Lovable Prompt Creator - AI Prompt Generator

## APPLICATION OVERVIEW
This web application is designed to create a predictive model for stock analysis of the Ibex 35, utilizing Python and machine learning techniques. Its main purpose is to download historical stock data, process various financial indicators, and provide predictive analytics to assist users in making informed investment decisions.

## CORE FEATURES
1. **Data Downloading**: Automatically retrieve daily stock prices (open, close, high, low), trading volume, and various financial indicators (RSI, MACD, SMA, EMA, stochastic oscillator, ATR, Bollinger Bands).
   
2. **Data Visualization**: Display charts for each indicator and stock, allowing users to visually analyze trends and patterns.

3. **Data Cleaning and Preparation**: Implement tools for cleaning downloaded data and deriving additional variables for analysis, ensuring data quality for modeling.

4. **K-means Segmentation**: Use K-means clustering to segment stocks based on derived indicators and sentiment analysis from news.

5. **Predictive Modeling**: Employ random forest algorithms to predict stock movements (buy, sell, hold) for the next five days and compare predictions with actual market outcomes.

6. **Performance Analysis**: Provide insights and reports on the model's accuracy and learning, facilitating continuous improvement of predictions.

## DESIGN SPECIFICATIONS
- **Visual Style**: minimalist - Clean, simple design with plenty of white space, minimal color palette, and focus on typography.
- **Color Mode**: Light theme with dark text on light backgrounds.
- **Primary Color**: #1978E5 (accent for buttons, links, highlights).
- **Typography**: Use Inter from Google Fonts for headings, Inter for body text and UI elements.
- **Border Radius**: 8px (moderately rounded) for buttons, cards, and inputs.
- **Layout**: The layout will consist of a top navigation bar, a hero section for introductory information, followed by sections for data visualization, predictive insights, and a summary of performance metrics.

## TECHNICAL REQUIREMENTS
- **Framework**: React with TypeScript
- **Styling**: Tailwind CSS
- **UI Components**: shadcn/ui
- **State Management**: Redux or Context API as needed for managing app state.

## IMPLEMENTATION STEPS
1. **Set up the React project** with TypeScript and install Tailwind CSS for styling.
2. **Design the main layout**: Create components for the navigation bar, hero section, data visualizations, and performance analysis.
3. **Implement data fetching logic** to retrieve stock data from financial APIs and store it in state management.
4. **Create data visualization components** using libraries like Chart.js or Recharts for rendering financial indicators.
5. **Develop the K-means clustering functionality** and integrate it into the app to segment stocks based on analysis results.
6. **Implement the random forest model** using a suitable machine learning library (like TensorFlow.js or a Python backend) and connect predictions to the frontend.
7. **Build performance reports** that analyze the model's predictions against actual stock performance.
8. **Test the application thoroughly** to ensure all features work as intended and provide a seamless user experience.

## USER EXPERIENCE
Users will interact with a clean and intuitive interface, navigating through sections to download and visualize data. They can easily switch between different indicators and view predictive analytics. The application will provide real-time feedback on the model's performance, ensuring users remain informed and engaged throughout their analysis process.