tag:blogger.com,1999:blog-32202893.post7816980054291405077..comments2023-10-18T08:32:17.510-07:00Comments on Kevin Hillstrom: MineThatData: A Forecasting QuizUnknownnoreply@blogger.comBlogger6125tag:blogger.com,1999:blog-32202893.post-52387541595051911612007-06-10T10:00:00.000-07:002007-06-10T10:00:00.000-07:00For segment four and segment five, you can use the...For segment four and segment five, you can use the dropoff in performance for segments one, two and three to estimate segments four and five.<BR/><BR/>This exercise assumes the same level of online marketing from year to year. Adjustments to online marketing volume should happen if traffic increases, conversion rate improvements or online marketing changes are expected.<BR/><BR/>The really good forecasting folks don't actually use a lot of statistical modeling ... gut feel, business instinct, knowledge of relationships and numerical accuracy are most important.<BR/><BR/>For me, the most important thing is the dropoff between the first and second segment, then the second and third segment. That tells me that I should see smaller and smaller dollar dropoffs from segment three to segment four, and smaller yet from segment four to segment five.MineThatDatahttps://www.blogger.com/profile/14014200122021988374noreply@blogger.comtag:blogger.com,1999:blog-32202893.post-77716471312453070362007-06-09T00:12:00.000-07:002007-06-09T00:12:00.000-07:00Kevin,How did you come up with your numbers? Great...Kevin,<BR/>How did you come up with your numbers? Great exercise, but a little more detail on segments 4 and 5--were they marketed in anyway or just stumbled on web? Either way, I thought both you and Bryan have underestimated the ratio of online sales to catalog, seeing as portion of segments 4 and 5 already used it year previously without catalog and would do so again even with catalog mailed to them.<BR/>Thanks for sharing.<BR/>KAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-32202893.post-44238589096294979222007-06-06T09:10:00.000-07:002007-06-06T09:10:00.000-07:00Thank you, Kevin. How did you arrive at your fore...Thank you, Kevin. How did you arrive at your forecast? <BR/><BR/>I agree wholeheartedly with your comment regarding intuition (ans history and context) as key inputs into any forecast. <BR/><BR/>The numbers alone, without context, ignore several key elements...longer term file performance and trends, segment migration (e.g., source) of the customers in each segment, plus a feel for the merchandise and how changes in the assortment might effect response.<BR/><BR/>Plus, with a little history, predictions can be vetted against the reality of actuals over time, which is perhaps the best way to validate and refine forecasting models.<BR/><BR/>Awesome blog, by the way. Thanks!Unknownhttps://www.blogger.com/profile/08659348302720417457noreply@blogger.comtag:blogger.com,1999:blog-32202893.post-49741562952335182822007-06-05T20:00:00.000-07:002007-06-05T20:00:00.000-07:00Steve/Bryan ... not too shabby!If it were me, I wo...Steve/Bryan ... not too shabby!<BR/><BR/>If it were me, I would estimate Segment Four to spend $2.25 in catalog, $2.90 online, if mailed a catalog.<BR/><BR/>I would estimate Segment Five to spend $2.00 in catalog, $2.65 online, if mailed a catalog.<BR/><BR/>Do the math, and you end up with $3,100,750.<BR/><BR/>This is a great example to illustrate that there isn't a right or wrong answer to any of these problems.<BR/><BR/>Over time, an analyst develops an intuition that suggests which of these three answers is "most likely" to be accurate.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-32202893.post-40151240460274112992007-06-05T15:32:00.000-07:002007-06-05T15:32:00.000-07:00I used regression modeling on the spend per custom...I used regression modeling on the spend per customer in each segment. Catalog appears to follow a power law degradation, while online appears to follow a linear degredation, with an incremental degredation when we don't mail a catalog...i.e., catalog drives online and offline value.<BR/><BR/>So, I came up with the following, assuming I mail the whole file...<BR/><BR/>Segment<BR/>Households<BR/>Predicted Catalog<BR/>Predicted Online<BR/>Predicted Totals<BR/>% of online driven by catalog<BR/> <BR/>Customer Segment 1<BR/>62,000<BR/>$5.69<BR/>$4.25<BR/>$616,156<BR/>38%<BR/><BR/>Customer Segment 2<BR/>68,000<BR/>$3.35<BR/>$3.75<BR/>$482,589<BR/>36%<BR/><BR/>Customer Segment 3<BR/>79,000<BR/>$2.45<BR/>$3.25<BR/>$450,634<BR/>34%<BR/><BR/>Customer Segment 4<BR/>125,000<BR/>$1.97<BR/>$2.75<BR/>$589,919 <BR/>31%<BR/><BR/>Customer Segment 5<BR/>195,000<BR/>$1.66<BR/>$2.25<BR/>$762,502 <BR/>27%<BR/><BR/>Total<BR/>529,000<BR/>$2.54<BR/>$2.94<BR/>$2,901,799<BR/>31%<BR/><BR/>End is, about $2.9 million in total demand, with 31% of online demand driven by catalog. I estimated that latter number by looking at the trend by segment of those mailed last year versus those not mailed...<BR/><BR/>Net net, mailing the whole file will add $792 to the demand total, and theoretically, catalog is responsible for $1.845 million in demand - roughly 2/3.Unknownhttps://www.blogger.com/profile/08659348302720417457noreply@blogger.comtag:blogger.com,1999:blog-32202893.post-86818115599411967912007-06-01T12:28:00.000-07:002007-06-01T12:28:00.000-07:00One approach is to use the computed average for la...One approach is to use the computed average for last year's values. The average catalog sale amount for LY was 3.62 (to two significant digits, 3.6216 if you want more precision for later). Assume that this average holds for next year along with the other segment values. This drives the average catalog sale up to 3.66. The revised average sale for online becomes 2.52. The forecasted grand total is approx $3,268,540.Anonymousnoreply@blogger.com