Altınbaş, Hazarvd.2023-03-082023-03-0820221029-8479https://doi.org/10.1007/s40797-021-00147-2This paper uses learning methods and optimization techniques to investigate the determinants of shock propagation in the Euro area for the period 2001–2015. First, principal component analyses are used with country bond yields to identify sub periods and country groups; second, infuencing factors for country bond yields are investigated with random forest models; lastly, shock propagation among groups are examined with impulse response functions. Models in steps two and three are improved by using simulated annealing algorithm. The empirical fndings achieved can be particularly relevant for both investors and policymakers. Shedding light on the determinants of fnancial contagion may be in fact useful for investors who can derive relevant information about countries which are less sensitive to be afected by shocks, orienting thus their investment strategies. At the same time, policymakers could draw worthwhile and preventive hedging strategies and design the most suit able crisis management policies.enContagionEuro areaSovereign debtTime-series analysisMachine learningOptimizationArticle10.1007/s40797-021-00147-22-s2.0-85102270564Q2WOS:000626479100001N/A