The　scale　of　the　digital　economy　is　an　important　quantitative　index　to　measure　the　development　level　of　a　country＇s　digital　economy.　Through　reasonable　and　scientific　prediction　of　the　scale　of　China＇s　digital　economy,　it　can　not　only　further　understand　the　development　situation　of　the　digital　economy　objectively　and　fairly,　but　also　provide　a　reference　for　the　government　to　conduct　macro-control　of　the　digital　economy　based　on　the　existing　data.　Based　on　the　ARIMA　model　and　BP　neural　network,　this　paper　constructs　a　variety　of　prediction　models　for　the　size　of　China＇s　digital　economy　and　makes　an　empirical　analysis　of　the　effectiveness　of　the　models　through　the　size　data　of　China＇s　digital　economy　from　1993　to　2020.　The　results　show　that　the　combination　model　constructed　by　using　the　error　correction　strategy　has　the　better　fitting　and　prediction　effect,　the　performance　of　MAPE,　MAE,　R2,　and　other　evaluation　indicators　is　better　than　that　of　the　single　model,　and　the　combined　model　based　on　the　weight　allocation　method.　©　2023　Technical　Committee　on　Control　Theory,　Chinese　Association　of　Automation.