{ "data_id": "42717", "name": "Click_prediction_small", "exact_name": "Click_prediction_small", "version": 9, "version_label": null, "description": "**Author**: Tencent Inc. \n**Source**: [KDD Cup](https:\/\/www.kddcup2012.org\/) - 2012 \n**Please cite**: \n\n**0.1% balanced subsample of the original KDD dataset** \n\nThis data is derived from the 2012 KDD Cup. The data is subsampled to 0.1% of the original number of instances, downsampling the majority class (click=0) so that the target feature is reasonably balanced (5 to 1).\n\nThe data is about advertisements shown alongside search results in a search engine, and whether or not people clicked on these ads. \nThe task is to build the best possible model to predict whether a user will click on a given ad.\n\nA search session contains information on user id, the query issued by the user, ads displayed to the user, and target feature indicating whether a user clicked at least one of the ads in this session. The number of ads displayed to a user in a session is called \u2018depth\u2019. The order of an ad in the displayed list is called \u2018position\u2019. An ad is displayed as a short text called \u2018title\u2019, followed by a slightly longer text called \u2019description\u2019, and a URL called \u2018display URL\u2019. \nTo construct this dataset each session was split into multiple instances. Each instance describes an ad displayed under a certain setting (\u2018depth\u2019, \u2018position\u2019). Instances with the same user id, ad id, query, and setting are merged. Each ad and each user have some additional properties located in separate data files that can be looked up using ids in the instances.\n\nThe dataset has the following features: \n* Click \u2013 binary variable indicating whether a user clicked on at least one ad. \n* Impression - the number of search sessions in which AdID was impressed by UserID who issued Query.\n* Url_hash - URL is hashed for anonymity\n* AdID \n* AdvertiserID - some advertisers consistently optimize their ads, so the title and description of their ads are more attractive than those of others\u2019 ads.\n* Depth - number of ads displayed to a user in a session\n* Position - order of an ad in the displayed list\n* QueryID - is the key of the data file 'queryid_tokensid.txt'. (follow the link to the original KDD Cup page, track 2)\n* KeywordID - is the key of 'purchasedkeyword_tokensid.txt' (follow the link to the original KDD Cup page, track 2)\n* TitleID - is the key of 'titleid_tokensid.txt'\n* DescriptionID - is the key of 'descriptionid_tokensid.txt' (follow the link to the original KDD Cup page, track 2)\n* UserID \u2013 is also the key of 'userid_profile.txt' (follow the link to the original KDD Cup page, track 2). 0 is a special value denoting that the user could be identified.", "format": "ARFF", "uploader": "Neeratyoy Mallik", "uploader_id": 8309, "visibility": "public", "creator": null, "contributor": null, "date": "2014-11-27 01:18:40", "update_comment": null, "last_update": "2014-11-27 01:26:36", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/184157\/phpfGCaQC", "default_target_attribute": "click", "row_id_attribute": null, "ignore_attribute": "\"url_hash\",\"query_id\"", "runs": 0, "suggest": { "input": [ "Click_prediction_small", "This data is derived from the 2012 KDD Cup. The data is subsampled to 0.1% of the original number of instances, downsampling the majority class (click=0) so that the target feature is reasonably balanced (5 to 1). The data is about advertisements shown alongside search results in a search engine, and whether or not people clicked on these ads. The task is to build the best possible model to predict whether a user will click on a given ad. A search session contains information on user id, the que " ], "weight": 5 }, "qualities": { "NumberOfInstances": 39948, "NumberOfFeatures": 10, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 9, "NumberOfSymbolicFeatures": 1, "Dimensionality": 0.00025032542304996493, "PercentageOfNumericFeatures": 90, "MajorityClassPercentage": 83.15810553719835, "PercentageOfSymbolicFeatures": 10, "MajorityClassSize": 33220, "MinorityClassPercentage": 16.841894462801644, "MinorityClassSize": 6728, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 10, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.7170250582021178, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Economics" }, { "uploader": "38960", "tag": "Human Activities" } ], "features": [ { "name": "click", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "33220", "0" ], [ "0", "6728" ] ] ] }, { "name": "impression", "index": "1", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "11820", "mean": "2", "stdev": "66" }, { "name": "url_hash", "index": "2", "type": "numeric", "distinct": "6941", "missing": "0", "ignore": "1", "min": "2147483647", "max": "2147483647", "mean": "2147483647", "stdev": "2147483647" }, { "name": "ad_id", "index": "3", "type": "numeric", "distinct": "19228", "missing": "0", "min": "1000515", "max": "22227340", "mean": "16016716", "stdev": "7222260" }, { "name": "advertiser_id", "index": "4", "type": "numeric", "distinct": "6064", "missing": "0", "min": "82", "max": "39074", "mean": "22454", "stdev": "11796" }, { "name": "depth", "index": "5", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "2", "stdev": "1" }, { "name": "position", "index": "6", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "1", "stdev": "1" }, { "name": "query_id", "index": "7", "type": "numeric", "distinct": "30748", "missing": "0", "ignore": "1", "min": "0", "max": "26240100", "mean": "3142146", "stdev": "5841540" }, { "name": "keyword_id", "index": "8", "type": "numeric", "distinct": "19803", "missing": "0", "min": "0", "max": "1243163", "mean": "35194", "stdev": "100915" }, { "name": "title_id", "index": "9", "type": "numeric", "distinct": "25321", "missing": "0", "min": "0", "max": "4050208", "mean": "173283", "stdev": "465675" }, { "name": "description_id", "index": "10", "type": "numeric", "distinct": "22381", "missing": "0", "min": "0", "max": "3171504", "mean": "111151", "stdev": "328374" }, { "name": "user_id", "index": "11", "type": "numeric", "distinct": "30114", "missing": "0", "min": "0", "max": "23907337", "mean": "3669622", "stdev": "5492058" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }