LikeLogic-Engine

Machine Learning system for predicting Facebook post engagement (daily likes) using historical interaction data.

---

Overview

LikeLogic-Engine is a machine learning web application that predicts the number of likes a Facebook post will receive based on engagement signals such as user interactions, video replays, and unlikes.

It enables data-driven social media decision-making by estimating post performance using historical behavioral patterns.

Built with Streamlit and a supervised regression model, it transforms raw engagement metrics into real-time predictive insights.

---

🎯 Key Features

Engagement Analytics Dashboard

Interactive visualizations for:

• Likes trends
• Unlikes patterns
• Engagement behavior
• Video replay activity

---

🧠 Machine Learning Prediction Engine

A regression-based model that predicts expected daily likes using engagement inputs such as:

• Unlikes per day
• Engagement interactions
• Video replay counts

---

⚡ Real-Time Prediction Interface

Instant prediction system that outputs estimated likes based on user-provided metrics.

---

📊 Data Insights Layer

Helps users understand how engagement signals influence content performance.

---

Model Overview

• Algorithm: Linear Regression
• Task Type: Supervised Regression
• Input Features: Facebook post engagement metrics
• Output: Predicted daily likes
• Dataset Size: 34,000+ interaction records (Kaggle dataset)

---

System Architecture

User Input (Engagement Metrics)
        ↓
Data Validation & Preprocessing (Pandas / NumPy)
        ↓
Feature Processing Layer
        ↓
Trained ML Model (Joblib - Linear Regression)
        ↓
Prediction Output
        ↓
Streamlit Visualization Layer

Run Locally

1. Clone repository

git clone https://github.com/Pro-phet123/LikeLogic-Engine.git

2. Enter project folder

cd LikeLogic-Engine

3. Create virtual environment

python -m venv venv

4a. Activate virtual environment(windows)

venv\Scripts\activate

4b. Activate virtual environment(mac/linux)

source venv/bin/activate

5. Install dependencies

pip install -r requirements.txt

6. Run the application

streamlit run social.py

🌐 Live Demo

Launch Web App