Conference
Open access
2026
Predicting Financial Bubbles with Imbalanced Data
The results suggest that even with the SMOTE synthetic data, the noise in daily data makes it difficult to generate F1 scores comparable to bubble prediction using lower frequency data, and the tradeoff is between faster but noisier bubble detection and slower but more accurate bubble detection.
Alexei Bogoslavskiy
· ITM Web of Conferences · 0 citations