Misamis University

Oroquieta City
Department of Information Technology

Crime Rate Reduction through Forecasting Utilizing

Autoregressive Integrated Moving Average
(CRRFUARIMA)

A Capstone Project Presented to the Faculty of the

Department of Information Technology
Misamis University, Oroquieta City

In Partial Fulfilment of the Requirements for the

Degree of Bachelor of Science in Information Technology

Researchers:

Gumatay, Edcel M.
Marcil, Ramil M.
Romero, Jumar Rey D.
Testa, Aisa Mae R.

March 2017
 Chapter 1

Introduction

1.1 Background of the Study

The government has long been ineffective at solving crimes, many of which are categorized
as being heinous. Rampant crime has plagued practically all levels in the society, and their
occurrences have largely been attributed to the weak and useless systems that characterize the
government, especially those mechanisms within it that are meant to address the crime problem.
The crime problem has taken its toll on the lifeblood of the nation’s socioeconomic situation.
Crimes have tremendously affected our country. A large segment of our people has lost
confidence in the law-enforcing agencies of government. Many fear that tragedy might suddenly
strike them in broad daylight. Stories from the newspapers (particularly the tabloids) are
sufficient to send tingles down the spine. One thing is certain the government is helpless at
effectively checking and containing the already serious and increasingly more serious crime
problem in the country. Common causes of criminality can be traced through sociological and
behavioural studies of the human condition. It is a fact of life that crimes occur only in the
human sphere, and social relations are therefore a major aspect in approaching the issue of
criminality. With this point of departure, we can objectively mention some factors that have been
identified by professional practitioners engaged in the study of criminality, among whom are
psychologists, sociologists, criminologists and others. (Pepa, 2013)

Crime Rate Reduction through Forecasting Utilizing Autoregressive Integrated Moving

Average (CRRFUARIMA) was designed to develop crime forecasting as an application area
for police in support of tactical deployment of resources. Data on crime offense reports and
computer aided dispatch (CAD) has been made relevant by recent criminological theories, made
possible by recent information technologies and made desirable because of innovative crime
management practices. While focused primarily on the police component of the criminal justice
system, the project provides a wide range of forecasting settings and models in crime reduction.
Furthermore, the project includes several innovations for forecast models, with many driven
unique features of the problem area and data. (Elsevier, 2016)
 Crime forecasting is one of research in forecasting world. Many forecasting methods have
been applied in this field, exponential smoothing, decomposition method and ARIMA model.
This study proposed crime forecasting using Autoregressive Integrated Moving Average
(ARIMA) model. This combination is expected to generate more accurate forecasting result with
minimum error. The results will help the decision maker’s in making the right decision in crime
prevention strategies. (Jiang & Barricarte, 2011)

Crime rate reduction is one of the important roles of the police system in any country. One of
the components of crime prevention is crime rate predictions or in other word is crime
forecasting. Police will require crime forecasting to make operational and tactical strategies in
the future, as like to allocate police patrols in the right area, although several economic theories
of crime postulate that crime rates and police strength are simultaneously determined, empirical
research on the issue has produced highly divergent results. The need for strong assumptions
about temporal patterning, which the theories do not supply, is probably responsible for these
findings. A statistical technique which permits a more flexible approach to temporal analysis is
described and applied to data on crime and police strength in any countries. We find no evidence
for the systematic relationships envisioned in economic theory and attribute this to important
organizational and political variables which are omitted from these theories. (Chen et al, 2008)

ARIMA model has higher fitting and forecasting accuracy than exponential smoothing. This
work will be helpful for the local police stations and municipal governments in decision making
and crime suppression. In the recent years, volumes of crime had brought serious problems, not
least in any country. The government has taken a step forward in reducing crime program
included index crime in overall reported index crime every year and reduction in street crime.
(Menteri, 2011)

The reason why we create this project is to improve the accuracy of crime forecasting. This
study proposes combined between ARIMA models for crime forecasting process. The results
could provide information about crime trends, especially the possible worst and better condition
in the future. This information can help the police in making decision for operational and tactical
strategies in crime prevention.
1.2 Statement of the Problems
After the studies and considerations, the researchers found the following problems at the PNP
Oroquieta City:

1.2.1 General Problem

The researchers will design and develop a system that will provide s o l u t i o n t o
reduce crime rate and will help the police of Oroquieta City .

1.2.2 Specific Problems

 Delay in generating reports due to substantial data.
 Existing system generate statistics reports which are ambiguous.
 Unable to generate report that foresees the reoccurrence of incident crimes.
 Manual retrieval of crime incident record resulting to deceitful graphical figures.

1.3 Study Objectives

1.3.1 General Objective

The main objective of this study is to develop Crime Rate Reduction through Forecasting
ARIMA system that can determine the crime rate of a certain place.

1.3.2 Specific Objectives

 To provide a system that will automatically gather data needed for generating reports.
 To generate graphical reports showing graphs on number of crime incident in a specific
area.
 To generate annual reports for comparison of data regarding occurrence of incident
crimes.
 To provide a system that will automatically retrieve information and avoid redundancy
through data filtering.
1.4 Scope and Limitation of the Study

To create a more effective system, the proponent needs to

k n o w t h e m e a s u r e o f responsibilities and boundaries of the proposed system.

The main scope of the research study is the accuracy and reliability of crimes in the
Oroquieta City. It mainly focuses on the management of crimes from the initial reporting of the
crime until the investigation process. This research is mainly focused on the city of Oroquieta
making the police headquarters and precincts in city test bed of the study.
Our system also focuses on recording and generating reports and forecasting of crime
incidents of a certain place using graphical method intended only in Oroquieta City which will
be promoted to the different organizations that connects at Oroquieta Police Station, namely the
police provincial office, the prosecutor’s office Media/Press for reports and for journalism.
Several information can also be retrieved using the proposed system wherein names,
address etc. will be displayed based on any circumstances. It will determine the crimes that had
happened in a certain month, how many cases are there in each category, when and where crime
occurred, who are the persons involved and determine the total number of solved and unsolved
cases among the recorded crimes. The system is only standalone which restricts outsiders
(public) in manipulating confidential files.
The system limits the issuance of pertinent documents like police clearance and blotter is
not included in the system.

1.5 Significance of the Study

Oroquieta City Police Station. The proposed system will make it easier for the police to manage the crime
forecasting of Oroquieta City.

PNP Staffs. Police’s secretary and staff can benefit a lot from this study, as they are an integral part of
the police station management.
Researchers. The researchers have developed their writing, analysis, and interpretation skills
needed to make a good thesis.

Future Researchers. This will benefit other researchers who wish to have similar studies
as they can get background information from the result of this study which will serve as template to
modify their research.
 Chapter 2

Review of Related Literature

2.1 Related Literature

In making research project the first step to do is to conduct a review on related literature
for every piece ongoing research needs to be connected with work already done to attain referrals
of what have been already established by the authors and to give chance to the readers to
appreciate the related evidences.

I. Crime Forecasting using ARIMA Model and Fuzzy Alpha-cut

The author cited that the combination of the two methods is expected to generate more
accurate forecasting result with minimum error. The results will help the decision maker’s in
making the right decision in crime prevention strategies. (Noor Maizura Mohamad, et. Al, 2013)

II. Forecasting Crime Using the ARIMA Model

The author stated that ARIMA is used to make short-term forecasting of property crime for
one city of China. It0 shows that the ARIMA model has higher fitting and forecasting accuracy
than exponential smoothing. It is helpful for the local police stations and municipal governments
in decision making and crime suppression. (Peng Chen, 2008)

III. Fuzzy Seasonal ARIMA Model for Forecasting (FSARIMA)

The system used Seasonal ARIMA to forecast two seasonal time series data of the total
production value of Taiwan machinery industry and soft drink time series. The model includes
both interval models with interval parameters and the possible distribution of future value. Based
on the results of practical application, it can be shown that this model makes good forecasts and
is realistic. (Fang-Mei Tseng & Gwo-Hshiung Tzeng, 2007)
 IV. CAPRI or Computer-Aided Police Records Index
The Phoenix Police Department, Azusa, USA is using CAPRI or Computer-Aided Police
Records Index to manage criminal history information at a local and regional level. They use
computer-based record management through the use of database for easy access and storing data
of crimes and incidents. Information includes criminal histories, incident reports references,
name indexes, fingerprint classifications and violence. . (Jiang & Barricarte, 2011)

V. DNA Testing in Police Investigative Work for Increasing Offender

Identification, Arrest, Conviction, and Case Clearance
Studies were coded with respect to a range of methodological and substantive features. When
possible, odds-ratios were computed to reflect the effect of DNA testing on criminal justice
system outcomes. Given the diversity of designs, we did not meta-analyze results across studies.
We did, however, use meta-analysis to synthesize results across multiple sites within two of the
five studies. Across studies we found generally positive results regarding the utility of DNA
testing. The results from the single experimental study on the effectiveness of DNA for property
crimes were consistently positive across the included sites. A time-series analysis found a
relationship between the size of a local DNA database and clearance rates for most crime types.
Two of the remaining three quasi-experimental designs found positive, and sometimes large,
effects for the benefits of DNA testing. A study of homicides found a negative effect of the value
of DNA. Clear alternative explanations for this finding are plausible. (Wilson, 2001)
 Chapter 3

Methodology

3.1 System Method

The system development life cycle (SDLC) is the entire process of formal, logic steps
taken to develop a software product. It is also type of methodology use to describe a process of
building information system for collecting information on the system to a deliberate, methodical
and structured, reoffering each of the cycle life development.

Figure 3.1 Modified Waterfall Model

Modified Waterfall Model came into existence because of the defects in the traditional
Waterfall Model. The phases of the modified model are to traditional model; they are planning
phase, analysis phase, design phase, implementation phase, and support phase. One of the
features of the Modified Waterfall Model is overlapping, which means a number of tasks can
function concurrently, ensuring the defects in the software are removed in the development stage
itself and the overhead cause of making changes to the software before implementation to saved
(Valdin, 2013).
 Modified Waterfall Model is a process used by the researcher to develop Crime Rate
Reduction through Forecasting Utilizing Autoregressive Integrated Moving Average
(CRRFUARIMA): the result will be in a high quality and will meet the expectation of the user.
Researchers developed this system so the user can manage and monitor the crime rate of
Oroquieta City.

ARIMA Forecasting Equation

ARIMA models are, in theory, the most general class of models for forecasting a time
series which can be made to be “stationary” by differencing (if necessary), perhaps in
conjunction with nonlinear transformations such as logging or deflating (if necessary). A random
variable that is a time series is stationary if its statistical properties are all constant over time. A
stationary series has no trend, its variations around its mean have constant amplitude, and it
wiggles in a consistent fashion, i.e., its short-term random time patterns always look the same in
a statistical sense. The latter condition means that its autocorrelations (correlations with its own
prior deviations from the mean) remain constant over time, or equivalently, that its power
spectrum remains constant over time. A random variable of this form can be viewed (as usual)
as a combination of signal and noise, and the signal (if one is apparent) could be a pattern of fast
or slow mean reversion, or sinusoidal oscillation, or rapid alternation in sign, and it could also
have a seasonal component. An ARIMA model can be viewed as a “filter” that tries to separate
the signal from the noise, and the signal is then extrapolated into the future to obtain forecasts.
(Hall, 2011)
 3.1.1 Planning Phase

In planning, the researchers gathered importance ideas and researched data which useful
in creating Crime Rate Reduction through Forecasting Utilizing Autoregressive Integrated
Moving Average (CRRFUARIMA). The phase includes the interview, gathering data,
Observation, and setting scope and limitations.

The researchers created plan in developing and proposed system. There were few
activities performed during this phase. First was defining the system to be developed. The
researchers performed a brain storming and apply the proposal system in the organization.
Second was the communication with the end user. The researchers were able to know the
necessary data requirements in making the proposal system. Third was setting the scope of the
proposed system. By setting the scope, the researcher would have a guide on were to limit the
system. The researchers also included the budgeting of expense throughout the process on
building proposed system.

In this phase, the researchers set goals and objectives in developments the system study
by making some list of activities using which help to monitor and to manage the time. This
calendar of activities is very useful in checking the progress of the system.

3.1.1.1 Calendar of Activities

The chapter scheduled the activities and the steps by the researchers to attain and
complete the development of Crime Rate Reduction through Forecasting Utilizing
Autoregressive Integrated Moving Average (CRRFUARIMA)

Phase June July August September October

Planning
Analysis
Design
Implementation
Maintenance
3.1.1.1 Calendar of Activities for 1st Semester
 Phase June July August September October
Planning
Analysis
Design
Implementation
Maintenance
3.1.1.2 Calendar of Activities for 2nd Semester

3.1.2 Analysis Phase

The analysis phase involved the researchers and the end-user to work together and to
gather, understand and document the Crime Rate Reduction through Forecasting Utilizing
Autoregressive Integrated Moving Average (CRRFUARIMA).

Based on the interview with police station staff, the researchers were able to understand
the current set-up of the crime rate of Oroquieta City. The researchers gathered data information
and use it for the systems requirements.

By making the interviews, the researchers analyze the given data to come up with
concrete information into specify the existing problem sequentially.

3.1.2.1 Functional Requirements

Required software is for conducting Crime Rate Reduction through Forecasting Utilizing
Autoregressive Integrated Moving Average (CRRFUARIMA) and providing results. The system
should satisfy the following requirements.

3.1.2.1.1 User Requirements

3.1.2.1.1.1 Administrator Aspect

1. Logging into the system.

2. Taking back up for database.
3. Forecasting crime rates.
4. Updating crime record.
5. Monitoring crime records.
 6. Generating crime reports.
7. Logging out into the system.

3.1.3 Design Phase

3.1.2.1.2 System Requirements

The following are the hardware and software requirements for the user to run the system
effectively:

3.1.2.1.2.1 Hardware Requirements

The following are the hardware requirements needed for the user to run the
system effectively:

 Computer

This will enable the user to view, use and run the system smoothly.

 Printer

The device should have at least a budget for ink in order for the system to be
usable in terms of printing documents or reports about crimes.

3.1.2.1.2.1.2 Software Requirements

The following are the hardware requirements needed for the user to run the
system effectively:

 Windows XP/7/8
An operating system that supports the installation of Apaches is Unix-based web
server from the Apache Software Foundation.
 MySQL
A multithreaded database management system and PHP which is server-side
scripting language.
3.1.2.2 Hardware Interfaces

3.1.2.2.1 Software Interfaces

The following software requirements are needed to develop the proposed system.

3.3.2.3 Non-functional Requirements

Performance:

 The system can save crime records for a long period of time.
 The system only supports one (1) user as the admin.

Usability:

 The system should be user friendly and should require least effort to operate.

Portability:

 This system was created using HTML, CSS, JavaScript, PHP, etc. which are
platform independent and can be transported to other servers with minimum
effort.

3.3.2.4 System Function

 Login – the admin enters his/her account before managing the system.
 Logout – the admin will logout after his/her work after using the system.
 Add - the administrator will add crime reports.
 Update - in this phase only the admin is responsible to this. He/she can update the
crime reports.
 Search - the user can search places that have high crime rates.
 Generate - the user can collect the generated reports about crime rates.
Context Diagram

Admin

Organization
Chart of
PNP Staff
Crime
Details
Forecast
Crime
History

Crime Reports
(monthly or annually)

CRIME RATE REDUCTION

THROUGH FORECASTING
UTILIZING AUTOREGRESSIVE
INTEGRATED MOVING AVERAGE

Intensity of crime
(major or minor)
Crime
Details

Crime

The context diagram for the proposed system shown in the figure, Crime Rate Reduction
through Forecasting Utilizing Autoregressive Integrated Moving Average (CRRFUARIMA) has
(2) two external entities named Admin and Crime.

The admin will the one responsible in manipulating the system. The admin will then
input the data to the system. The admin manages the PNP staff to monitor the crime rates within
the area. Crime is either major or minor and the admin is responsible in generating the reports of
the crime rate accumulated all throughout the entire year.
 Top Level Diagram

Crime details
Crime details
Admin Crime MajorC

Crime
details
Forecast
details
6.0
4.0
Generate
Update
reports

Admin accnt.
5.0
Report Gives forecast
details database Forecast
1.0
Log in details

Crime Crime
details 2.0 3.0 details
Investigates Add crime
crime details

Reports

Forecast details Crime details

Reports Forecast MinorC

Crime details

The top level diagram for the proposed system shows the Crime Rate Reduction through
Forecasting Utilizing Autoregressive Integrated Moving Average (CRRFUARIMA) which has
(6) six processes, (1) one data store and (6) one external entity, namely: Admin, Crime, MajorC,
MinorC, Forecast and Reports.

The admin examine the crime by doing investigations. The admin then inputs the
information gathered into the system for further examination of the crime. After that the admin
then determine whether the crime is major or minor. After determining, the admin then generate
reports regarding the crime. The admin is also responsible for the forecasting of crime rates.
They can also retrieve crime record history. The reports can also be printable.
Database Design

Entity Relationship Diagram

Admin Crime MajorC

1...* 1...*
User investigates MJ_ID
Crime_ID 1...* 1...*
Pass Entry_ID
Entry_ID has Type
Findings Victim
1...* Remarks Accused
1...*
Witness
Note
gives 1...*

1...*
has
Forecast MajorC
generates
MN_ID
1...* Entry_ID
FID
Type
Rate
Victim
Location
Accused
Warning
Witness
Message
Note
1...*

Reports

RID
Entry_ID
Location
Incident.no
Type
Percentage
Monthly
Annually

The ER-Diagram in the figure, there are (6) six external entities: the Admin, Crime,
MajorC, MinorC, Forecast and Reports.

The Admin will manage the system. The staffs are responsible for taking the crime
details. Crime is determined into (2) two: MajorC and MinorC and is the main reason why this
system is created. Forecast is responsible in sending forecasting about the crime rate. And the
crime reports are printable.
Data Dictionary
Structured Chart

A Structure Chart in software engineering is a chart which shows the breakdown of a

system to its lowest manageable parts. They are used in structured programming to arrange
program modules into a tree. Each module is represented by a box, which contains the module’s
name. The tree structure visualizes the relationships between modules, showing data transfer
between modules using arrows. Structured Charts are an example of a top-down design where a
problem (the program) is broken into its components.

Structured Chart

CRIME RATE REDUCTION THROUGH FORECASTING UTILIZING

AUTOREGRESSIVE INTEGRATED MOVING AVERAGE

Admin Crime

Major Minor
Log in Update Profile Update Accnt.

Reports
Organization Chart of
Update
PNP Staff

Update
Monthly Annually
View

Crime History

Add

Save

Update

Forecast

Save

The Figure above shows the Structure Chart of Crime Rate Reduction through Forecasting
Utilizing Autoregressive Integrated Moving Average (CRRFUARIMA). (2) Two main modules
– Admin and Crime. Admin has (5) five sub modules – Login, Organizational Chart of PNP
Staff, Crime History and Forecast. Login has (1) one sub module – Admin Profile. Admin Profile
has (1) one sub module – Update Account. Organizational chart has (1) one sub module –
Update. Crime history has (4) four sub modules – Update, View Add and Save.
 Forecast has (2) two sub modules – Update and Save. Crime has (2) sub modules – Major
and Minor. Reports have 2 sub modules – monthly and annually.

3.1.3 Implementation Phase

In this phase, the researchers implemented the system, to check whether the application
meets all the requirements of the client and to detect the errors. The researchers checked whether
the work done meets the standards of the organization. They will input values and check if the
output as expected. The researcher integrated and tested the system and proved that the system
meet all requirements, including for performance and accuracy.

Once the testing was done, the researchers then found the developed system ready to
deploy to the user. The researcher developed the system was installed, initial user training was
completed, and user documentation was delivered. All of the goals in the project plan for
satisfactory result to the user.

3.1.4 Operation and Maintenance

There are some issues which came up in the client environment. To fix those issues
researchers then provided some services to maintain the system. Maintenance is done to deliver
these changes in the user environment. It is the modification of a software product after delivery
to correct faults, to improve performance or other attributes. It includes errors corrections, and
enhancement of capabilities.