

This approach plays to ChatGPT’s strengths by allowing it to produce conversational, easily digestible explanations of price moves underpinned by our system’s highly technical model output coupled with carefully curated news and social media content.
#Garbage in garbage out drivers
In order to generate succinct, useful explanations of why asset prices are moving in the market, we are sending ChatGPT the combined output of our proprietary fundamental models, which analyze potential volatility drivers ranging from calendar events to social media posts. And that is our current approach at MarketReader. In order to get specific results that are more suited to technical applications, it needs to be trained on domain-specific language and fed timely, well curated data at the input stage. In other words, ChatGPT is a blunt instrument, but it can be made much more precise.ĬhatGPT is trained on a large dataset of general conversational text and thus excels at producing conversational, “human-sounding” output.

Large language models, like GPT and BERT, are fantastic for generalist use cases but tend to struggle when it comes to understanding the nuances of domain-specific language, such as that used in finance. This is a classic “garbage in, garbage out” problem. In some cases, companies have even banned the use of ChatGPT due to risks posed by inaccurate output. It has essentially reached household status, yet most are unfamiliar with how large language models such as ChatGPT actually work.Īs a result of this confusion, many companies have tried to benefit from ChatGPT’s human-like conversational abilities but struggled to get consistently useful output. The AI chatbot, predicated on a neural network machine learning model, seems ubiquitous. ChatGPT is having a moment, but it isn’t meeting everyone’s expectations.
