An Empirical Study of Machine Learning Algorithms for Stock Daily Trading Strategy

Table 1

Main parameter settings of traditional ML algorithms.

	Input Features	Label	Main parameters
LR	Matrix(250,44)	Matrix(250,1)	A specification for the model link function is logit.
SVM	Matrix(250,44)	Matrix(250,1)	The kernel function used is Radial Basis kernel; Cost of constraints violation is 1.
CART	Matrix(250,44)	Matrix(250,1)	The maximum depth of any node of the final tree is 20; The splitting index can be Gini coefficient.
RF	Matrix(250,44)	Matrix(250,1)	The Number of trees is 500; Number of variables randomly sampled as candidates at each split is 7.
BN	Matrix(250,44)	Matrix(250,1)	the prior probabilities of class membership is the class proportions for the training set.
XGB	Matrix(250,44)	Matrix(250,1)	The maximum depth of a tree is 10; the max number of iterations is 15; the learning rate is 0.3.