There are two tables. The target.csv file has one record for every\ncustomer in the training and test sets. The id variable uniquely \nidentifies a customer and logtarg is the dependent variable. It is \nset to NA for the test cases. There should be 19,259 records plus a \nheader line giving the variale names.\n
The orders.csv file has one record for every item ordered by a \ncustomer in the test or training set prior to the contact point. \nThere are 775012 records plus a header line. The variables are as \nfollows:\n
Here is example code to get your started. Upload testanswer.csv.\n
\nlibrary(tidyverse)\nsetwd(\"/Users/ecm/teach/data/booknew\")\norders = read.csv(\"orders.csv\")\ntarget = read.csv(\"target.csv\")\n\nrfm = orders %>%\n group_by(id) %>%\n summarise(tof=max(t), r = min(t), fitem=n(), ford=n_distinct(ordnum), m=sum(price*qty))\nhead(rfm)\nsummary(rfm)\n\nall = target %>%\n left_join(rfm, by=\"id\")\ntrain=!is.na(all$logtarg)\nfit = lm(logtarg ~ r + fitem + m, data=all, subset=train)\nyhat = predict(fit, all[!train,])\nans = data.frame(id=all$id[!train], logtarg=yhat)\nwrite.csv(ans, \"testanswer.csv\", row.names=F)\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "A German book retailer sent out offers to customers. You job is to build predictor variables and a machine learning model to predict how much each customer who received the contact point will spend. The outcome variable is logtarg. The test set is indicated by is.na(logtarg). The objective is to predict logtarg with minimum RMSE on the test set.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "
The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:
\r\nThe evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:
\r\n\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]
\r\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.
\r\nFor every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).
\r\nThe file should contain a header and have the following format:
\r\nAuthorId,DuplicateAuthorIds", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "You may submit up to two entries a day until 11:59pm on June 8. The winner will be the team with the lowest MSE on the private leader board test set.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }
1,1
8,8
9,9 10
10,10 9
etc.