Copyright © 2026 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{178697,
        author = {VAKKALAGADDA NAMITA and Mrs N RANGA SREE and NUKATHOTI SRAVANI and RAVULAPATI PAVITRA and UNDARAKONDA VARSHINI LAKSHMI},
        title = {CRIME PREDICTOR FOR ANDHRA PRADESH},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4796-4800},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178697},
        abstract = {Advancements in machine learning and data analytics are enabling more effective methods of predicting criminal activity. Crime prediction systems, when powered by tools like TensorFlow, can analyse historical crime data to forecast potential future incidents in terms of location, time, and type of crime. The objective is to support law enforcement and policy makers in identifying patterns and optimizing resource allocation.
TensorFlow, an open-source machine learning framework, plays a significant role in building and training predictive models for this purpose. Algorithms such as Random Forest, Naïve Bayes, Support Vector Machines, and deep neural networks can be implemented within TensorFlow to learn from large and complex datasets. These datasets typically include crime records with attributes like geographical location, date, time, and crime category.
By leveraging TensorFlow’s capabilities, these models can automatically learn from past crime data and improve their accuracy over time without manual intervention. Pattern recognition, statistical modelling, and geographical analysis are combined to enhance the model's ability to predict criminal behaviour more accurately. Experimental results show that models built using TensorFlow outperform traditional crime prediction methods. These models provide valuable insights that can aid in crime prevention strategies, urban planning and more informed decision-making by public safety authorities.},
        keywords = {Tensor Flow, Random Forest, Naïve Bayes, Support Vector Machines, Deep neural networks.},
        month = {May},
        }