AI SafeSpot: Women Safety Risk Predictor

Inspiration

Making safe travel decisions is a major concern, especially in areas where people are unaware of the risk levels associated with different locations. Many individuals commute daily without clear insights into safety conditions. This inspired the idea of building a system that uses data and artificial intelligence to analyze and present safety risks in a simple and understandable way.

What it does

AI SafeSpot is an intelligent safety analysis system that evaluates the risk level of a location using crime-related data.

The system analyzes factors such as assault, kidnapping, and other incidents to generate a safety risk score between 0 and 1. Based on this score, locations are categorized into:

• Low Risk
• Moderate Risk
• High Risk

It also provides visual insights through charts and maps, helping users better understand patterns and identify high-risk regions for safer decision-making.

How I built it

The project was developed using machine learning along with modern web technologies.

A model was trained using a real-world dataset containing crime statistics. The model learns relationships between different crime features and overall safety risk. Once trained, the model was integrated into a backend using FastAPI.

The backend exposes an API that receives input data and returns a predicted risk score. The frontend was built using Streamlit, allowing users to input data, view predictions, and explore visualizations such as charts and maps. The frontend communicates with the backend to fetch results in real time.

Challenges I ran into

One of the main challenges was integrating the machine learning model with the backend and ensuring smooth communication with the frontend. Handling and aligning dataset features with user inputs required careful attention. I also faced issues related to environment setup, dependency management, and debugging API responses.

Accomplishments that I'm proud of

I successfully developed an end-to-end system that combines machine learning, backend APIs, and an interactive frontend. The application can generate real-time predictions and present data in a clear and user-friendly way. I am proud of building a solution that applies technical skills to a meaningful real-world problem.

What I learned

Through this project, I gained practical experience in training and deploying machine learning models. I learned how to use FastAPI for backend development and Streamlit for building interactive frontends. I also understood how to structure a complete AI-based application using real-world data.

What's next for AI SafeSpot

In the future, I plan to enhance the system by incorporating larger datasets and improving model accuracy. I also aim to integrate real-time data sources and location-based analysis for more dynamic predictions. Additionally, I plan to improve the user interface and expand the solution into a mobile-friendly platform for better accessibility.

Built With

• fastapi
• machine-learning
• matplotlib
• numpy
• pandas
• python
• scikit-learn
• streamlit