afzalur/Qwen-Market-Prediction-Model

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 3, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Warm

The afzalur/Qwen-Market-Prediction-Model is a 4 billion parameter causal language model, fine-tuned by Afzalur Rahman from Qwen3-4B-Thinking. It specializes in financial analysis of NIFTY 50 market data, predicting short-term price movements and providing reasoning based on technical indicators like RSI, MACD, and Bollinger Bands. This model is optimized for traders and financial analysts requiring AI assistance for technical analysis within the Indian stock market.

Loading preview...

Qwen Market Prediction Model: NIFTY 50 Forecasting

This model, developed by Afzalur Rahman, is a fine-tuned version of the Qwen3-4B-Thinking causal language model, specifically adapted for financial market prediction. It focuses on analyzing NIFTY 50 market data to forecast short-term price movements.

Key Capabilities

  • Technical Indicator Analysis: Interprets RSI, MACD, and Bollinger Bands to identify market trends.
  • Directional Prediction: Forecasts next-day price movement (Up/Down/Flat) for NIFTY 50.
  • Percentage Change Estimation: Provides an estimated percentage change in price.
  • Confidence Levels & Reasoning: Offers confidence scores for predictions and explains the underlying market forecasts.
  • Efficient Fine-tuning: Utilizes LoRA adaptation, adding approximately 41 million trainable parameters to the 4 billion parameter base model, resulting in a compact adapter size of ~168MB.

Training and Evaluation

The model was trained on historical NIFTY 50 price data, technical indicators, options data, and VIX data. Evaluation on a held-out test set showed promising directional accuracy under standard market conditions, with particular sensitivity to RSI values and MACD/Bollinger Band patterns. The model's predictions are probabilistic and should be used as one input among many for financial decision-making.

Good For

  • Traders and Financial Analysts: Seeking AI assistance for technical analysis of the Indian stock market.
  • Integration into Financial Tools: Suitable for trading dashboards, market research platforms, and algorithmic trading systems (with risk management).
  • Educational Purposes: Can be used in platforms teaching technical analysis.

Finetunes
1 models