A hybrid model for stock price prediction based on multi-view heterogeneous data

Financial Innovation

Table 13 The predicting accuracy of MVL-SVM models in different sliding windows

Sliding windows	Model	Statistics	\(T_1\) = 1	\(T_1\) = 2	\(T_1\) = 3	\(T_1\) = 4	\(T_1\) = 5
\(T_1\) = 1	MVL-SVMMD	Average	0.8741	0.8108	0.7884	0.7497	0.7459
		Median	0.8767	0.8082	0.7945	0.7534	0.7397
	MVL-SVMDR	Average	0.8789	0.8336	0.7905	0.7499	0.7423
		Median	0.8904	0.8356	0.7945	0.7534	0.7397
\(T_1\) = 2	MVL-SVMMD	Average	0.8842	0.8121	0.7808	0.7533	0.7366
		Median	0.8904	0.8082	0.7808	0.7534	0.7260
	MVL-SVMDR	Average	0.8797	0.8197	0.7860	0.7673	0.7391
		Median	0.8904	0.8056	0.7808	0.7671	0.7397
\(T_1\) = 3	MVL-SVMMD	Average	0.8777	0.8272	0.7741	0.7588	0.7438
		Median	0.8904	0.8219	0.7671	0.7534	0.7397
	MVL-SVMDR	Average	0.8815	0.8018	0.7845	0.7517	0.7426
		Median	0.8904	0.8219	0.7808	0.7534	0.7534
\(T_1\) = 4	MVL-SVMMD	Average	0.8758	0.8346	0.7703	0.7506	0.7357
		Median	0.8767	0.8356	0.7671	0.7534	0.7397
	MVL-SVMDR	Average	0.8722	0.8231	0.7831	0.7621	0.7497
		Median	0.8767	0.8356	0.7808	0.7671	0.7397
\(T_1\) = 5	MVL-SVMMD	Average	0.8767	0.8117	0.7728	0.7485	0.7355
		Median	0.8767	0.8082	0.7671	0.7534	0.7260
	MVL-SVMDR	Average	0.8777	0.8134	0.7804	0.7520	0.7449
		Median	0.8904	0.8219	0.7808	0.7534	0.7397