Forecasting cryptocurrency markets using recurrence and time-frequency analysis-based machine learning algorithms

• We develop machine learning algorithms for forecasting cryptocurrency prices. • Algorithms use return data transformed into recurrence statistics and spectrograms. • The XGBoost algorithm achieves AUC above 76.7% and accuracy of 70%. • Our algorithm supports optimisation of cryptocurrency portfolio management. This study is the first to integrate recurrence plots, recurrence quantification analysis (RQA) and short-time Fourier Transform (STFT) to predict cryptocurrency market behaviour. Recurrence plots, RQA statistics and STFT spectrograms were calculated from return data and used as input in random forest algorithms as they are optimal tools for identifying non-linear dynamics in market data and analyse their frequency. Our optimised XGBoost algorithm provided a forecasting AUC above 76.7% and accuracy of 70% in predicting increasing or decreasing returns. This highlights the model’s ability to support cryptocurrency investment decision-making within an interpretable machine learning framework.