The popular press is abuzz with articles about AI's transformation of investing, financial research and analysis, and stock market forecasting. At MarketPsych we work in the field of AI with large language models (LLMs) including chatGPT, and in today’s newsletter we explain some LLM trading basics as well as our own successful AI agent designed for stock price forecasting. To illustrate the value of AI in investing, we'll start with the human weaknesses it is designed to exploit…
Investing on fear
AI vs AGI
chatGPT is a non-sentient model (it's not conscious), and there is a big gap between it and the type of artificial general intelligence (AGI) described in the Fear Index. As physicist David Deutsch noted: “AI [artificial intelligence] has nothing to do with AGI [artificial general intelligence]. It’s a completely different technology, and it is in many ways the opposite of AGI … An AGI can do anything, whereas an AI can only do the narrow thing that it’s supposed to do.”
Below is a minutely depiction of our #RegimeChange score (blue line) for #Russia from June 22nd to 28th, 2023 UTC time.
MarketPsych's real-time NLP engine scours macroeconomic themes, political risk, and country-level signals around 100' of risk-related events from 1000s of #globalnews and #socialmedia sources in 13 languages. In partnership with Refinitiv, an LSEG business our clients set risk management alerts for 100s of such risk-related events. Available country-level indicators include #SocialUnrest, Terrorism, InflationForecast, BondStress, and 100+ more.
In Jan 2020 our MarketPsych team launched a stock predictive model in partnership with #StarMine and Refinitiv, an LSEG business, called the MarketPsych Media Sentiment (MMS) model. It is an #AI based model, making stock forecasts based solely on media themes and #sentimentanalysis.
The model was approved for production in Aug 2019 (red dotted line in the image) and has been sold commercially since Jan 2020. It showed yet another great performance in May 2023.
This model ranks stocks daily according to their expected relative performance for the following 30 days. This past May, the spread between the highest and lowest-ranked US stocks was 4.3%, accruing to +13.4% on a 12-trailing months basis. Among large-caps, the performance is at an impressive +22% with a Sharpe of 3.3. The decile spread is plotted in the image as the blue line.
There are predictive patterns embedded in the emotions and themes expressed about companies in news and social media. #behavioralfinance #quantitativefinance #quantitativeanalysis
For an introduction to MMS, please watch the promo video at: https://lnkd.in/gNqwX7fx
With U.S. commercial real estate sentiment plummeting, is it time to buy?
In the chart below we plotted the #Russell1000 price versus two moving averages of media-derived U.S. #commercialrealestate sentiment from 2020 to now. When the 90-day is under the 200-day, the gap between the lines is shaded pink. Note that COVID led to a slight downturn due to WFH (work from home), then there was optimism about RTO (return to office), but today's interest rate / hybrid work habits-driven collapse depressed sentiment much more.
The Wall Street Journal last week reported distressed asset buyers buying properties like #AgaveHoldings. Per managing director Jose Perez “We have learned from the past, that when everyone is selling, buy; and when everyone is buying, sell.”
#sentimentanalysis #sentiment #behavioralfinance
The U.S. CPI came out yesterday showing inflation at 4.9%. Our predictive model, based on the aggregate inflation forecasts from news and social media, shows a further significant inflation drop over the next month to 4.3%. This model has consistently had a 30% tighter fit to the U.S. CPI than the consensus of experts since it began rolling-forward (expanding window architecture) in 2004.
Once interest rate expectations plateau, then the market may resume its upwards drift.
Today's bankrun is targeting large non-US banks: Credit Suisse (a repeat target from back in October 2022) and BNP. Note that Schwab is in the green, probably due to being in the US (Fed backstop) and having a supportive CEO aggressively buying his own shares.
We plotted the overnight bullishness in the media about select major banks, below: