After the Great Recession, there has been speculation as to whether it is possible to effectively detect systemic risk in the financial sector in order to guide macroprudential policy. This paper explores how aggregate indicators may be significant in forecasting banking crises among and across advanced economies. The paper begins by reviewing financial crisis theory and noteworthy qualitative frameworks and quantitative models for predicting financial crises. Mindful of the literature and models, machine learning techniques are used to assess the significance of 26 indicators in forecasting crises, two years in advance, for 20 high income countries. The classification models per country indicate that domestic credit to the private sector, as a percent of GDP, is the most common significant indicator in forecasting banking crises. When creating classification models inclusive of all countries, which are assumed to be of comparable financial depth, the bank lending-deposit spread becomes the most significant indicator. While the specificity of the models per country were quite high, the specificity dropped dramatically for models across countries. Overall, the results indicate a significant relationship between indicators of financial depth and banking crises, however, more data is needed to build upon these models to ensure their robustness.