Stock trading with cycles: A financial application of ANFIS and reinforcement learning

► Reinforcement learning is used to formalize an automated process for determining stock cycles by tuningthe momentum and the average periods. ► The secondary and tertiary trends or short-term wave cycles are eliminated by a smoothing technique. ► The use of reinforcement learning (RL) as a non-arbitrage algorithmic trading system. ► Our study attempts to identify the change of a primary trend or a broad movement. ► Dynamic asset switching based on the detection of peaks and troughs within a portfolio of stock counters.