It’s polite to let the regular readership know when posting frequency and content is changing. It was done 158 posts ago, on December 31, 2011. I’m doing so again. Thank you for reading, commenting, sharing, conversing and generating data. I’ve been testing a few hypotheses. The data set won’t be complete for another few months until the search returns are complete. There was no optimization objective and it showed. As a result: The posting frequency (and predictability) will decrease. There will be fewer words to read. There will be more novel ideas curated from other sources. Pandering and Trolling Trolling is the act of forecasting what will likely cause drama or controversy, creating such content, and distributing only for the[…]
Month: July 2012
This series originally appeared in Eyes on Analytics on April 16, 2012 The City of Edmonton posted a pretty interesting position last month. The description is so good that it bears repeating in this space. Bolding is my emphasis. Traffic Safety Predictive Analyst Put your superior analytical skills to work in North America’s first and only municipal Office of Traffic Safety. You will be joining the rapidly growing field of urban traffic safety where the application of statistics and predictive analysis is becoming a vital decision support tool in reducing motor vehicle collisions. Your responsibilities will be: Provide short, medium, and long-term predictions of collisions and/or speeding by considering current and historical traffic safety related data as well as other[…]
Tor.com wrote a decent summary about the Norvig-Chomsky debate. I don’t think we have a common understanding of the science, just in general. Proponents of an extreme Norvig perspective say that Chomsky’s ever complicated theories and models are proof that the traditional scientific method has failed, and that machine learning is the future. Those proponents may be misguided by how science works with models. A model is representation. It’s like looking at the shadow produced by an umbrella. It’s a deliberate abstraction so that you can understand some aspect of it. And you can learn a lot about the shadow. Why not just look at the umbrella? An umbrella is extremely complex, and really difficult to analyze if you have[…]
The best map of the American Census, in my judgement, is from the New York Times. You can find it here. The best map of the Canadian Census is from OpenFile.ca. You can find it here. Many analytics practitioners have their roots in catalogs. And in the cataloging business, geography is a huge predictor. You look for exploitable geographical cleavages in electoral behavior and public opinion studies. Geo-targeting is one of the few things that many social platforms do really well. Consider the cleavage in the chart below. The darker the red, the older the population. Canada is a country without people. Lots of land. Not a lot of people. You see these very red areas in rural zones. You[…]
Predictive analytics is about making statements about the future, and then enabling either an individual or a group of people to make decisions. The idea is that better decisions will be made if people have a better idea of what to expect in the future. I’m not quite as optimistic in the whole relationship between better information and better decisions. The intervening variable, the person, or worse, the group of people, are make poor choices in the face of good futures. They have their own preferences and expectations. Judgement is certainly a trait that is distributed normally in the population. Besides, Arrow’s Theorem. That’s where automatic decision systems can help. Remember the idea of Website Morphing? You can read the[…]
The social app gaming trend continues apace. The mobile app gaming trend continues too. Remember PC gaming? Me too. Steam, from Valve, is a major way that PC gamers buy and manage their games. They release statistics. And, Lauri has visualized some statistics and made them available through an interface called ‘SteamGraph‘. It’s interesting to look at substitution among successive releases of games. A game in a series will be decaying in terms of active players over time. The next one in the series is released. You see a nice big spike in the new release, and then a slow, tell-tale decay. The previous games in the series resume their cold death, but at a slowing rate. PC gaming substitution[…]
Why did I buy the Wool by Hugh Howey Saturday night sometime after 11pm? In the tradition of Deb Luneau, who impressed me some six years ago with her customer journey diary, here’s my account of the consumer journey. We had gone to see the latest Batman. If you follow me on twitter, and open twitter on the weekends, and, have me in a list that you pay attention to, then you knew that I had low expectations going in. And, the movie exceeded my expectations. We got home at around 9pm and ate Thai. I fired up Netflix at around 11pm. It recommended a movie called ‘Kick-Ass’. Bad choice. What a terrible movie. The iPad was out by 11:15pm.[…]
I read, with glazed eyes, a product announcement that called predictive analytics an ‘extreme’ technology. lolwut It’s the latest buzzword. It might stick. What comes after Big Data? Extreme Data. Thrutch. Gnarly. Grinding. Both Extreme Data and Extreme Predictive Analytics are in use. Why does this happen? It happens because we have to introduce ideas that are old to us to markets where it’s new to them. It’s expedient to present old ideas as new, because novelty spawns excitement and action. And, in many societies, excitement spawns action. It creates demand. Predictive analytics has been in professional use since at least World War II. Did that keep airlines from adopting the techniques twenty years later? Of course not. And yet,[…]
Every year I spend a day with the strategists at the eat:Strategy conference in Toronto. What strategists say and how they treat each other is interesting and predictive. I heard five different definitions of insight I heard three different definitions of strategy I heard three different definitions of brand It’s interesting because there’s discord, and that it persists. The web analysts reading this post should click this link. Yeah baby. 5 out of the 8 presentations contained web analytics results as proof points that a strategy worked. 6 out of the 8 mentioned the importance of business objectives and customer needs/wants. The term ‘ROI’ was said with contempt by 2 out of the 8 speakers. Interesting. Maybe a little bit[…]
Einstein had it wrong. The only thing that moves faster than light through a vacuum is bullshit through a social medium. Marketing scientists in academia communicate to each other through journals and presentations. The peer reviewed journal innovation was necessitated by Sir Isaac Newton, who somehow had a drawer that was filled with the ideas of others. “Oh, that’s a neat idea, too bad you didn’t come up with it first. I had written about it five years before you, see, it was in my desk all along.” He wasn’t very popular. Academic findings are loosely peer reviewed (see: biology). There’s a form of moderation there. It varies, but it’s there. Industry marketing scientists talk over beer, blogs, conferences, pdf’s[…]