- Total Influencers
- Average Engagement
- High Risk Accounts
- Average Trust Score
Brands spend millions on influencer marketing, but many influencers have fake followers, low engagement, or suspicious audience behavior.
This project helps detect risky influencers using:
- AI-based trust scoring
- engagement analytics
- machine learning anomaly detection
- interactive dashboard visualization
- Influencer Trust Score System
- Fake Influencer Detection
- Engagement Rate Analysis
- Machine Learning Anomaly Detection
- Interactive Streamlit Dashboard
- Country-wise Influencer Filtering
- High Risk Influencer Detection
- Download Processed Analytics
- Python
- Pandas
- Plotly
- Streamlit
- Scikit-learn
- Seaborn
- Matplotlib
Used for:
- anomaly detection
- unusual influencer behavior analysis
- suspicious engagement pattern detection
- Total Influencers
- Average Engagement
- High Risk Accounts
- Average Trust Score
- Followers Analysis
- Engagement Distribution
- AI Anomaly Detection
- Category Distribution
- High Risk Influencers Table
- Large follower count does not guarantee high engagement.
- Low engagement influencers may indicate fake audience behavior.
- High anomaly influencers require manual brand verification.
- Trust score helps brands identify safer collaborations.
pip install -r requirements.txtpython -m streamlit run dashboard/dashboard.py- Real-time Instagram API integration
- NLP-based comment analysis
- Advanced AI fraud detection
- Brand collaboration recommendation engine
- Live influencer monitoring system
🔗 https://influenceguard-ai.streamlit.app
Aditya Singh





