top of page

Your next sentiment driven portfolio rebalance may be powered by Inventzia SciTech trained GPT-4




The buzzword for everyone is now AI. Inventzia SciTech has been working on proprietary neural networks for many years obtaining excellent results in various quantitative predictive fields, spanning from risk estimation to recommendation systems and time series predictions. With the advent of LLM (Large Language Models) AI has expanded into a new dimension, that of learning from large sources of unstructured text data. While it is known in the quantitative analyst communities that LLM fare poorly so far when used to model and predict quantitative effects, they excel in the ability to synthesize and discover patterns in text. Starting from the latest GPT-4 release, Inventzia SciTech is preparing a specially trained derived model to estimate the ongoing prevailing sentiment toward a range of macro-economic indicators and stock tickers.

This model will provide an "almost human touch layer" to standard quantitative based investment models.

Comments


Featured Posts
Recent Posts
Archive
Search By Tags
Follow Us
  • Facebook Basic Square
  • Twitter Basic Square
  • Google+ Social Icon
bottom of page