Inflation Macro AI NLP

SZ-NLP MARCH UPDATE: A FEW OF THE RECENT THEMES

[dividend_yield], [post_pandemic], [supply_shock], [home_cooking], [crossborder_trade] Even though the bears on long duration have lost some momentum, [inflation expectation] has continued […]

ESG AI Risk Investment

AI can resolve ESG rating shortfalls

“AI and machine learning can improve measurement of ESG risks to enhance investment performance, says State Street.

“By using artificial intelligence (AI) and machine learning, new data providers and analyses are popping up to address some of these concerns,” says Daniel Gerard, head of advisory solutions at State Street.

ESG is becoming increasingly important in the portfolio investment process…

The new era of AI; Causality, Prediction and Decision Making

From prediction to decision making  

In order to move to generate relevant predictive signals and guide decision making, best AI systems need to integrate another level of knowledge: beyond statistical measures, beyond causality, the ability to analyse and determine the level of stability of a dynamical system as well as the capacity to identify the existence of equilibrium or “attractors”.  

From Correlation to Causality 

Often causality is confused with correlation. Human intuition has evolved such that it has learned to identify causality through correlation; yet the fact that two quantities are …

NLP beyond sentiment: the new source of Alpha

The boundaries of true alpha have been pushed further since the last 10 years with the development of a large variety of alternative risk premia (ARP) strategies as a new layer between passive/beta investing and active alpha generation. Today, in order to go beyond risk premia strategies, alpha generators need to use not only current market observables (prices of assets, implied volatilities, …) but also some true fundamental forward-looking information as well as exogeneous variables directly rooted in macroeconomics, socioeconomics and geopolitics. Natural Language Processing (NLP) technology can be used today to identify stable causal and predictive relationships…