Change　point　detection　is　an　important　area　of　scientific　research　and　has　applications　in　a　wide　range　of　fields.　In　this　paper,　we　propose　a　sequential　change　point　detection　(SCPD)　procedure　for　mean-shift　change　point　models.　Unlike　classical　feature　selection　based　approaches,　the　SCPD　method　detects　change　points　in　the　order　of　the　conditional　change　sizes　and　makes　full　use　of　the　identified　change　points　information.　The　extended　Bayesian　information　criterion　(EBIC)　is　employed　as　the　stopping　rule　in　the　SCPD　procedure.　We　investigate　the　theoretical　property　of　the　procedure　and　compare　its　performance　with　other　methods　existing　in　the　literature.　It　is　established　that　the　SCPD　procedure　has　the　property　of　detection　consistency.　Simulation　studies　and　real　data　analyses　demonstrate　that　the　SCPD　procedure　has　the　edge　over　the　other　methods　in　terms　of　detection　accuracy　and　robustness.　©　The　Author(s),　under　exclusive　licence　to　Springer-Verlag　GmbH　Germany,　part　of　Springer　Nature　2024.