This project helps remote workers find optimal work-friendly locations by clustering real-world venues (cafes, libraries, coworking spaces, etc.) based on environmental features like noise level, Wi-Fi strength, and comfort level using unsupervised machine learning (K-Means clustering).
- Collects real-world venue data using the Foursquare Places API
- Simulates environmental features like:
- Noise Level (in decibels)
- Wi-Fi Strength (in Mbps)
- Comfort Level (scale of 1 to 10)
- Uses the Elbow Method to determine the optimal number of clusters
- Applies K-Means clustering to group similar venues
- Evaluates results using Silhouette Score
- Visualizes clusters using scatter plots
- Python
- Pandas & NumPy
- Scikit-learn (KMeans, metrics)
- Matplotlib & Seaborn
- Foursquare Places API
- Google Colab
- Used Elbow Method to find the best
k - Calculated Silhouette Score to evaluate clustering quality
The final clusters group locations based on a combination of noise, comfort, and Wi-Fi quality, allowing remote workers to identify the most suitable environments. This can be expanded into a mobile/web app for real-time recommendations.
- Integrate live sound/Wi-Fi sensor data from mobile devices or APIs
- Deploy as a web app with maps and real-time user input
- Add user reviews and crowdsourced comfort ratings