This　research　focused　on　the　effect　of　particle　size　and　flotation　time　on　magnesite　flotation,　and　the　flotation　performance　of　various　size　fractions　were　predicted　by　a　machine　learning　(ML)　method.　Four　kinetic　models　were　used　to　fit　the　recovery　of　MgO　and　SiO2　in　various　size　fractions　of　magnesite　flotation.　The　results　demonstrated　that　the　flotation　of　magnesite　exhibits　good　agreement　with　the　classical　first-order　kinetic　model.　Besides,　the　effect　of　various　particle　sizes　on　MgO　recovery　and　selectivity　index　was　predicted　by　ML　method.　It　was　shown　that　the　proposed　ML　model　could　accurately　reproduce　the　effects　of　particle　size　and　flotation　time　on　magnesite　flotation　performance.　Furthermore,　the　developed　model　revealed　that　the　optimal　mean　size　range　for　magnesite　flotation　is　30　to　48　μm.　Therefore,　this　paper　is　of　great　significance　to　the　application　of　ML　methods　in　the　prediction　of　various　magnesite　size　flotation　performance.　©　2020　Elsevier　B.V.