A Predictive Analytics Framework for Crime Type Forecasting
International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)
DOI: 10.15662/ijeetr.2026.0802225 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von A Kasithangam N und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Understanding crime patterns is essential for improving public safety and making informed decisions based on data. This project presents a web-based application that studies past crime records and predicts possible crime types using machine learning techniques. The system is developed using Python and Streamlit, which makes it interactive and easy for users to explore. A real-world crime dataset from Kaggle is used to train and test the model. Algorithms such as Support Vector Machine and Random Forest are applied to recognize patterns in the dataset and generate predictions. Apart from prediction, the system also provides charts and visual summaries that allow users to observe trends, frequency, and distribution of crimes more clearly. The purpose of this project is not only to build a prediction model but also to demonstrate how machine learning can be practically used to analyze real-world data and derive useful insights from it
Zitieren
APA
N, A. K., J, J. K., M, P., & R, S. (2026). A Predictive Analytics Framework for Crime Type Forecasting. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802225
Vancouver
N AK, J JK, M P, R S. A Predictive Analytics Framework for Crime Type Forecasting. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802225
BibTeX
@article{N2026,
author = {N, A Kasithangam and J, Jayashree K and M, Priyavarshini and R, Shalini},
title = {A Predictive Analytics Framework for Crime Type Forecasting},
journal = {International Journal of Engineering & Extended Technologies Research},
year = {2026},
volume = {08},
number = {02},
doi = {10.15662/ijeetr.2026.0802225}
}
EUVIMED