Enhancing Technical Trading Strategy on the Bitcoin Market using News Headlines and Large Language Models

We present a technical trading strategy that leverages the FinBERT language model and financial newsanalysis with a focus on news related to a subset of Nasdaq ۱۰۰ stocks. Our approach surpasses the baselineRange Break-out strategy in the Bitcoin market, yielding a remarkable ۲۴.۸\% increase in the win ratio forall Friday trades and an impressive ۴۸.۹% surge in short trades specifically on Fridays. Moreover, weconduct rigorous hypothesis testing to establish the statistical significance of these improvements. Ourfindings underscore considerable potential of our NLP-driven approach in enhancing trading strategies andachieving greater profitability within financial markets.

Keywords:

Quantitative Finance , Technical Analysis , Bitcoin Market , NLP , Large Language Models