New models of aggregate trend analysis are unfolding from our initial beta testing and we’ve garnered a bit of underground media interest.

We are attempting to analyze the effects of various variable constraints when applied to model overlays across market sectors. So far the results are ambiguous and disambiguation doesn’t seem possible just through additional testing. It looks like we’ll need a radical refinement of how we approach the modeling aspects in this area.

What we initially thought were statistical outliers look as if they may not be. So we are reexamining our techniques for determining statistical outliers since obviously until we get that right it doesn’t make any sense to start any type of root cause analysis.

We’ll have some interesting updates a bit later this month, so definitely stay tuned.

As you know we’re beta testing traffic channel specific implementations of RoboCrush and hope to be able to work on merging some of the aggregate trending data in order to create super-aggregrate trending model overlays, although the complexity of that project has grown terribly out of scope.

We’ve been looking quite a bit at the RC-Factor as well now that we are gathering more data on S-Trending and believe we have a better understanding of what the real value of the RC-Factor will be for businesses.

Admittedly we are still in some very theoretical stages at this point so massaging of the various data mining algortithms and their contingent real-world model implementation in order to create business value propositions is to be expected.

What can I say.

Hang tough!

Tad

As discussed previously, while model overlays are typically most useful for analyzing the growth pattern and potential strategies of specific businesses or within more localized market segments, aggregate trending models tend to be most useful for identifying potential model anomolies within related market sectors and predicting the likely future existence of breakthroughs that could lead to rapid acquisition of market share.

The downside is it is still nearly impossible to predict WHAT those breakthroughs will be other than by using relatively new analyis techniques.

And that’s still a big problem. In order to undertake proper development of models to analyze aggregate trending models, multiple output scenarios have to be posited and “assumed” to some degree, but other than comparing the model results to real world results it is for the most part very difficult to accelerate the detection of predictive differences off the posited models.

However, there can be sets of overlays that can be tied to specific instances of data organization and theoretically the data modeling can be optimized in such a way to maximize the number of potential overlays within certain overlay constraints. However, once again, the data and the overlays can’t be totally decoupled. That’s not hard to grasp from a “common sense” perspective, but as it turns out it’s quite difficult to prove conclusively.

Once again the time-factor is non-trivial in relation to the coupling/decoupling of data/overlay connections (also known as “n-realms”). Of course when dealing with any type of data collection that is derived from or has a bearing on specific markets and sub-markets naturally the element of time will be an important factor. But what’s surprising is the WAY in which time is a factor when manipulating data/overlay connections.

Just as we optimize our algorithms, we also on optimizing both our workflow and workspace design within the furniture “parameters” in place already. LOL…i.e., don’t expect any brand new furniture anytime soon - that means you, Doug!

If anyone has suggestions, please let us know.

I have a few things to say about that question.

1) Since, technically we’re not really in the marketplace yet, I guess we’re not in competition. LOL.

2) But seriously, there are companies that already have technology capable of doing components of what we’re doing and likely have taken notice of the new direction we are taking in the field of aggregate trending data  - which is actually a positive development as other companies have tried what we’re doing in the past but have not been taken seriously.

3) Competition also opens up the potential for strategic alliances - either with the competitors OR more likely with other companies with technology complimentary to the RoboCrush technology sets that we are developing.

We’ve been out of site, but not out of mind. We’ve had our nose to the grindstone and our feet to the pavement. Yes, we’ve partly been scrambling, but we’ve mostly been thinking and planning - thinktanking as it were about the future direction of our beta testing phases.

The ultimate direction of Robocrush has not changed, but sometimes the path to a final destination must take into account the unpredictable changes to the landscape required to get there. Anyone who’s ever downloaded driving directions from an online mapping service only to be faced with unanticipated constructions knows exactly what I mean.

We will reach our destination. And we will travel whatever new path we must in order to get there.

Tad

Apologies for not keeping the blog updated but we are in a bit of triage mode right now and also are trying to be fair to those of you who put so much effort in so far.

Needless to say, we didn’t see this coming.

We’ll be posting more updates after the first of the year and possibly a few in between.

In the meantime, enjoy your holidays!

Of course there are many variables involved and because of the nature of modeling aggregate trends the inherent complexities make untangling nondependent variables that are ‘wrongly coupled’ quite difficult: for example, dense clusters of “variable neighborhoods” may lead to potentially misleading identification of opportunities.

Perfecting these modeling techniques is likely to be a long uphill battle for RoboCrush, but a very important one.

Tad & PJ