Large language models like ChatGPT could supercharge sentiment analysis, a key aspect of trading.
If you ask a large language model (LLM) like ChatGPT how to choose an LLM, it will give you an answer such as this from GPT-4:
โChoosing the best large language model is a lot like speed dating: you ask it severalย questions, hope it impresses you with its wit and intelligence, and then decide if you want to spend the rest of your project together!โ
In the world of finance, the principle of supply and demand serves as a foundational mechanism for determining the fair price of any investment class at any point in time. This economic concept holds that the equilibrium price of an investment is established when the quantity demanded by buyers matches the quantity supplied by sellers.
Fundamental factors have long played a critical role in assessing traditional equity markets, where investors analyze a companyโs financial health, industry position and overall economic climate to determine its intrinsic value. Key metrics such as earnings, revenue and debt-to-equity ratios provide a clear imageย of a companyโs performance, enabling investors to make buy/sell decisions. Nonetheless, such metrics are not available isย still in the rapidly evolving world of cryptocurrencies.
The absence of financial statements and difficulty of estimating the impact of emerging technologies makes it hard to value digitalย currencies by traditional pricing methods. Furthermore, the extreme price volatility further challenges the efficiency of fundamental analysis in the cryptocurrency space.
In the absence of traditional valuation methods, the price often appearsย to be determined by the sentiment around the overall cryptocurrencyย market and/or a particular cryptoย token. The perception and emotional reactions of market participants often play a more prominent role in driving price fluctuations and shaping financing decisions.
For a rational trader, such irrationality presents aย chance in the market โ if only she could quickly and accurately capture the mood (aka sentiment) of the market. For severalย years, working with sentiment seemed like an insurmountable challenge. Day traders mostly relied on cryptocurrency news headlines, Discord insider chats and announcements. And systematic traders had to invest considerable effort into development of just average-quality sentiment analysis tools. The limitations of technology at the time made it difficult to efficiently process and understand the vast amounts of data generated by worldwide media.
The revolution in transformers and LLMs, inย particular, allowed traders to approach sentiment at scale, delivering an incredible improvement over traditional methods that relied on manual scoring and Word2Vec models.
The competitive landscape of software-based technology corporations vying to create the best LLM is rapidly evolving now. The table below provides an impressive illustration of this ongoing race, showcasing some of the key players and their respective contributions to the field:
These LLMs continue to boostย in size and makeย better performance, surprising even their creators. And while people debate about whether LLMs are the 1st indicationsย of artificial general intelligence (AGI) or just mindless parrots, their use in different industries and finance inย particularย will only accelerate.
Theย capacity revolution brought about by transformers and LLMs could significantly transform the cryptocurrency trading landscape. With the capability to assess market sentiment on a larger scale, traders canย potentially be able to capitalize more effectively on market irrationalities.
You can learn more about LLMs, their types and applications in our most up-to-date white paper, available here.
Nick Baker.
