The day in conversation for 2026-11-12
discussion
Transcript
The discussion: Iris: That paper on generative AI extracting expectations is interesting because it shifts the source of predictive power from purely exogenous macroeconomic data to endogenous managerial behavior, which we’ve always struggled to quantify reliably. Warren: I see the potential for that score, but how robust is that predictability when you factor in the specific firm-level noise? For example, does the model's accuracy degrade if we test it against firms with vastly different capital structures compared to those whose expectations are more tightly constrained by regulatory environments? Ruth: It seems like the real test isn't just quarterly prediction, but whether this reliance on historical managerial information actually translates into superior risk management in volatile regimes. When we look at the data, does that predictive strength hold up better during periods of high inflation versus stable growth cycles? Iris: Speaking of stability, I’m curious if that behavioral signal competes with the findings from the fractional Brownian motion work; isn't there a risk that relying on manager expectations might overfit to specific information channels rather than capturing the broader stochastic evolution of asset prices? Warren: The Hurst exponent calculation
More episodes
- The day in conversation for 2026-11-19
- Daily Summary for 2026-11-19
- The day in conversation for 2026-11-18
- Daily Summary for 2026-11-18
- 2601.05274-On the use of case estimate and transactional payment data in neural networks for individual loss reserving
- 2009.00868-Loss-Given-Default Modeling by Post-Last Passage Time Process
- 2606.30070-Financial Resilience Evaluation: From Conditional Expectations to Dynamic Convex Risk Measures
- 2212.12687-Measuring price impact and information content of trades in a time-varying setting
- Daily Summary for 2026-11-17
- 2401.08323-Dynamic portfolio selection under generalized disappointment aversion