GLAD: Global–Local Approach; Disentanglement Learning for Financial Market Prediction

Table 2

Results of univariate price prediction on four datasets.

Stock	End-to-end learning			Representation learning
	Metric	Transformer [3]	Informer [5]	CoST [25]	GLAD_b	GLAD_c	GLAD_a	GLAD
S&P 500 index	MSE	0.0037	0.0029	0.0038	0.0035	(0.0026)	0.0027	0.0025
	MAE	0.0131	0.0125	0.0129	0.0128	(0.0117)	0.0121	0.0111
Nikkei 225	MSE	0.0002	0.00015	0.0004	0.00018	(0.00009)	0.00012	0.00006
	MAE	0.0017	0.0013	0.0019	0.0015	0.0006	(0.0012)	0.0006
Hang Seng HSI	MSE	0.0005	0.00045	0.00091	0.00049	(0.00028)	0.00039	0.00023
	MAE	0.0025	0.0022	0.003	0.0023	0.0011	(0.0016)	0.0011
CSI	MSE	0.0004	0.00029	0.0009	0.00035	(0.00019)	0.00026	0.00015
	MAE	0.0025	0.0021	0.0029	0.0022	(0.0015)	0.0018	0.0012

The best results are highlighted in boldface, while the second-best results are enclosed within brackets.