In this article, multi‐scale LPPLS confidence indicator approach is used to detect both positive and negative bubbles at short‐, medium‐, and long‐term horizons for the stock markets of the G7 and the BRICS countries. This enables detecting major crashes and rallies in the 12 stock markets over the period of the 1st week of January, 1973 to the 2nd week of September, 2020. Similar timing of strong (positive and negative) LPPLS indicator values across both G7 and BRICS countries was also observed, suggesting interconnectedness of the extreme movements in these stock markets. Next, these indicators were utilized to forecast gold returns and its volatility, using a method involving block means of residuals obtained from the popular LASSO routine, given that the number of covariates ranged between 42 and 72, and gold returns demonstrated a heavy upper tail. The finding was, these bubbles indicators, particularly when both positive and negative bubbles are considered simultaneously, can accurately forecast gold returns at short‐ to medium‐term, and also time‐varying estimates of gold returns volatility to a lesser extent. The results of this paper have important implications for the portfolio decisions of investors who seek a safe haven during boom‐bust cycles of major global stock markets.