Friday, March 3, 2023

Heller and Shannon: Pay-dirt

Shannon found three animations in the first twelve that she was not able to find a ready explanation for. In addition to the professionally oriented modes, there was a golf league, two groups of people who followed the two local universities and so on.

Shannon was fully aware of the caution in the Tutorial that while it was mathematically possible for the software to extract thirty characteristic shapes from thirty “seeds”, the fact was that the “crispest” shapes or modes were the first ones to be extracted and each subsequent shape had a lower signal-to-noise ratio because the noise accumulated in the remainder left from each extraction.

One of the three animations included Ce’Diff but none of the animations had Shequlia Washinton.

Shannon put four animations up on the 54” TV. At Heller’s urging, she used the three unknowns and the gambling mode. Shannon and Heller watched them for a while.

After watching for a couple of minutes, Shannon shared with Heller that they were looking for multiply connected “dots” and ones that had long chains hanging off of them.

After a bit, Heller asked “What about that one?” while tapping one of the dots on the animation of the gambling group.

Shannon clicked on the dot which caused it to brighten. A window popped up and identified the dot. Shannon read, “That is Reverend Mike Kingston”. Opening up another screen, Shannon did a search on him. “He is an Associate Pastor at the local Mega-Church.”

Heller cocked an eyebrow in a silent question.

“I don’t think he is who we are looking for. He might be counseling gambling addicts. But even if he isn’t, I am not sure he would be generating huge amounts of money” Shannon said.

They watched a few minutes more. Then Heller tapped another dot.

Shannon clicked on it and the dot brightened on the animation she tapped but it also brightened on two of the other animations. “Tom Yankel” she said. She didn’t need to look him up. “He the guy who owns all of the car dealerships.”

That was promising.

They hit pay-dirt on the fifth dot Heller pointed at.

Shannon clicked on it and it lit up in all four animations. The dot was a circle, so it was not one of the “seeds”. All four dots had the same “boss-man” connections and long chains.

“Lon Turner, CFO of Heroton Capital” Shannon said. 

“What is a CFO?” Heller asked.

“A CFO is a Chief Financial Officer. He is like the top bean-counter in the company. He controls every penny in-and-out of it” Shannon said.

Shannon assigned a vivid purple to Turner’s name and Heller watched it pulse for another minute. 

Heller cocked his head. “I've heard of Heroton but can't exactly place where."

Watching the animation a bit longer "I gotta feeling that is our guy” Heller said, tapping the dot. “Now we gotta learn everything about him without leaving tracks."


  1. I apologize, I must have missed an episode or three, or I've simply just lost the thread, but what's the objective here?


    1. Hello Albert:

      Thanks for asking.

      At this point, they want the Woke industry to feel the same pain Shannon had to endure. Or perhaps a bit more because Heller and Shannon know it is about way more than just them.

      They want to throw some sand into the gear-box.

  2. ERJ, this is a rather interesting (and terrifying) insight into how data software is used. I am both grateful and bothered.

  3. One of the things that this shows is how naive folks are that use social media. These links they are finding are voluntarily offered. I scrubbed my anemic pluggedin acct several years ago.

    I've been able to identify locations just based on pictures of unique things, like in youtube videos or blogs. There is so much information voluntarily given out, that almost no one is anonymous. Not even me. I've given plenty of info, too. The paradigm of trust is the old way.

    1. Reminds me of when Shia LaBeouf raised a 'he will not divide us' flag in an undisclosed location in response to Trump's inauguration... 37 hours later (using star tracking and flight patterns of commercial aircraft), the flag was captured, and a 'Make America Great Hat' was in it's place.

      He later raised it in Liverpool, England, on top of a 'secure' building. It was also shortly found and removed.

      It's amazing what dedicated people can find...

  4. I had to go back thru February’s postings to get the sense of it all, but it is developing nicely.

  5. I've gone through decision analysis before, where an array of seemingly unrelated variables or conditions are introduced to help make an informed, defensible decision for big-money projects. I've used many of the visualization techniques that approach the problem obliquely in a way that is intended to tease out the answer that is not immediately apparent: Tornado plots, bubble diagrams, etc. I'm not familiar with these techniques of data manipulation, though. Are you making them up, or is this based on an actual process? Just curious. It's a great plot development, my compliments.

    1. For some reason, this comment utility is posting all of my comments as 'Anonymous', even though I'm selecting my identity first. What's up with that? It used to be automatic. - Aggie

    2. The plotting part or the analysis part?

      Regarding the analysis:

      "Principal component analysis of a data matrix extracts the dominant patterns in the matrix in terms of a complementary set of score and loading plots. It is the responsibility of the data analyst to formulate the scientific issue at hand in terms of PC projections, PLS regressions, etc. Ask yourself, or the investigator, why the data matrix was collected, and for what purpose the experiments and measurements were made. Specify before the analysis what kinds of patterns you would expect and what you would find exciting.

      The results of the analysis depend on the scaling of the matrix, which therefore must be specified. Variance scaling, where each variable is scaled to unit variance, can be recommended for general use, provided that almost constant variables are left unscaled. Combining different types of variables warrants blockscaling.

      In the initial analysis, look for outliers and strong groupings in the plots, indicating that the data matrix perhaps should be “polished” or whether disjoint modeling is the proper course.

      For plotting purposes, two or three principal components are usually sufficient, but for modeling purposes the number of significant components should be properly determined, e.g. by cross-validation."

  6. The hunters are getting closer to a useful target. Good that they are planning to do further research "without leaving tracks". That will be critical after they make their move on the final target.

    They might want to consider setting up diversions, distractions, and false leads, just in case somebody does try to track them after the sting. Of course, they are being careful not to leave traces behind them...

    I have never seen any project that went quite as planned.

    Cannot wait for more episodes. Thanks for all the fun!

  7. And away we go….

  8. Anyone can make 500$ a day…Yes! You can make more money (c22:. than you think by working from home online. I have been doing this job for a few weeks and my salary last week was exactly $25,370.
    Click This Site OPEN HERE… DollarsInside


Readers who are willing to comment make this a better blog. Civil dialog is a valuable thing.