Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175108,
        author = {Riya Bansilal Mulani and Anushka Biswas and Jaypriya J and Vinay M},
        title = {A Study on Crime Hotspot Detection and Prediction Using Spatial-Temporal Modeling for Safe Navigation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {8022-8029},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175108},
        abstract = {This research explores advanced methods for crime hotspot detection and forecasting using spatial-temporal modeling and machine learning techniques. We employ the Space-Time Permutation Model (STPM) via SatScan to classify crime hotspots in Pune city, India, comparing its effectiveness with Kernel Density Estimation (KDE) and Getis-Ord Gi* statistics. While these approaches produce generally similar outcomes, minor discrepancies suggest the need for improved detection strategies. Additionally, we apply machine learning algorithms, including Logistic Regression, SVM, and Random Forest, to crime datasets from Chicago and Los Angeles to enhance prediction accuracy. Our findings highlight the potential for integrating real-time data and predictive models to optimize law enforcement resource management and improve future crime prevention efforts.},
        keywords = {Crime hotspot detection, spatial-temporal modeling, Space-Time Permutation Model, SatScan, Kernel Density Estimation, Getis-Ord Gi* statistic, machine learning, crime prediction, Logistic Regression, SVM, Random Forest, ARIMA, LSTM, real-time data, law enforcement},
        month = {May},
        }