Gray Beard Posted January 17, 2014 Share Posted January 17, 2014 I question analytics versus statistics. For example, if a running play to the left with FJ22 will get you at least two yards 80% of the time, then when it is third down and two, you should call a running play to the left with FJ22. From what I have just read, that is not really what analytics is all about. That's kind of a shame, because I wish somebody would impress on these coaches that when it is third down and short, a long pass play that focuses on a single, well covered receiver running along the sideline will fail 95% of the time and stall your drive. Link to comment Share on other sites More sharing options...
Buffalo Barbarian Posted January 17, 2014 Share Posted January 17, 2014 One of the big words used after Marrone was hired by both him & the Bills grand pooh bah Russ Brandon was analytics . They talked about using them & have started a new analytics department at one Bills drive . I did graduate from high school so Russ & Marrone are much smarter than i so i had to look up exactly what the word meant which probably won't surprise many of you after reading a few of my posts ! The definition is as follows Analytics - Logic - the science of logical analysis . If they were so big on introducing this to the Bills why wasn't it used in building the current coaching staff ? There was no reason why they couldn't have opened the door for any of the other coaches to stay which could have meant players staying too . While watching the play offs i saw more than one of the Bills old coaches from Gailey's coaching staff prowling the side lines of some of the play off teams such as in San diego - Joe Dealisondris - Carolina - Bruce Dehaven & if any of you can add to this list please do ! I know that when a new coach comes in they want there guys with them but last year our O line was as good as it's been in years ! Good enough for CJ to average 6 YPC & allow a very low amount of sacks, & if Bruce Dehaven isn't better than Crossman then i'm going to put in my application for the ST coach . I didn't really care for the coaching choice but we have him now & i think he is a very passionate HC & has the team headed in the right direction . I also hope that he proves me totally wrong in what i thought of him being chosen ! But why didn't they use their brain child of installing this analytics thing while putting together his now staff ? It just makes little to no sense what so ever to be so gung hoe about something then don't use it immediately because he had all the previous years stats & how the Bills did . Not to mention it would have been less change as far as blocking schemes & would have gotten the offense up to speed much quicker !! Well it's all yours Bills fans what do you think ? If this has been discussed sorry but i must have missed it !! got to have chemistry, I think that is in highschool too. Link to comment Share on other sites More sharing options...
Rubes Posted January 17, 2014 Share Posted January 17, 2014 This is the rare example of a situation where I'm actually glad I opened a particular thread. Link to comment Share on other sites More sharing options...
Gerry Posted January 17, 2014 Share Posted January 17, 2014 These guys (Marrone, Brandon & Co.) are on the cutting edge with analytics; I hope the energy generated from brainstorming this offseason at One Bills Drive doesn't blow up the bubble..... Link to comment Share on other sites More sharing options...
Jerry Jabber Posted January 18, 2014 Share Posted January 18, 2014 I am currently working on my Master's Degree in Information Systems and came across these sections in the course book: “The Boston Red Sox won the World Series in 2004 and 2007. Contributing to their success is their sophisticated recruitment and layoff strategy, which is heavily supported by IT. Winning depends on identifying players with the right talents, knowing how long to keep each player, and developing the right strategy—all of which depend on information, analysis, and intelligence. Extensive and detailed data is available on each player and game. Players’ performance is measured down to every swing, step, or throw taken. Baselines are calculated on every facet of an athlete—height, weight, arm strength, hitting discipline, and mental errors. The Red Sox require players in their farm system to keep a log of their every at-bat.” “Teams need to develop a winning strategy. Sports data needs to be analyzed to compare actual performance of each player against average number of wins. This determines whether or not to pay $10 to $20 million per year to a star pitcher or other player and when to retire a player. Some teams can afford to pay more for players and therefore acquire the best players. Business intelligence (BI) can give every team an edge. BI is a broad category of applications, technologies, and processes for gathering, storing, accessing, and analyzing data to help business users make better decisions. BI helps identify the winning characteristics of “human capital” before the competition finds them. BI does analysis with sabermetrics. Sabermetrics is the mathematical analysis of player batting and pitching performances.” “The term is derived from SABR (Society for American Baseball Research), a community of baseball enthusiasts, and differs from traditional player metrics, such as runs batted in and batting averages. Sabermetricians use measures that accurately reflect a player’s contribution toward achieving a win, such as “runs created.” This statistic counts the number of times a batter gets on base and factors in an added value for the power of a hit (single or home run). The purpose is to determine what the batter does at the plate to create an opportunity for his team to score a run. Sabermetrics can help teams more accurately find minor league prospects likely to succeed in the big leagues.” "The Dallas Mavericks: Using IT for successful play and business. The Dallas Mavericks of the National Basketball Association (NBA) expect to fill every seat at every game in their stadium and to maximize sales from concessions and souvenir items.” “To track attendance, the Mavs were the first NBA team to put barcodes on tickets and then scan them.The information encoded in the barcode enabled them to find out whether group sales and community organization giveaways were filling seats or whether those marketing efforts were just wasting tickets.The team’s business managers have found other uses for the attendance information as well. By using forecasting models in a DSS, they more accurately predicted attendance for particular games and demand for beverages, which reduced beverage inventories by 50 percent—reducing inventory costs.” “Each of the 144 luxury suites is equipped with a PC that handles orders for merchandise, food, and beverages.Wireless access from all seats in the arena is available so that fans can place orders directly from their seats. All 840 cash registers at concessions stands, restaurants, stores, and bars use a sophisticated point-of-sale (POS) system. In the big retail store on the ground floor, salespeople using handheld computing devices ring up credit card purchases when lines get too long. During a game, managers can see which concession stands are busy and which can be closed early to cut labor costs. IT also supports the Mavs on the court. The team has 10 assistant coaches, and each has a laptop computer and a handheld computing device. Game films can be streamed over the Web for coaches to view on the road or at home. Another system developed in-house matches game footage with precise, to-the-minute statistics provided for every play of every game by the NBA. Coaches use data from the database to analyze the effectiveness of particular plays and combinations of players in different game situations." "Since 2002, the Mavs have used handheld computers to track the performance of each referee in every one of their games.The coaches look at patterns and trends—for example, to see which referee favors a given team or which one calls more three-second violations—and alert their players.Another system logs different offensive and defensive schemes used against the Mavs. It’s used by coaches to make realtime adjustments based on statistics from previous games." Depending on how much data the Bills are looking at, this could be very beneficial to the Bills in numerous areas, such as player acquisitions (draft/FA), game day situations (for example, if a ceratin player is on the field for the opposite tea, what is the likelihood of it being a pass or run). If the Bills analytical department is as extensive as the Boston Red Sox, then this could pay dividends in years to come. Link to comment Share on other sites More sharing options...
Over 29 years of fanhood Posted January 18, 2014 Share Posted January 18, 2014 (edited) This is the rare example of a situation where I'm actually glad I opened a particular thread. Yup. Nice thread collegial and insightful. Well done team. Oh and as always go bills! I question analytics versus statistics. For example, if a running play to the left with FJ22 will get you at least two yards 80% of the time, then when it is third down and two, you should call a running play to the left with FJ22. From what I have just read, that is not really what analytics is all about. You would not be the only on with that info. This stems back to the elapsing of time point one of the excellent posts made earlier... I believe The true north utopia of Analytics used by two competing teams would become an Unwinnable game. Statistical analysis is absolutely required,the models just use a lot more variables and test to see which matter. Edited January 18, 2014 by over 20 years of fanhood Link to comment Share on other sites More sharing options...
OCinBuffalo Posted January 18, 2014 Share Posted January 18, 2014 (edited) I question analytics versus statistics. For example, if a running play to the left with FJ22 will get you at least two yards 80% of the time, then when it is third down and two, you should call a running play to the left with FJ22. From what I have just read, that is not really what analytics is all about. That's kind of a shame, because I wish somebody would impress on these coaches that when it is third down and short, a long pass play that focuses on a single, well covered receiver running along the sideline will fail 95% of the time and stall your drive. Then, let me answer your question as follows with 2 hypotheticals: Statistics: run Fred to the left-->works 80% of the time. Analytics: runs to the left for RBs of Fred's type(power/slasher) work against this defense, or defenses constructed similarly, with "up to standard" players playing in all 11 spots, or, at least those on "the left" works....80% of time in cold weather, 60% of the time in hot. It works 60% of the time when the Bills are ahead or within 7 points of the other team, while it works 95% of the time when the Bills are down by more than 7 points. But, interestingly: it works 90% of the time when the Bills have thrown 2 or more times on this series, from this part of the field, but only 50% of the time when the Bills have run 1 or more times. Meanwhile, when we look at weather, score, field position and playcalling? We find that in this situation right now: where it's hot, the Bills are ahead in the game, and we've already run once this series, whose first down began on our 37 yard line? It's better to throw it. It's this part, right here, when we start throwing seemingly unrelated data into the mix, that we start to see patterns emerge. The challenge for 1 Bills drive? Stay the F out of the way, and let them emerge. EDIT: Then, all of a sudden....the Offensive Quality control coach, a young guy with little experience, but who can "see" steps up and says "hey, we have to throw a screen pass here, because the other team just substitued their big guys in for short yardage, and, every time a sub is made in this situation, screen passes work 95% of the time in these conditions". Will Hackett/Marrone listen? I dunno. That's a hell of a thing to ask them to do, but, if Ogilvie is right? These guys (Marrone, Brandon & Co.) are on the cutting edge with analytics; I hope the energy generated from brainstorming this offseason at One Bills Drive doesn't blow up the bubble..... Well, no. This: http://www.nytimes.c...o-killings.html which uses this: http://christopheviau.com/d3list/ (Example site) Or this: http://mikemcdearmon...lio/300-outings which also uses this: http://d3js.org/ (actual D3 home site, just click on a hex to see cool things!) Or this, my favorite(click anywhere to see why): http://bl.ocks.org/mbostock/7607535 + This: http://nodejs.org/ (F Java, F Ruby, F it all: we are talking analytics and in my case, real time, workflow+businesss process/rules-based analytics, so as I said, F the rest) + One/more of these: http://www.mongodb.org/ , http://redis.io/ or even this http://basho.com/riak/ (not recommended yet, but boy this one is going to good) = The cutting edge of analytics. Marrone and company may not be there, but now? You are. Check this crazy thing out: http://bost.ocks.org/mike/uberdata/. Once you get the hang of it, it's cool, but, I would never put that in front of a user. I am currently working on my Master's Degree in Information Systems and came across these sections in the course book: Nice. Want some unsolicited core competency advice? Edited January 18, 2014 by OCinBuffalo Link to comment Share on other sites More sharing options...
Dibs Posted January 18, 2014 Share Posted January 18, 2014 (edited) I question analytics versus statistics. For example, if a running play to the left with FJ22 will get you at least two yards 80% of the time, then when it is third down and two, you should call a running play to the left with FJ22. From what I have just read, that is not really what analytics is all about. That's kind of a shame, because I wish somebody would impress on these coaches that when it is third down and short, a long pass play that focuses on a single, well covered receiver running along the sideline will fail 95% of the time and stall your drive. I might be corrected here......but to put things simply.... Statistics is the gathered data. Analytics is the logical analysis of that data. Add more data(statistics)......ask more complex questions......get a better analytic result. Edit: Teams have used analytic methods since inception. Running on short yardage, passing on long, analyzing game footage for team/player tendencies etc, etc, etc.......these are all products of basic analytic study/thinking. Providing extra resources to develop the existing basic analytic methods(as well as expanding the scope of where it can be used) should have been done decades ago IMO. Edited January 18, 2014 by Dibs Link to comment Share on other sites More sharing options...
Dibs Posted January 18, 2014 Share Posted January 18, 2014 .... Will Hackett/Marrone listen? I dunno..... I tend to think they will listen. Marrone has stated several times this season that this sort of analytics is what he wants.....though his examples to the media were extremely simplistic. Link to comment Share on other sites More sharing options...
Gray Beard Posted January 18, 2014 Share Posted January 18, 2014 How do you tell if analytics is better than gut instinct? Isn't gut instinct what separates the good coaches from the great coaches? Based on gut instinct a coach can say "we have run to the right twice, it's time for a pass to the left" or "player x seems to be doing well today, let's throw him the ball" or "player y seems to be a step slower than usual today, let's exploit that and send players in his direction" etc. Aren't some coaches better at doing "analytic" type thinking on their own, without collecting a lot of data? (Apparently not Wanny) The example of diapers and beer shows how seemingly unrelated things can actually show a significant interdependence. Those are the types of things that would be interesting to find out about. Link to comment Share on other sites More sharing options...
OCinBuffalo Posted January 18, 2014 Share Posted January 18, 2014 I tend to think they will listen. Marrone has stated several times this season that this sort of analytics is what he wants.....though his examples to the media were extremely simplistic. I hope so. And, would I be too much of a to say: Like any NFL head coach, Marrone has learned to be a good communicator. Thus, he knows he knows Communication Rule #2: Know Your Audience. Perhaps that has something to do with using extremely simplistic examples? Link to comment Share on other sites More sharing options...
Rubes Posted January 18, 2014 Share Posted January 18, 2014 Statistics is the gathered data. Analytics is the logical analysis of that data. Hmm...I'd probably say the gathered data are just the data, while statistics is a mathematical description of those data. Link to comment Share on other sites More sharing options...
Dragonborn10 Posted January 18, 2014 Share Posted January 18, 2014 Analytics don't block anyone. I'm sure the analytics on CJ Spiller are off the charts but he has no vision. The scale says Kiko is too small but he made a lot of plays. If the analytics department show Lee Smith deserves to wear an NFL uniform I will take gut instinct or fan message board suggestions over the Bills analytics department any day. Link to comment Share on other sites More sharing options...
OCinBuffalo Posted January 18, 2014 Share Posted January 18, 2014 (edited) How do you tell if analytics is better than gut instinct? Easy: you look at the results of one vs. the other. Isn't gut instinct what separates the good coaches from the great coaches? Look at the greatest coaches, but also, look at the greatest generals, politicians, historical figures: all of them? Also the greatest teachers. I would say that teaching accounts for 60-90% of their success. Sure there are big personality types that can lead/get by based purely on charisma and speeches(remind you of anyone?)...but...in the end, the best leaders are leaders first, but also, good teachers. If you know the movie version of Patton, you know that he made a lot of great "gut calls". However, if you actually know, you know that he was an absolute bastard when it came to training, and, he never missed an opportunity to teach/mentor his younger officers. Everybody knows about the yelling and the cussing, few know about the teaching....which is exactly the way Patton wanted it. I would argue that the training allowed Patton to make those gut calls, because it gave him confidence in his men. No different than Belechick going for it, over and over, on 4th down. We all love to hate on him when he fails. But, ask yourself: we admire him for it, don't we? He does it, because he believes he's taught his players well enough that they can win in any situation, and if they believe they can, they will, more often than not. Analytics is great, and very powerful, but so is leadership. When both are done properly? It's a hell of thing to see. Based on gut instinct a coach can say "we have run to the right twice, it's time for a pass to the left" or "player x seems to be doing well today, let's throw him the ball" or "player y seems to be a step slower than usual today, let's exploit that and send players in his direction" etc. Aren't some coaches better at doing "analytic" type thinking on their own, without collecting a lot of data? (Apparently not Wanny) Actually most of what appears to be "gut" is merely: rote experience. You've seen the same thing happen over and over, so, your perception is altered to attend to that info, aggregate or minute, which is useful in that situation, and block out everything else, which is just as important. It's no different than a fisherman who knows where the fish are. It may look like "gut" but, actually it's just that he's picking up tiny bits of information, that he might not even be consciously aware of, that create a "feeling" for him. What makes this weird/seemingly supernatural: we don't know what those bits of data are, and the "lucky" fisherman doesn't either. What's really happening: the still undisputed analytics heavy weight of the world, the human brain, can process these pieces of data in real time, far better than computers currently can. However? The example of diapers and beer shows how seemingly unrelated things can actually show a significant interdependence. Those are the types of things that would be interesting to find out about. Diapers/Beer are things that are outside of our rote experience, therefore they are outside of our perception. Therefore, the human brain doesn't know to process them. Once the pattern is recognized, just like when you suddenly see a double jump move in checkers, you wonder how the hell you didn't see it immediately. When you get a "gut" feeling that somebody is a bad dude, it's because you've subconsciously seen something that tells you they are. You get a "bad feeling". But, it's not a feeling at all. It's data. Quantifiable data no less. You just don't realize that you've already processed it, and created your own "analytics" about it. Edited January 18, 2014 by OCinBuffalo Link to comment Share on other sites More sharing options...
Jerry Jabber Posted January 18, 2014 Share Posted January 18, 2014 Nice. Want some unsolicited core competency advice? Sure Link to comment Share on other sites More sharing options...
todd Posted January 18, 2014 Share Posted January 18, 2014 I know a little about analytics from an IT standpoint. You don't just hire somebody and then BOOM! you immediately have analytics. It doesn't work like that. Any analytics project is a multi-year effort. Here are the general steps for setting up a new analytics department, once the director of analytics has been hired: Create initial budget. (2 weeks) Create staffing strategy & hire analytics staff. This will be the first set of hires to stand up the system (2-3 months) Determine what software platform is best for what you are trying to do. There are a number of excellent platforms to choose from. (1 month) Purchase and install servers & software, or contract with 3rd party hosting/cloud facility for hardware/software install. (1.5 months) Determine measures. Determine what data you actually want to measure. (initial 2 -3 months, ongoing process) Create data collection routine & strategy. This would include ETL (extract, transform, load) processes from any existing data stores (HR systems containing salary, etc) (2-3 months) Create cube (BI data structure) (2 months?) Create reporting interface and mashup/display front end. (1-2 months) Refine, refine, refine. Develop more measures. Report on measures (forever) That's over a year of development just to start utilizing analytics. Sure, some data is useful before that, but my point is that this is a serious project that will take a while to show results. One of the big words used after Marrone was hired by both him & the Bills grand pooh bah Russ Brandon was analytics . They talked about using them & have started a new analytics department at one Bills drive . I did graduate from high school so Russ & Marrone are much smarter than i so i had to look up exactly what the word meant which probably won't surprise many of you after reading a few of my posts ! The definition is as follows Analytics - Logic - the science of logical analysis . If they were so big on introducing this to the Bills why wasn't it used in building the current coaching staff ? There was no reason why they couldn't have opened the door for any of the other coaches to stay which could have meant players staying too . While watching the play offs i saw more than one of the Bills old coaches from Gailey's coaching staff prowling the side lines of some of the play off teams such as in San diego - Joe Dealisondris - Carolina - Bruce Dehaven & if any of you can add to this list please do ! I know that when a new coach comes in they want there guys with them but last year our O line was as good as it's been in years ! Good enough for CJ to average 6 YPC & allow a very low amount of sacks, & if Bruce Dehaven isn't better than Crossman then i'm going to put in my application for the ST coach . I didn't really care for the coaching choice but we have him now & i think he is a very passionate HC & has the team headed in the right direction . I also hope that he proves me totally wrong in what i thought of him being chosen ! But why didn't they use their brain child of installing this analytics thing while putting together his now staff ? It just makes little to no sense what so ever to be so gung hoe about something then don't use it immediately because he had all the previous years stats & how the Bills did . Not to mention it would have been less change as far as blocking schemes & would have gotten the offense up to speed much quicker !! Well it's all yours Bills fans what do you think ? If this has been discussed sorry but i must have missed it !! Link to comment Share on other sites More sharing options...
JM57 Posted January 18, 2014 Share Posted January 18, 2014 (edited) Big credit to OCinBuffalo. One of the best threads I've read on TBD in a long time. Especially for an off season thread, when its usually wading through 2 pages of crap to find an OK thread Edited January 18, 2014 by JM57 Link to comment Share on other sites More sharing options...
BillsFanM.D. Posted January 18, 2014 Share Posted January 18, 2014 As a guy who's been getting paid to do "analytics" for quite some time, I believe I can answer your question. First of all, analytics is not a light switch. You don't just flip it, and suddenly you are doing it. Second? What the hell do diapers have to do with beer? Quite a lot actually, and we know this because of analytics. I always use this real world outcome of analytics to explain it. Third: here's your requirement Wrong. Sorry, but wrong. You don't approach analytics in terms of looking for the answers to your questions, or what "I believe". Clients constantly struggle with this. Yes, if you go looking for an answer, you'll probably find it: because your methodology was designed to find it. This is doing it wrong. Doing it right = You let questions, not answers, come to you. Questions, such as "Hey! There seems to be a connection between lowering the price of beer, and increased diaper sales, I wonder why?", is where the value of analytics becomes clear. If you started by saying "I think lowering the price of beer will increase beer sales", and go looking into the universe(fancy analytics word) you've created for this purpose, then yeah...somewhere, someplace, you'll find confirmation. But, more often than not, you've inherently biased the entire process towards your predetermined conclusion, and you've also missed a lot(diapers). Instead, the job is to create a universe WITHOUT a specific...something...you are trying to prove. Thus, the weird things, like diaper sales being a function of lowering beer prices, jump out at you. See, if you were just looking to measure beer prices, because you already "know" the "answer"....then you'd never have included diaper sales data in your universe. In this case of NFL coaches, if we just look at football coaches in terms of the play at their players positions, and build a universe on that? I'm sure you can prove what you are looking for too, but it's doubtful it's right...or at the very least, it's doubtful that we have the complete picture. Thus, building a proper universe should take time. You don't want everything you have, or maybe you do. Figuring our what is relevant, on a macro scale...is why you hire guys like me, who've done this before. We're objective. We aren't looking to prove anything other than: we know how to do it right. So finally, what the hell does beer have to do with diapers? Sale of diapers, when purchased as part of a small order(5 or less items sold) that also includes beer, increased when beer prices were lowered. The reason this was found? The sale of ALL items was looked at relative to beer prices(or prices of ALL items), for small orders, medium orders and big orders, and diapers jumped to the top of that list in terms of significant increase. In order to find out why, the customer's credit card info was added to cube(another fancy analytics word). Then, it was determined that these small orders were bought by: men. Who runs out to the store for diapers? Who is most likely to buy beer? Who makes buying decisions based on beer prices? Who doesn't know/care about diapers in general, never mind their prices? See? More questions, not answers. But, once you answer the questions with the right data? Boom. You want to sell more high margin diapers? Cut your beer prices, and you will, because men don't care about diapers, or their price, but they do care about beer, and its price. Get it? If we didn't build the data warehouse properly, to allow for these kind of cross-product analyses, or the ability to add dimensions, like the credit card data, if we didn't allow for what we call "drill across": this diapers/beer thing never happens. That's why analytics takes time, and this is why it's not a light switch. IF you want to use analytics to determine which coach to keep, and which to fire? You have a hell of a lot of work to do. I haven't been on here in a while but I'm shocked. This entire cogent post and not a single emoticon. You're slipping OC. Thanks for the info here. It is fascinating how the approach can literally dictate the findings if one allows it to happen (via desire, selection bias, methodology, etc)...and how the influence of beer is clearly 'untapped.' Very interesting topic and post. Link to comment Share on other sites More sharing options...
buffalover4life Posted January 18, 2014 Share Posted January 18, 2014 As a guy who's been getting paid to do "analytics" for quite some time, I believe I can answer your question. First of all, analytics is not a light switch. You don't just flip it, and suddenly you are doing it. Second? What the hell do diapers have to do with beer? Quite a lot actually, and we know this because of analytics. I always use this real world outcome of analytics to explain it. Third: here's your requirement Wrong. Sorry, but wrong. You don't approach analytics in terms of looking for the answers to your questions, or what "I believe". Clients constantly struggle with this. Yes, if you go looking for an answer, you'll probably find it: because your methodology was designed to find it. This is doing it wrong. Doing it right = You let questions, not answers, come to you. Questions, such as "Hey! There seems to be a connection between lowering the price of beer, and increased diaper sales, I wonder why?", is where the value of analytics becomes clear. If you started by saying "I think lowering the price of beer will increase beer sales", and go looking into the universe(fancy analytics word) you've created for this purpose, then yeah...somewhere, someplace, you'll find confirmation. But, more often than not, you've inherently biased the entire process towards your predetermined conclusion, and you've also missed a lot(diapers). Instead, the job is to create a universe WITHOUT a specific...something...you are trying to prove. Thus, the weird things, like diaper sales being a function of lowering beer prices, jump out at you. See, if you were just looking to measure beer prices, because you already "know" the "answer"....then you'd never have included diaper sales data in your universe. In this case of NFL coaches, if we just look at football coaches in terms of the play at their players positions, and build a universe on that? I'm sure you can prove what you are looking for too, but it's doubtful it's right...or at the very least, it's doubtful that we have the complete picture. Thus, building a proper universe should take time. You don't want everything you have, or maybe you do. Figuring our what is relevant, on a macro scale...is why you hire guys like me, who've done this before. We're objective. We aren't looking to prove anything other than: we know how to do it right. So finally, what the hell does beer have to do with diapers? Sale of diapers, when purchased as part of a small order(5 or less items sold) that also includes beer, increased when beer prices were lowered. The reason this was found? The sale of ALL items was looked at relative to beer prices(or prices of ALL items), for small orders, medium orders and big orders, and diapers jumped to the top of that list in terms of significant increase. In order to find out why, the customer's credit card info was added to cube(another fancy analytics word). Then, it was determined that these small orders were bought by: men. Who runs out to the store for diapers? Who is most likely to buy beer? Who makes buying decisions based on beer prices? Who doesn't know/care about diapers in general, never mind their prices? See? More questions, not answers. But, once you answer the questions with the right data? Boom. You want to sell more high margin diapers? Cut your beer prices, and you will, because men don't care about diapers, or their price, but they do care about beer, and its price. Get it? If we didn't build the data warehouse properly, to allow for these kind of cross-product analyses, or the ability to add dimensions, like the credit card data, if we didn't allow for what we call "drill across": this diapers/beer thing never happens. That's why analytics takes time, and this is why it's not a light switch. IF you want to use analytics to determine which coach to keep, and which to fire? You have a hell of a lot of work to do. This reminds me of my marketing research class at SJFC. Russ probably took it at one point. Link to comment Share on other sites More sharing options...
OCinBuffalo Posted January 18, 2014 Share Posted January 18, 2014 (edited) Sure PM sent. I haven't been on here in a while but I'm shocked. This entire cogent post and not a single emoticon. You're slipping OC. Thanks for the info here. It is fascinating how the approach can literally dictate the findings if one allows it to happen (via desire, selection bias, methodology, etc)...and how the influence of beer is clearly 'untapped.' Very interesting topic and post. One of these days, you guys are going to realize that what I do at PPP, isn't what I do everywhere else. Well...mostly. Excuse me, I believe this, , is yours. Also, one of these days: you will realize that the entire emoticon issue is a troll, especially because...I'm telling you it is. A troll, of a poster who is here all the time, who demanded that I insert a certain amount of emoticons per # of words...so that they could "get" my sarcasm. This was after my second post ever. More emoticons: were demanded. I have merely: responded. All it takes: for said poster to acknowledge their status as "he who has unleashed the upon us" and the emoticons will go away. Until then? All of this, is up to me, and not you. So? Live with it. Feel the s flying around you. Feel them tracking you, hunting you , waiting until you sleep . See them in your dreams! See them replace your kid's faces(which for some kids, is an improvement)! There will be no end to the s ! A sea of washing over you, you're drowning in .... Unless...the poster who has woven this spell...dispels it. Now, it's very likely they know all about this, yet, they do nothing. So, who is the real cause of your suffering? Edited January 18, 2014 by OCinBuffalo Link to comment Share on other sites More sharing options...
Recommended Posts