Due to recent updates, all users are required to create an Altair One account to login to the RapidMiner community. Click the Register button to create your account using the same email that you have previously used to login to the RapidMiner community. This will ensure that any previously created content will be synced to your Altair One account. Once you login, you will be asked to provide a username that identifies you to other Community users. Email us at Community with questions.

stock trend prediction

fpaganelfpaganel Member Posts: 4 Contributor I
edited November 2018 in Help

Hi everyone,

I'm trying to develop a model that optimize buy/sell signals at the end of day, in order to obtain the best gain.

Inputs are techical indicators like RSI, MACD, Stochastic and candle patterns.

At the moment I have a training set of Apple's stock in excel (that I will share when I find out the way).

In the past I have tried to build a model considering following label:

  • 1 if the price variation is >0.2
  •  0 if the price variation is between -0.2 and 0.2
  • -1  if the price variation is <0.2

But the result accurancy is around 50% .

How can improve it?

Could you please help me? 

 

Thanks in advance

Francesco

Tagged:

Answers

  • Thomas_OttThomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn

    I would optimize your algorithm using the Grid Operator. You can get good success when you do that. 

     

    Also, visit my site on using RapidMiner for Stock Market related things. http://www.neuralmarkettrends.com/tutorials

Sign In or Register to comment.