AI-Investment-ChatBot-SOC-2024

This is the doc link consisting of the whole resources. CLICK HERE

Task 1

Objective: Implement basic forecasting models you have learned in Python. Use data from Nifty 50 or any other source you prefer. Utilize the yfinance library to fetch the data.

Instructions:

1. Data Collection:

   • Use the yfinance library to download historical stock price data.
   • Choose a stock or index (e.g., Nifty 50) and specify the date range for the data.

2. Data Preparation:

   • Split the data into training, validation, and test sets.
   • Ensure the data is preprocessed appropriately (e.g., handling missing values, normalizing if necessary).

3. Model Implementation:

   • Implement the following forecasting models:
     • ARIMA
     • SARIMA
     • Exponential Smoothing
   • Feel free to implement additional models if you are comfortable with them.

4. Model Evaluation:

   • Train your models using the training set.
   • Validate the models using the validation set to fine-tune hyperparameters.
   • Test the models on the test set and evaluate their performance.

5. Results Presentation:

   • Show the predictions of each model and compare them with the actual values.
   • Visualize the results using plots (e.g., line plots for actual vs predicted values).
   • Calculate and display relevant metrics (e.g., RMSE, MAE) to evaluate the models' performance.

6. Documentation:

   • Document your code clearly, explaining each step and the reasoning behind it.
   • Include comments in your code to enhance readability and understanding.
   • Provide a summary of your findings and insights from the model comparison.

Deliverables:

• A Jupyter notebook or Python script containing the code for data collection, model implementation, and results visualization.

---

Additional Resources:

• yfinance Documentation
• ARIMA Model in Python
• SARIMA Model in Python
• Exponential Smoothing in Python

Feel free to reach out if you have any questions or need further assistance!