There have been many beautiful aspects to the moves of the market during the last two weeks. Looking at the S&P futures:

  08/06/2007   15/06/2007  
    Close Cl - Cl(t-1) Close Cl - Cl(t-1)
Mon 1555.4    1 1525.2     3
Tue 1548.7  -7 1507.5  -18
Wed 1531.2 -17 1530.2   23
Thu 1503.7 -28 1539.5     9
Fri 1522.5  19 1547.7     8


I notice that on Friday June 15th the futures ended at approximately where they were on Friday June 1st, or Tuesday June 5th. Also, there were three big down days in a row during the week ending June 8th, and three big up days in the week  ending June 15th. Many other regularities appeared in the last two weeks, and generalizing them to all weeks of the year could be a meal for a lifetime, or at  least for a day.

To help me in this pursuit, I have been reading the chapter on code construction in the book Strange Curves, Counting Rabbits, and other Mathematical Explorations by Keith Ball. In particular, I am very interested in the idea that the ideal curve should have various codewords that are as different as possible, so that it is unlikely that their content will be mixed up.

This is very closely related to the astonishing results in Kendall's Rank Correlations work — that the number of interchanges necessary to bring one set of ranks into another is the same as the number of inversions in their perspective rankings.

I believe that there are many helpful ways of extending these two ideas and perhaps some of them will give some insight into what is going to happen in the future, including next week.





Speak your mind


Resources & Links