We examine factors that predict financial crises and the evolution of financial crises using non-traditional methodologies, such as machine learning and system dynamics. Firstly, in our random forest model, the top six most important predictors among 12 indicators for the entire period (1870-2017) are the slope of the yield curve, the CPI, consumption, the debt service ratio, equity return, and public debt. Secondly, even though the manifestations of financial crises differ in each case, five common characteristics have been identified by examining various past financial crisis cases using a system dynamics approach (causal loop diagram). The first characteristic is a feedback loop that reinforces credit expansion. Next, the feedback loop leads to the buildup of financial crisis risk. Third, there is the shock that triggers the financial crisis. Fourth, there are risk-spreading factors. Lastly, individual financial crises do not end in themselves but have the common characteristic of becoming the seeds of new crises. In conclusion, two key findings emerge. First, the financial crisis is a systemic problem rather than an individual risk factor. Second, in diagnosing the recent situation, the results point to the risk of the financial crisis spreading.