Pricing a phone is a critical and complex decision for businesses and consumers. With new phone models launching rapidly, retailers must decide which models to stock, while consumers rely on pricing trends to make informed purchasing decisions.

However, phone pricing is influenced by multiple macroeconomic factors beyond historical data, including:

• Inflation Rate – Higher inflation increases production costs, leading to price hikes.
• GDP Growth – Strong GDP boosts consumer purchasing power, increasing demand for premium phones.
• Public Sentiment – Market perception and brand reputation directly impact pricing.
• Supply Chain Disruptions – Component shortages or geopolitical factors can lead to price fluctuations.
• Exchange Rates & Import Duties – Variations in currency exchange rates affect international pricing.

We developed a predictive AI model that integrates macroeconomic indicators and historical phone pricing trends to accurately forecast future prices.

✅ Ensemble Model (Gradient Boosting + LSTM): Captures both short-term fluctuations and long-term pricing trends.
✅ Macroeconomic Analysis: Incorporates external factors affecting phone prices.
✅ Historical Data Integration: Learns from past pricing patterns for more reliable forecasts.
✅ Streamlit UI: Interactive web application for real-time price predictions and visualizations.

1️⃣ Data Ingestion – Collects phone price trends and macroeconomic indicators.
2️⃣ Feature Engineering – Processes historical price movements, inflation rates, GDP trends, and supply chain disruptions.
3️⃣ Model Training – Uses an ensemble of Gradient Boosting and LSTM models to predict future prices.
4️⃣ Prediction & Visualization – Displays insights via an interactive Streamlit UI for retailers and consumers.

In addition to price prediction, our Multimodal AI Agent:
📊 Extracts insights from raw data across multiple sources.
🔄 Automates the workflow from data ingestion to insights.
🛡 Supports asset protection and social responsibility in disaster recovery.
⏳ Reduces manual verification time, improving operational efficiency.

With this AI-powered model, businesses and consumers can:

• 📉 Make smarter stocking decisions based on predictive insights.
• 📊 Understand pricing trends and plan purchases accordingly.
• 🏪 Optimize inventory management to reduce losses and maximize profitability.

• 📡 Incorporate real-time web scraping for up-to-date phone price tracking.
• 🗣 Leverage social media sentiment analysis to assess brand perception.
• ⚙️ Optimize hyperparameter tuning for improved prediction accuracy.

• Machine Learning: Gradient Boosting, LSTM
• Deep Learning: TensorFlow, PyTorch
• Data Processing: Pandas, NumPy
• Web Framework: Streamlit
• Visualization: Matplotlib, Seaborn

To run this project locally, follow these steps:

# Clone the repository
git clone https://github.com/your-repo/phone-price-prediction.git
cd phone-price-prediction

# Install dependencies
pip install -r requirements.txt

# Run Streamlit UI
streamlit enhanced_app.py