Skip to content

Aditya-Rajput-00/InfluenceGuard-AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI-Powered Fake Influencer Detection & Brand Trust Analytics

Dashboard Banner


Live Dashboard Features

KPI Analytics

  • Total Influencers
  • Average Engagement
  • High Risk Accounts
  • Average Trust Score

KPI Dashboard


Overview Analytics

Top Influencers By Followers

Overview Chart


AI Insights

Engagement Distribution & Anomaly Detection

AI Insights


Risk Analysis

High Risk Influencers Detection

Risk Analysis


Influencer Category Analysis

Category Analysis


Problem Statement

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

Features

  • 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

Technologies Used

  • Python
  • Pandas
  • Plotly
  • Streamlit
  • Scikit-learn
  • Seaborn
  • Matplotlib

Machine Learning Used

Isolation Forest

Used for:

  • anomaly detection
  • unusual influencer behavior analysis
  • suspicious engagement pattern detection

Dashboard Features

KPI Cards

  • Total Influencers
  • Average Engagement
  • High Risk Accounts
  • Average Trust Score

Interactive Visualizations

  • Followers Analysis
  • Engagement Distribution
  • AI Anomaly Detection
  • Category Distribution
  • High Risk Influencers Table

Business Insights

  • 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.

How To Run

Install Requirements

pip install -r requirements.txt

Run Dashboard

python -m streamlit run dashboard/dashboard.py

Future Improvements

  • Real-time Instagram API integration
  • NLP-based comment analysis
  • Advanced AI fraud detection
  • Brand collaboration recommendation engine
  • Live influencer monitoring system

Live Dashboard

🔗 https://influenceguard-ai.streamlit.app


Project Author

Aditya Singh

About

AI-powered influencer analytics dashboard using Python, Streamlit, Plotly & Machine Learning for fake influencer detection, trust score analysis, anomaly detection, and brand risk analytics.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors