The signal is multicross. The algorithm training was developed through the Python platform with trend following and mean-reverse criteria. It is an algorithm that works on multi-TF starting from H1 for trading in intraday scalping mode up to TF H4 and D1, preferred for trading in swing mode. The result of the algorithm was subsequently subjected to the Monte Carlo analysis to obtain more certain results from a statistical point of view. The algorithm uses roughly ten proprietary filters and standard filters, including price standard deviation, linear regression, OBV (on-balance volume) to highlight potential price accumulation and distribution zones, the ADX multi-TF to measure the strength of the trend. For some specific setups, the SSI (Speculative Sentiment Index) filter is also used, which indicates the ratio between buyers / sellers for a given instrument. The set and combination of these filters is constantly reviewed and calibrated according to the different market phases.