search

musiclicn / deep_finance

apply deep learning/ neural network to analysis stock price
5 stars 2 forks source link

Chan Gravity 0 #30

Open musiclicn opened 7 years ago

musiclicn commented 7 years ago

Gravity 0

Basic concepts: gravity = (high + low)/2 log change = log( price t/ price t-1)

Features: log change of gravity if is bar3 of fenxin, shape of fenxin- sum of previous three gravity log change days of current trend accumulated strength of current trend- sum log change of gravity belong to this trend previous opposite trend strength, days previous same trend strength, days Target: gravity direction (Up or Down)

musiclicn commented 7 years ago

Gravity 1

Basic concepts: gravity = (high + low)/2 log change = log(Price t/ Price t-1)

Features: position (distance to current day) log change of gravity log(high/previous gravity) log(low/previous gravity) log change of volume if is bar3 of fenxin, shape of fenxin- sum of previous three gravity log change days of current trend accumulated strength of current trend- sum log change of gravity belong to this trend previous opposite trend strength, days previous same trend strength, days

Target:

Thinking how to model shape of Fenxin? combine Volume and Price together Analyze Fenxin shape and true reverse relationship (true reverse- one Bi )