| Poll | ||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||
14%
9%
8%
7%
7%
6%
6%
4%
4%
4%
4%
4%
3%
3%
3%
3%
2%
2%
1%
1%
1%
1%
0%
0%
0%Comments
Editor, vendor participation
Although this poll uses several mechanisms against double voting, it should not be considered scientific, since people from some companies voted much more actively than others (some obvious duplicate vendor votes were removed). However, this poll does give a flavor of the diversity of existing tools.
Comparing with a similar 2002 data mining tools poll, we see some new entries that are popular, including free tools Prudsys Xelopes and R which took some votes from Weka. People also use Excel as part of the data mining process, and about 15% of the responders write their own code.
We can also note a growing popularity of Microsoft SQL Server for data mining.
Among other tools responders also mentioned Microsoft Visual Foxpro and SPSS Base/Regression.
Will Dwinnell, Number of votes
The "over 1000" figure you mention is the total number of votes, across all choices. Since a voter may select more than one choice, the figure of greater interest is the maximum any single choice has received, which is 160 (at present).
On the other hand, I have no doubt that there has been lobbying on the part of some vendors. This has also definitely happened in the past.
Muhammad Shahbaz, number of votes
I am just curious that why in this poll the votes crossed the 1000 barrier. In the previous polls, I can't remember if the number of votes reached half of this number. (Are there some people doing the marketing of their products? Or suddenly the traffic increased to this web site.)