Neural Market Trends

Using SVM Kernels for Time Series Analysis

Tom — Tue, 24 Jan 2012 08:07:50 PST

I wanted to share two research papers that are invaluable to anyone trying to use Support Vector Machines (SVM) for modeling the stock market. One written by an author well known to the Rapid-I team, and another by Korean researcher. I’ve used both of these papers as blueprints for some of my past stock market analysis processes.

The first one is by Kyoung-jae Kim and titled “Financial time series forecasting using support vector machines.

The second is by Stefan Ruping (forgive the missing umlaut) and titled “SVM Kernels for Time Series Analysis.”

Rapidminer Sample Process: Multiply Data

Tom — Mon, 23 Jan 2012 07:17:16 PST

I often use the Multiply operator to make copies of my data set and feed it into different learners. I do this because sometimes I don’t know if a Neural Net operator, or a SVM operator, give me better performance. Once I know which operator performs my task better, I then use the parameter optimization process to see if I can squeeze more accuracy out it.

The sample process below uses the Iris data set, just switch it out with your data set and enjoy.

Multiply Sample Process.txt

Rapidminer Sample Process: Financial Text Mining

Tom — Thu, 19 Jan 2012 05:23:15 PST

This is the sample Rapidminer process I used in Video #14. Just download the text file and import into into RM using the import process function. Please note, you will need to create the Excel spreadsheet yourself, as I show you in the video. Just save the Excel to a 2003 format and you’re done.

Enjoy!

Financial Textmining.txt

Rapidminer Sample Process: Parameter Optimization

Tom — Wed, 18 Jan 2012 08:05:22 PST

Below is a simple parameter optimization process in Rapidminer using the Iris data set. Download the TXT file and import it into Rapidminer. Of course, you may use whatever data set you want and switch out the learner. Make sure to update the parameter optimization operator parameters. :)

RM-Parameter Optimization.txt

Terrible

Tom — Wed, 18 Jan 2012 07:37:29 PST

Expression Engine = Terrible

Textpattern = Terrible

Never again will I be switching from WordPress.

Violin Plots of Volatility

Tom — Wed, 30 Mar 2011 03:33:40 PDT

I came across a fantastic R script from blogger Milk Trader. Â It’s about generating something called violin plots of volatility for the S&P500 index and the VIX, which he got from this CBOE paper. Â I took that script a bit further and added in one of my current trend positions, $ARLP, just for fun.

The plot is essentially a “combination of a box plot and a kernel density plot” and shows us the absolute value of volatility (negative returns are represented as positive) on the y axis.

A very simple R code (you can get it on his site) with a great visual impact. Â Great job Milk Trader!

Don’t miss my posts about Rapidminer and R! Sign up for my feed now!Â It’s easy to do and I’d be eternally grateful!

Name That Technical Pattern!

Tom — Thu, 24 Mar 2011 17:37:35 PDT

Three different stocks, three different (possible) technical patterns. Â Can my readers tell me where and what these technical patterns are?

Stock #1

Stock #2

Stock #3

Which Sector Would You Buy?

Tom — Wed, 23 Mar 2011 13:16:22 PDT

Which of these sectors would you buy right now?

The answer depends on whether you’re a trader or investor, and of course your holding time.

Monthly Returns for XLE in R

Tom — Tue, 22 Mar 2011 18:38:59 PDT

I’m still poking around in R, and leveraging the Quantmod package for fun. Â Below I generated a simple bar chart of 6 months of monthly returns for XLE, the oil services ETF.

Not to shabby, eh? Â Now if only I can figure out how to correctly scale the y-axis and add in a few more ETF’s into the same chart,withÂ differentÂ colors, then I’ll be happy. Any reader know how to do this?

Update: Thanks to readers Shane, Â Sergi, and Cidiel, I was able to generate this new plot of XLE and XLF together for the past three months of returns. Thanks guys.

Let’s Go Jayhawks!

Tom — Fri, 18 Mar 2011 16:49:46 PDT