Using simulated annealing on a QUBO feature selection problem cuts random forest training time for Bitcoin mixer detection by about 30% with F1 falling from 0.92 to 0.91.
Sensors 22(19), 7162 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection
Using simulated annealing on a QUBO feature selection problem cuts random forest training time for Bitcoin mixer detection by about 30% with F1 falling from 0.92 to 0.91.