Small AI Model for Stock Price Prediction: A High School Project
Analysis
This post describes a high school student's project to create a small AI model for predicting Apple stock price movements based on news sentiment. The student is seeking recommendations for tools, programming languages, and learning resources. This is a common and valuable application of machine learning, particularly NLP and time series analysis. The project's success will depend on the quality of the datasets used, the choice of model architecture (e.g., recurrent neural networks, transformers), and the student's ability to preprocess the data and train the model effectively. The binary classification approach (up or down) simplifies the problem, making it more manageable for a beginner.
Key Takeaways
- •Stock price prediction using news sentiment is a common ML project.
- •Recurrent Neural Networks (RNNs) or Transformers are suitable model architectures.
- •Data preprocessing and feature engineering are crucial for model performance.
“I set out to create small ai model that will predict wheter the price will go up or down based on the news that come out about the company.”