StockDirection-6K: Specialized Stock Movement Prediction

StockDirection-6K is a fine-tuned language model developed by khazarai, specifically designed for binary stock movement prediction. Unlike general-purpose LLMs, this 0.8 billion parameter model focuses on a very narrow, yet complex, financial task.

Key Capabilities & Features

• Targeted Prediction: Predicts "UP" or "DOWN" for the next day's stock price of Akbank (AKBNK) on Borsa Istanbul.
• Input Format: Utilizes a structured prompt detailing the daily percentage price changes over the last five days.
• Fine-tuned Data: Trained on a dataset of 6,300 labeled rows of historical AKBNK stock data, emphasizing sequence learning for financial time series.

Use Cases & Limitations

This model is primarily intended for:

• Educational Purposes: Demonstrating the application of LLMs in financial classification.
• Research: Exploring text-based sequence learning for stock direction.
• Proof of Concept: Serving as an example for specific stock price direction prediction using natural language prompts.

Important Note: This model is not intended for financial advice or live trading decisions. Its purpose is strictly for academic and experimental exploration of AI in finance.