To predict the next song at salsa, bachata, or kizomba events, the model considers factors like tempo, rhythm, mood, lyrics, and popularity of the current song. It aims to select a song that will keep the audience engaged and maintain the energy level. The proposed solution uses a random forest model trained on a dataset of songs to predict popularity. It has estimated popularity for new songs but faces challenges adapting to available data. Current priorities include implementing playback of predicted songs in real time.