Applications of Eureqa

Posted: April 16, 2010 in Forecasting, Grains, Prediction
Tags: , , ,

On our last post, there was a brief introduction to Eureqa.  In this post, I am to show you sample output from its findings for our trusty wheat data:

First outright = price level

Second outright = price level + 13.75

third outright = price level +25.75

fourth outright = price level*0.96+59.78

It took 5 minutes to find these relations in the package and here are the sample mis-pricings:

This is in no way a complete picture; it was only my aim to show you the type of pictures that the user may paint with this tool.  In the next Eureqa post, we will show how to use the software to create these numbers and make a more complete wheat market model.

Advertisements
Comments
  1. jim says:

    hey,

    interesting software. What do you mean when you say first outright? Then 2nd outright +13.75? And these are mispricings from what?

    • autospreader says:

      Hello,

      By first outright, I mean the closest contract to delivery or expiration. In the example I provided, it was a simple linear function so the results will be pricing relative to the average.

  2. jim says:

    oh I see. is it difficult to do this in this software? How would you do this with any two time series? Is it possible to do with multiple time series and baskets?

    • autospreader says:

      It is not difficult at all! You can load multiple time-series via multiple file formats (xls,csv,etc.) and actually the data used in this simple analysis is multiple time series of net changes homogenized to 1 day intervals. It is possible to do this with multiple time series and baskets as well. Are the weights constant or varying between instruments? The weightings might be difficult but I can play around with it and see right now.

  3. jim says:

    Well Im just gonna try and start with two variables. X and Y. I can input the data in the x and y columns. But what is the w confidence column for?

    I am wondering what this software is for exactly. If you input two time series that were totally unrelated, what would it output? There are these formulae with sin and whatnot on the side. What are those things? The output you got would means that on average the second outright trades at a 13.75 premium?

    Is there no way to make this software find what would be an optimum coefficient for one of the variables?

  4. autospreader says:

    The columns are going to vary based upon your chosen inputs.

    The software was designed to be utilized as a tool to discover hidden relationships (laws) within datasets. Those formulas are the potential models that it will try to fit to the datasets that you have loaded into it.

    You are correct on the premium over the period that the data was computed.

    Yes there is; I believe you are then looking to perform a linear regression?

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s