"Hi Tom, we don't support auto-smoothing of the data prior to analysis (only smoothing of data / results after analysis) which would be an interesting addition. I guess you could feed it first-order differences, second-order differences, or…"
"Interestingly, Von Neumann came up with a simple method to generate a fair coin toss from a biased coin.
Flip the coin twice. If it comes up heads followed by tails, then call the outcome head. If it comes up tails followed by heads, then call the…"
"Hiya, sorry for the delay, was away on vacation! To tell you the truth, the economy is quite bad here in the US at the moment (unlike India which apparently is still booming). I asked around a little bit, but didn't come up with much in terms…"
"Hi Alexey, thanks much for the encouragement! I think the answer would be: business users who are sophisticated enough to use pivot charts in Excel, but who so far have been unable to cross the bridge to data mining, because of…"
You gotta love this internet thing! :) I had every intention of following up with you a few days after I wrote my post but I have been swamped at work and the blog has suffered a bit. Obviously when I wrote it I realized the…"
I mostly share your vision on the target audience for your project. The only thing that I would have added to your product is a well-thought consultancy and support services. As for me this is crucial because OR/data mining projects are much more than tools (even a good one) applied to data. Your application may allow combining domain insight of business user, consultancy of data mining professional and ability to collaborate in a single workspace. In this case your end-user would benefit from on-demand access to professional consultancy & support services with flexible pricing options. And for you it will become additional source of revenue. I would recommend you to look at any generic description of data mining project workflow. This will help you to develop not just a set of tools but a platform for running efficient data mining projects. I hope I’ve explained my idea clearly. If you have any questions or want to discuss any details, feel free to contact me, I would be glad to help.
You gotta love this internet thing! :) I had every intention of following up with you a few days after I wrote my post but I have been swamped at work and the blog has suffered a bit. Obviously when I wrote it I realized the possibility of it being discovered by you.
Thanks so much for answering my questions they were all very interesting! I can understand the temptation to keep adding more!
I was particularly interested in how you came up with visualizations and your answer tells it all ... "inspiration" (with a healthy dose of experience I'm sure).
I was just thinking about why I'm so into this visualization thing (other than the fact that it's extremely helpful) and I realized it has a lot to do with my experience with web analytics tools. The 2 I'm most familiar with have terrible visualizations (3d bar graphs for ex.) and piss-poor (excuse my vernacular) usability. I have little love for them, yet I understand that their 'beauty' lies underneath it all.
I apologize you were not able to log-in to the blog to leave your comment. I will have to look into that later. Would you mind if I re-posted your note (verbatim) on my blog?