well as personally
damaging consequences for citizens and
communities.

Community

Community
• Many privacy laws in the United States, Canada,
Europe, and other regions are structured around
the widely accepted Fair Information Practice
Principles.

Community
• Openness Principle
• There should be a general policy of openness about developments,
practices and policies with respect to personal data. Means should be
readily available for establishing the existence and nature of personal data,
and the main purposes of their use, as well as the identity and usual
residence of the data controller.
• Collection Limitation Principle
• There should be limits to the collection of personal data and any such
data should be obtained by lawful and fair means and, where
appropriate, with the knowledge or consent of the data subject.
• Purpose Specification Principle
• The purposes for which personal data are collected should be specified
not later than at the time of data collection and the subsequent use
limited to the fulfilment of those purposes or such others as are not
incompatible with those purposes and as are specified on each occasion of
change of purpose.

Community
• Use Limitation Principle
• Personal data should not be disclosed, made
available or otherwise used for purposes other
than those specified . . . except a) with the consent
of the data subject; or b) by the authority of law.
• Data Quality Principle
• Personal data should be relevant to the
purposes for which they are to be used, and, to
the extent necessary for those purposes, should
be accurate, complete, and relevant and kept up-
to-date.

Community
• Individual Participation Principle
• An individual should have the right:
• a) to obtain from a data controller, or otherwise, confirmation of whether or not the
data controller has data relating to him;
• b) to have communicated to him, data relating to him within a reasonable time; at a
charge, if any, that is not excessive; in a reasonable manner; and in a form that is
readily intelligible to him;
• c) to be given reasons if a request is denied and to be able to challenge such denial;
and
• d) to challenge data relating to him and, if the challenge is successful, to have the
data erased, rectified, completed or amended.
• Security Safeguards Principle
• Personal data should be protected by reasonable security safeguards against
such risks as loss or unauthorized access, destruction, use, modification or
disclosure of data.
• Accountability Principle
• A data controller should be accountable for complying with measures which give
effect to the principles stated above.

Community
• The purpose of this introduction to some of the
privacy considerations related to predictive
policing initiatives is as much to inform as it is to
caution that the applicable regulations and
guidelines are numerous.
• However, this also means that there are many
resources and communities of interest for law
enforcement agencies to consult.

Risk Assessment for Individual Criminal
Behaviour
• Can we estimate the risk that a person will commit a serious crime in
the near future?
• How well will a person respond to a short-term change in life
circumstances (e.g., getting fired from a job, fighting with a spouse or
partner, abusing alcohol or drugs)?
• What is the likelihood that these short-term circumstances will motivate a
person toward criminal behaviour?
• The findings suggest that short-term negative changes in life circumstances
may sharply increase criminal activity—for example, the use of illegal
drugs increased the odds of committing property crime by 54 percent and
committing an assault by more than 100 percent.

Risk Assessment for Individual
Criminal Behaviour

Risk Assessment for Organized Crime
Behaviour
• Predicting crimes committed by organized gangs
differs from detecting crimes committed by
individuals and predicting who will offend. Criminal
gangs usually engage in one or two types of criminal
behaviour, such as drug-related crimes or prostitution.
• In addition, criminal gangs often fight each other to
gain dominance in certain parts of the city.
However, our review of predictive methods would
not be complete without some mention of attempts
to forecast these types of crimes.

Behaviour

Behaviour
• The mobility of criminal groups is of international interest
because crime organizations can influence both local crime (e.g.,
through illicit drugs, prostitution, and robbery) and, in some
cases, international crime (e.g., through human trafficking, money
laundering, and the transport of illicit drugs).
• Methods for predicting the illegal activity of organized crime
groups include using the activity and dynamics of the group to
evaluate risks and techniques to measure criminal market
opportunities.
• The most common models include using group activity to identify
organized crime, determining the presence of organized crime
through illicit markets, and using a risk-based assessment (a more
holistic approach) to identify illicit behaviour.
• For the most part, to date, these methods have been qualitative
rather than formal statistical models for calculating the risk of
“organized crime.”

Behaviour
• Motivating the more holistic risk-based
assessments of illicit behaviour are questions like
• “Is there much organized crime?” “Is the situation
serious?”
• “Is it bad that there are more criminal groups now
than in the past?” and
• “Which criminal groups are the most dangerous?”

Behaviour
• The following list identifies and defines several of the methods used
by law enforcement agencies to describe trends in the criminal
market space
• Environmental scanning: A systematic effort to identify future
developments that could plausibly occur and whose occurrence
could alter a particular environment in an important way (e.g.,
economic fluctuations, social attitudes, advances in technology).
• Reviewing and synthesizing the literature in disciplines relevant to
the issues at hand are the two most common methods used by
practitioners.
• Nominal group and Delphi process: Surveying the opinions and
judgments of experts can also provide the insight needed to assess
the potential of various future events to alter the characteristics of
the criminal market space.

Behaviour
• Scenario writing: An attempt to identify the
range of possible conditions, scenario writing
challenges an analyst team to use facts, given
events, and a series of proposed forces to develop
a picture of the conditions that may lead to
various potential outcomes.
• By varying the assumptions associated with
existing trends and considering the dynamics
of the environment, analysts attempt to
prioritize key actors, conditions, and events to
watch.

Behaviour
• As a means to help policymakers set strategic
priorities, several national and international
governments have developed organized crime
threat assessment mechanisms.
• These monitoring systems, tests, and protocols
provide a framework for filtering and analyzing
data about the actions of known crime groups and
the crimes with which they are potentially
associated. The systems vary in reliability and
validity, however.

Risk Assessment Instruments for
Domestic Violence
• In Johnson County, Kansas, members of the
district attorney’s office developed a “lethality
assessment” that must be completed by law
enforcement officers on the scene of domestic
incidents where there is probable cause for
arrest. Several risk factors, the office determined,
are associated with an increased risk of homicides
of women and men in violent relationships. While
these associations are difficult to predict with
precision, the district attorney’s

Domestic Violence

Risk Assessment Instruments for Domestic
Violence
• Using the results of the lethality assessment
administered to the victim, officers were able
to automatically trigger certain protocols,
including a call or referral to the SAFEHOME
domestic violence shelter hotline.
• In 2011, the SAFEHOME shelter received
around 1,000 more calls to its hotline than
in prior years

Mental Health
• Often, law enforcement officers are called
upon to assess not only a general risk of
violence but also specific types of violence,
sometimes with only moments or even seconds
to make those decisions.
• Now more than ever, agencies are pairing up
with mental health professionals to make these
assessments well in advance, or at least
reasonably in advance of critical situations

Risk Assessment Instruments for Mental
Health
• Not only is the mental health professional fully trained
for such encounters, she is able to provide immediate
insight and information to officers on the scene to
protect the patient, the officers, and other citizens. This
model proved to be effective during the pilot
implementation, and other nearby jurisdictions are now
seeking funding to implement similar programs.
• However, reliance on behavioural patterns is extremely
problematic in that there is no agreed-upon list of
behaviours that point to likely offenders with any
certainty. Further, individuals with mental health disorders
can exhibit threatening behaviours but are not necessarily
potential offenders. Determining which ones are truly likely
to commit serious crimes is far from a settled science.

Risk Assessment Instruments for Mental
Health

Finding Suspects
• The common approach is to assemble the
available clues—pieces of data both about
the crime and about past perpetrators in the
area— and, using a combination of matches
to potential suspects and exclusions based on
the process of elimination, identify the most
likely perpetrators

Basic Queries
• The use of various queries of intelligence
and master name databases are useful in
finding suspects.
• Information collected through database
queries of persons under supervision, field
interview cards, and gang intelligence, for
instance, assists investigators and analysts in
identifying threats and finding likely suspects.

Criminal Intelligence in Social Network
Analysis
• Clearly, social network analysis has become extremely
popular and important in recent years. Monitoring real-
time updates on selected Face book, Twitter, and other
social media can provide law enforcement officials with
immediate information on crimes just committed and
other criminal activity being planned.
• From criminal mischief by juveniles to very serious crimes,
including homicide, some criminals frequently post and
promote their criminal activity and plans, leaving the ball in
law enforcement’s court to identify and stop it, when possible.

Criminal Intelligence in Social
Network Analysis

Links to Department of Motor Vehicle
Registries, Pawn Data, and Other Registries
• Classified as third-party data sharing
agreements, law enforcement partnerships
with motor vehicle and other public
registries have been used to develop rich
profiles of potential suspects, known
offenders, and possible witnesses

• Pawn shop data have also proved to be very useful.
In addition to identifying attempts to pawn known
stolen property, a review of pawn records can show
an increase in pawns by a particular subject that
may warrant further investigation.
• An analysis of those data, coupled with information and
intelligence from other sources, such as the areas
frequented by the subject and the types of crimes
committed, can inform behavioural and appropriate
responses to target the person or the activity.

Anchor Point Analysis, or Geographic
Profiling
• Geographic profiling is an analytic tool that
determines the most probable area of an
offender’s search base through an analysis of
his or her crime locations.
• For the vast majority of criminals, their search
base is their residence. In some cases, the search
base for an offender’s crimes is some other anchor
point, such as his or her work site or immediate
past residence. Either type of base can be located
using this technique

Anchor Point Analysis, or Geographic
Profiling

Modus Operandi Similarity Analysis
• Clearly, examining individual offenders
based on their known modus operandi
(MO) to crimes that have been committed
creates reasonable leads for investigators to
follow when following up on past incidents.
However, using this same information on
offenders, analysts can project future
behaviour.

Modus Operandi Similarity Analysis

Putting the Clues Together: Multisystem and
Network Queries
• Fusion and crime analysis centers have continued to
leverage federated searching technologies to
integrate disparate databases into a standardized
query and analysis platform.
• The ability to conduct “one-stop” searching across the
data sets of multiple jurisdictions and agencies has
substantially enhanced the ability to translate
investigative leads (such as aliases or phone numbers)
into known suspects, identify multijurisdictional crime
patterns, and discover offender associations and
criminal networks.

Putting the Clues Together: Multisystem
and Network Queries

Putting the Clues Together: Multisystem and
Network Queries
• While such technologies currently
supplement more traditional workflows, the
integrated nature of federated data systems
has great potential to enhance predictive
policing efforts.

Taking Action on Predictions
• The first stage in taking action on a prediction
about a high-risk individual or potential
suspect is to describe the crime pattern or
evidence related to the person.
• Past this point, actions taken with regard to
individuals become far more uncertain and of
greater concern from a privacy and civil rights
perspective.
• This is an area that calls for significantly more
research. However, in this section, we review
practices that are currently in use.

Identifying High-Risk Individuals
• One basic measure is to support improved situational awareness
of the highest risk
• For especially high-risk individuals, some departments allocate
resources to conduct regular surveillance.
• For high-risk individuals under community supervision (probation
and parole), departments and corrections agencies have applied
increased supervision, such as additional meetings and checks or the
use of GPS tracking devices.
• Interventions led by community or other non-profit
organizations are also in use.
• Some intervention and therapy programs have shown promise
for treating persons at high risk of engaging in domestic
violence, mental health–related violence, or violent behaviour in
general. offenders by providing officers with updated priority
lists of known offenders.

Identifying High-Risk Individuals

Identifying the Most Likely Suspects
• Actions taken in response to predictions of the
most likely suspects are more straightforward.
• Here, the actions involve simply integrating the
findings into the criminal investigation process.
The complications relate to due process and civil
rights: What levels of statistical “risk” or
“certainty” constitute standards for taking various
degrees of actions against suspects? This is likely
to be a major topic of future research and debate.

Identifying the Most Likely Suspects

Conclusions
• All departments can benefit from predictive policing
methods and tools; the distinction is in how
sophisticated (and expensive) the tools need to be.
• In thinking about what is needed, it is important to note
that the key value in predictive policing tools is their
ability to provide situational awareness of crime risks
and the information needed to act on those risks and
pre-empt crime.
• The question then becomes a matter of what set of
tools best provides situational awareness for a given
department, not which tools can serve as a crystal
ball.

Conclusions
• Generating predictions is just half of the
predictive policing business process; taking
actions to interdict crimes is the other half. The
specific interventions will vary by objective and
situation.
• Designing intervention programs that take
these attributes into account, in combination
with solid predictive analytics, can go a long
way toward ensuring that predicted crime risks do
not become real crimes.

Taking Actions To Interdict Crimes

Conclusions
• There is an obvious appeal to being able to prevent crime as
opposed to merely apprehending offenders after a crime has
been committed. For law enforcement agencies, the ability to
predict a crime and stop it before it is committed is tantalizing
indeed—as it is to the general public.
• Any hype must be tempered somewhat by considerations of
privacy and civil rights, however. Predictive methods,
themselves, may not expose sufficient probable cause to
apprehend a suspected offender.
• “Predictions” are generated through statistical calculations that
produce estimates, at best; like all techniques that extrapolate the
future based on the past, they assume that the past is prologue.
Consequently, the results are probabilistic, not certain.

PredPol: Predict Crime
Predictive Policing Software
• How Predictive Policing Works
• Using only three data points – crime type, crime location
and crime date/time – PredPol’s powerful software provides
each law enforcement agency with customized crime
predictions for the places and times that crimes are most
likely to occur.
• PREDPOL DOES:
• Increase Law Enforcement’s odds of stopping crime
• Predict WHERE and WHEN crime is most likely to occur
• Work for both large and small agencies
• Help new officers on-board quicker
• Make it easy to access predictions anywhere and anytime

• PREDPOL DOES NOT:
• Map out past crimes or another ‘hotspot’ tool
• Predict WHO will commit crimes
• Use PII, eliminating civil liberties issues
• Replace law enforcement veterans or analyst’s’
intuition and experience
• Require additional hiring or new hardware in
order to use

PredPol Benefits Everyone
• Crime Analysts: Using PredPol’s technology, analysts
spend less time making crime maps and more time
conducting the sophisticated analysis and intelligence
work for which they are trained.
• Patrol Officers: Newer officers are brought up to
speed faster in unfamiliar patrol areas, and veteran
officers are given additional, high-risk places to patrol
that take them beyond their usual target areas.
• Command Staff: Command staff can set crime-
specific missions by beat, shift and day of week. The
Patrol Heat Map feature allows command staff to see
aggregate patrol levels across their jurisdiction.

PredPol Benefits Everyone
• Agencies: Law enforcement agencies deploying
PredPol are experiencing marked drops in crime
due to increased police presence in areas deemed to
be at greatest risk. Agencies are able to allocate the
limited resources they do have more effectively.
• Communities: Most importantly, communities are
seeing fewer victims, reducing the tangible and
intangible impacts of crime. PredPol provides officers
an opportunity to interact with residents, aiding in
relationship building and allowing law enforcement to
be more transparent with the communities they serve.

References
• BUILDING SMART POLICE IN INDIA: BACKGROUND INTO THE NEEDED POLICE
FORCE REFORMS
• https://niti.gov.in/writereaddata/files/document_publication/Strengthening-Police-Force.pdf
• The Bureau of Police Research & Development
• http://www.bprd.nic.in/
• Criminology 101: A Guide for Smart Policing Initiatives
• https://cebcp.org/wp-content/evidence-based-policing/Decker-Criminology-101.pdf
• Can ‘predictive policing’ prevent crime before it happens?
• http://www.sciencemag.org/news/2016/09/can-predictive-policing-prevent-crime-it-happens
• What Crime Analysts Do
• https://www.iaca.net/dc_analyst_role.asp
• Defining e-policing and smart policing for law enforcement
• https://valleyinternational.net/thijsshi/v3-i12/1%20theijsshi.pdf
• PredPol
• http://www.predpol.com/
• Predictive policing
• https://en.wikipedia.org/wiki/Predictive_policing
• PREDICTIVE POLICING The Role of Crime Forecasting in Law Enforcement Operations
• https://www.rand.org/content/dam/rand/pubs/research_reports/RR200/RR233/RAND_RR233.pdf

Predictive Policing

More Related Content

What's hot (20)

Similar to Predictive Policing (20)

More from GAURAV. H .TANDON (20)

Recently uploaded (20)

Predictive Policing