Cybercrime is a growing threat in today’s digital world. This project aims to analyze and predict cyber crimes using machine learning algorithms based on real-world datasets. By leveraging data-driven approaches, the project attempts to help stakeholders identify patterns, trends, and potential threats effectively.

This repository contains code and resources for building a classification model to detect or predict types of cyber crimes. The machine learning pipeline involves data preprocessing, model training, evaluation, and visualization.

Key components:

Data Cleaning and Preprocessing

Exploratory Data Analysis (EDA)

Classification using Random Forest

Evaluation using confusion matrix and classification report

Modular Python code structure

Cyber Crime Dataset from Kaggle: 📦 Download here

Place the downloaded CSV file in the data/ directory and rename it to cybercrime_data.csv.

Random Forest Classifier (Scikit-learn)

Label Encoding for categorical data

Train-Test Split for model validation

Future improvements may include:

XGBoost, SVM, or Neural Networks

Feature Engineering and PCA

Anomaly Detection for advanced cyber crime prediction