🧠 FitFounder AI – Data-Driven Fitness App Analytics Dashboard
🚀 Overview
FitFounder AI is a data-driven analytics and decision-support system built to support the launch and growth of a personalized fitness and nutrition app.
This project combines:
- Descriptive & Diagnostic Analytics
- Machine Learning Models
- Customer Segmentation
- Association Rule Mining
- Pricing Intelligence
- Future Customer Prediction System
🎯 Key Features
Market Overview
- Customer demographics
- Fitness and diet behavior trends
- Feature demand analysis
- Willingness-to-pay distribution
Customer Diagnostics
- Pain-point analysis
- Churn reasons
- Behavior vs interest insights
Predictive Analytics
- Classification (Accuracy, Precision, Recall, F1, ROC)
- Regression (Willingness to pay)
Customer Segmentation
- K-Means clustering
- Persona identification
Association Rules
- Apriori algorithm
- Support, Confidence, Lift
Future Customer Prediction
Upload new data to:
- Predict app interest
- Predict willingness to pay
- Get marketing recommendations
🗂️ Files Included
- app.py
- requirements.txt
- dataset files
- sample upload file
⚙️ Setup
Install dependencies:
pip install -r requirements.txt
Run app:
streamlit run app.py
🌐 Deployment
Upload all files to GitHub and deploy via Streamlit Cloud.
📊 Models Used
- Logistic Regression
- Decision Tree
- Random Forest
- Gradient Boosting
- K-Means
- Apriori
- Linear Regression
👨💼 Purpose
This project helps founders:
- Identify target customers
- Optimize pricing
- Design marketing strategies
