A New Kernel of Support Vector Regression for Forecasting High-Frequency Stock Returns

Table 1

Out-of-sample forecast performance comparison results from February 2, 2012, to March 3, 2014 ().

Criterion	New kernel versus (minus) radial basis kernel			New kernel versus (minus) sigmoid kernel
	MSE	Hit rate	110-min gain	MSE	Hit rate	110 min gain

Note: indicates significance at the 1% level.