Ranked　keyword　search　over　encrypted　data　has　been　extensively　studied　in　cloud　computing　as　it　enables　data　users　to　find　the　most　relevant　results　quickly.　However,　existing　ranked　multi-keyword　search　solutions　cannot　achieve　efficient　ciphertext　search　and　dynamic　updates　with　forward　security　simultaneously.　To　solve　the　above　problems,　we　first　present　a　basic　Machine　Learning-based　Ranked　Keyword　Search　(ML-RKS)　scheme　in　the　static　setting　by　using　the　k-means　clustering　algorithm　and　a　balanced　binary　tree.　ML-RKS　reduces　the　search　complexity　without　sacrificing　the　search　accuracy,　but　is　still　vulnerable　to　forward　security　threats　when　applied　in　the　dynamic　setting.　Then,　we　propose　an　Enhanced　ML-RKS　(called　ML-RKS　+)　scheme　by　introducing　a　permutation　matrix.　ML-RKS+　prevents　cloud　servers　from　making　search　queries　over　newly　added　files　via　previous　tokens,　thereby　achieving　forward　security.　The　security　analysis　proves　that　our　schemes　protect　the　privacy　of　indexes,　query　tokens　and　keywords.　Empirical　experiments　using　the　real-world　dataset　demonstrate　that　our　schemes　are　efficient　and　feasible　in　practical　applications.　©　2008-2012　IEEE.