Description:
Bitcoin market crashes bring huge economic loss and weaken the global financial system. Thus, predicting Bitcoin market crashes is very important for investors. However, due to the high volatility of Bitcoin prices, accurate prediction of crash events is difficult. In this study, we propose three fusing approaches to Bitcoin market crash prediction for better investment decision-making. First, we offer a new hybrid prediction approach that combines various machine learning models with the Generalized Supremum Augmented Dickey-Fuller (GSADF) test. Analysis using machine learning models trained on information from four long-term bubble cycles from January 2016 to June 2021 captured via the GSADF test revealed significantly improved predictive performance. Second, we employed the Synthetic Minority Oversampling Technique (SMOTE) to address the loss of predictive power due to the severe imbalance between crash and no-crash periods in real-world data. Each machine learning model was trained using a different oversampling strategy to determine the best predictive performance. Finally, SHapley Additive exPlanations (SHAP) interpretation of outcomes from the predictive model provide practical information for the establishment of efficient investment strategies. In our model, factors such as increased interest rates and the continuation of the bubble greatly increased the probability of future crashes in the Bitcoin market