NORMA eResearch @NCI Library

Optimized Predictive Modelling to Unfold the Links of Crime with Education, Safety and Climate in Chicago

Pillai, Ratna (2019) Optimized Predictive Modelling to Unfold the Links of Crime with Education, Safety and Climate in Chicago. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (2MB) | Preview

Abstract

Crime is one of the common issues faced by any country that impacts both society and economy. Although, the overall crime rate in Chicago began to decline since the early 20th century, violent neighbourhoods still exist and continue to disrupt public peace. Moreover, the gun violence crimes aggravated the situation in Chicago in 2016, costing more than 700 lives and monetary costs estimated over 3 billion USD in 2018. Multiple studies are being carried out continuously to understand the cause of crime and violence in Chicago with a motive to improve public safety. Common census factors and ethnicity are studied enormously in this field to understand their relationships with crime. However, the complex nature of crime creates a wide scope to study several other factors which could possibly be a cause of crime. This research aims to identify whether violation and narcotics crimes in Chicago are linked to high schools, areas with surveillance cameras and climate.
Using this link, crime occurrences are predicted at a geohash level rather than at a community level. To achieve this, machine learning models like multiple regression, XGBoost, random forest and artificial neural networks are used. Each model is optimized and evaluated using standard regression metrics such as R2 statistic and RMSE (Root Mean Squared Error). XGBoost outperformed all the other models with a highest R2 value of 88% and RMSE value of 2.57 crime counts.
Keywords: Crime Prediction, Predictive Model, Machine Learning, Education, Climate, Safety

Item Type: Thesis (Masters)
Subjects: H Social Sciences > HN Social history and conditions. Social problems. Social reform
L Education > L Education (General)
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 15 Jun 2020 11:09
Last Modified: 15 Jun 2020 11:09
URI: https://norma.ncirl.ie/id/eprint/4281

Actions (login required)

View Item View Item