Monthly Archives: July 2008

Rapidminer Video Tutorial Sneak Peak

My next Rapidminer Video Tutorial #4 on Evolutionary Weighting is done and needs to be cleaned up before I post it this weekend, so get ready for it. It’s one of the most intricate ones I’ve shared with my readers yet and will probably clock in over 20 minutes in length. We combine the lesson from the Genetic Feature Selection Tutorial and build a new experiment on top of it. It’s a “one click” evolutionary extravaganza!

I’m also planning on cleaning up my older videos and re-recording them using Camstasia. I’ll definitely be finishing my Introduction to Rapidminer Video Tutorial 1 & 2 over the coming weeks and plan on recording some new ones.  All my old “Test Videos” will be deleted!

My new posting frequency has definitely helped my frame of mind and allows me to put more time into these videos. As always, thanks for visiting. Now would be a great time to subscribe to my feed!

Rapidminer Video Tutorial – How Stock NeuroMaster Works

After playing around with Stock Neuromaster, I realized that it transforms the time series data into a zig zag line or moving average and then learns the relationship between it and the price & volume data. The zig zag line connects high and low points together based on a % retracement level you define or a time period you choose for a moving average. Once the data is transformed to reflect this, its fed into the neural net as your output variable and the time series data becomes your input variables.

In this video tutorial, viewers will be able to create a similar type of model for Apple and learn how to use a great time saving data preprocessing operator called LabelTrend2Classification, see how to create Attribute and Data files, and use the NeuralNet learner from Rapidminer 4.2

[flashvideo filename=”” /]

As a parting gift, you can download the data files and Rapidminer experiment here.

Rapidminer vs Stock Neuromaster

I believe I’ve figured out, in concept, how the Stock Neuromaster product generates BUY/SELL signals and should be able to replicate it quite easily in Rapidminer. I’ll have to fool with some stock data and use some of Rapidminer’s special data pre-processing operators first and see where it gets me.

I hope to produce a video about it right after I post my Evolutionary Weighting Tutorial this weekend (a continuation of my Genetic Feature Selection Tutorial).

Soul Searching, Part 2

Thanks to all who commented on my Soul Searching post from this past weekend, they were thoughtful, honest, and sincere. After spending the weekend thinking more about the future of Neural Market Trends, I’ve decided to keep it going but get back to my roots.

I want to concentrate on high quality but low frequency posts on how to use Rapidminer to model trends in the markets, and create new video tutorials. I also want to create some videos on how to use Rapidminer for other applications like Business Intelligence. Some of my more complicated and in depth tutorials will be monetized.

To create high quality posts, I expect my frequency of posting will drop to maybe one post per week and as a result I expect 50% of my readership to disappear. I hope my readers decide to stick around and aren’t too pissed by my new (yet old) “focus.”

Thanks for understanding.

Updated RapidMiner Video Tutorial – Genetic Feature Selection

My Genetic Feature Selection Tutorial, using RapidMiner, has failed for reasons unknown to me. I used Wink previously but began to realize that it has some problems so I re-recorded the tutorial using Camtasia Studio. Camtasia Studio, by far, is the best product I’ve come across and I went out and spent money on it.

Please let me know if there are any more problems with the video tutorial.