Infants　with　gestational　weight　above　the　90th　percentile　of　same　gestational　age　are　termed　as　Large　for　gestational　age　(LGA).　LGA　suffers　from　serious　complications　during　and　after　the　antepartum　period　because　they　don’t　get　earlier　identification　of　the　disease.　Earlier　recognition　of　LGA　infant　could　slow　progression　and　prevent　further　complication　of　the　disease.　In　Medical　science　prevention　and　mitigation　of　disease　requires　examination　of　certain　biochemical　indicators　(BI).　Machine　Learning　(ML)　has　been　evolved　and　envisioned　as　a　tool　to　predict　LGA　infants　with　most　deterministic　characteristics.　This　study　aims　to　identify　most　deterministic　BI　for　LGA　prediction　with　minimal　computational　overhead.　To　the　best　of　my　knowledge,　this　is　the　first　time　a　study　is　carried　out　to　identify　most　deterministic　BI　associated　with　LGA　and　to　develop　LGA　prediction　model　using　advanced　ML　techniques　in　the　Chinese　population.　To　develop　an　effective　LGA　prediction　model,　we　used　Information　Gain　(IG)　an　entropy-based　feature　selection　method　to　filter　out　most　deterministic　BI　for　early　identification　of　the　disease.　Finally,　to　verify　the　idea　of　applying　IG,　four　widely　used　ML　classifiers　were　used　considering　Precision　and　AUC　as　a　performance　metrics.　The　drastic　improvement　in　precision　from　33　to　71%　validates　our　idea　of　applying　IG　to　mine　the　most　deterministic　BI　for　early　prediction　of　LGA.　©　2019,　Springer　Nature　Singapore　Pte　Ltd.