Multiple time period correlations

Okay, we now have three time periods covered for every stock in our database – 200 days, 100 days and 30 days. It took a little while to get things optimized so that we could re-run the calculations every days. Remember – we have well over 8000 stocks in the database, so that is (8000*8000)/2 = 32 million correlations that need to be calculated for each time period.

What the heck is the deal with IBM? It seems odd that no other stock has a positive correlation over 200 days that is above .80. It seems that MSFT is also weird – nothing over .80 for 30, 100 or 200 days.

3 Responses to “Multiple time period correlations”

  1. How often are your 32 million correlations calculated? Pretty impressive. We keep correlations to sectors and broad market indicators for all stocks. http://www.trade-ideas.com/StockInfo/AAPL/APPLE_COMPUTER_INC.html#Technicals

    Let me know if there’s a complimentary or peer-based association that’s possible.

  2. Administrator on April 20th, 2006 at 8:59 pm

    Hey David!

    I run them every morning (when I remember – I need to create a cron job). It was taking forever when I was depending on SQL, so I just wrote it all in Java and do everything in memory. Nice and quick on a 64-bit AMD processor and 64-bit Linux!

    You guys at trade-ideas seem to be doing quite a good job – plus you work with real-time data, right?

    Let me know if you come up with any good ideas for complimenting each others’ sites – I am trying to find the path least tread.

Leave a Reply