Alternative Data and NLP in Quant Strategies › Key Parameters
Michael BrenndoerferJanuary 4, 20261 min read
Quantitative FinanceAll chapters Part 13 of 15Machine Learning and Alternative Data
Alternative Data and NLP in Quant Strategies › Key ParametersOne section · Sections in this chapter9 / 18 ↓
Sections in this chapter18
Reading tools Definitions & inline links
Choose your expertise level to adjust how many terms are explained. Beginners see more tooltips, experts see fewer to maintain reading flow. Hover over underlined terms for instant definitions.
Article links
Make inline references clickable
Key parameters for deep learning sentiment models.
- pretrained_model: Choice of transformer architecture such as BERT, FinBERT, or RoBERTa. FinBERT is specifically fine-tuned on financial text and typically performs best for financial sentiment.
- max_length: Maximum sequence length for tokenization, typically 128 to 512 tokens. Longer sequences capture more context but increase computational cost.
- learning_rate: Controls how quickly the model adapts during fine-tuning. Financial text typically requires lower learning rates than general text.
- num_epochs: Number of training passes through the data. More epochs improve fit but risk overfitting.