{
  "id": 7660,
  "title": "repeat trips and repeaters",
  "url": "/competitions/acquire-valued-shoppers-challenge/discussion/7660",
  "author_name": "",
  "post_date": "2014-04-11T09:19:36.260Z",
  "votes": null,
  "comment_count": 18,
  "views": 6241,
  "content": "<p>these variables are the same right?&nbsp;</p>\n\n<p>repeaters = repeattrips &gt; 0 ?</p>",
  "messages": [
    {
      "id": "41701",
      "postDate": "04/11/2014 09:19:36",
      "content": "<p>these variables are the same right?&nbsp;</p>\n\n<p>repeaters = repeattrips &gt; 0 ?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "41712",
      "postDate": "04/11/2014 12:19:46",
      "content": "<p>I too guess the same.</p>\n<p>If repeatTrips &gt; 0 then repeaters = t else repeaters = f.</p>\n<p>I think the repeatTrips measure the intensity of the customer's repeated purchase. (a.k.a) how many times he came for the repeat purchase.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "41713",
      "postDate": "04/11/2014 13:00:23",
      "content": "<p>So its reapeat to the shop/brand/category?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "41715",
      "postDate": "04/11/2014 13:22:39",
      "content": "<p>Yes, this much is in the data description</p>\n<p style=\"padding-left: 30px\">repeater - A boolean, equal to repeattrips &gt; 0</p>\n<p>It indicates they repeat purchased the item for which they got on offer.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "41819",
      "postDate": "04/12/2014 21:53:02",
      "content": "<p>Can someone pls confirm that If&nbsp;repeattrips = 0 then it means that customer has never redeemed the offer in the very first place ?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "43700",
      "postDate": "05/05/2014 07:34:03",
      "content": "<p>@Decipher, from the problem description, you can see that if repeattrips=0, it only means that the shopper doesn't come back to purchase the same item again. it is not necessarily to indicate that he didn't redeem the offer.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44299",
      "postDate": "05/09/2014 13:58:53",
      "content": "<p>It seems to me that repeattrips is useless since it's not present in test history file. How we can take advantage to use this attribute?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44469",
      "postDate": "05/13/2014 16:00:30",
      "content": "<p>It's possible to use repeattrips to train the model but not use it explicitly as a feature.&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44470",
      "postDate": "05/13/2014 16:01:46",
      "content": "<p>[quote=David;44469]</p>\n<p>It's possible to use repeattrips to train the model but not use it explicitly as a feature.&nbsp;</p>\n<p>[/quote]</p>\n<p>Do let us know if you find out how</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44516",
      "postDate": "05/14/2014 11:20:14",
      "content": "<p>@Yiqun Hu -&nbsp;So going by your line of thought we are modeling whether customer will become repeat buyer or not, instead of if customer will buy/redeem the offer. Right?</p>\n<p>Also, here being repeater means purchasing the same item more than once so in the testhistory.csv we have to predict the probability of customer making more than 1 purchase of the same item. Am i understanding this correct?</p>\n<p>Thanks&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44523",
      "postDate": "05/14/2014 12:59:08",
      "content": "<p>One possible weight is to use it as a weight, so your model will know, that in this concrete case it's definitely repeater. Or use as a weight something like log(1 + repeats), or just say if it's more then 1 it have doubled weight and in other case it have ordinal weight. I hope I find out best way using CV :)</p>\n<p>I think it's natural for many algorithms to have some kind of weighted scheme, I didn't get to the testing of this for now, but I definitely will try this in some way.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44759",
      "postDate": "05/18/2014 00:13:20",
      "content": "<p>I tried to use repatertrips for weighting but I always get worse results, so at least in my approach it seems useless.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44763",
      "postDate": "05/18/2014 04:39:28",
      "content": "<p style=\"padding-left: 30px\">Did you try to scale that values? For example set 0.8 weight for repeattrips == 1, and 1.0 weight for others?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44802",
      "postDate": "05/19/2014 00:56:17",
      "content": "<p>Yes, I did roughly that and did see worse results, and I used different variables too with and without this weight assignment.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "44809",
      "postDate": "05/19/2014 05:23:50",
      "content": "<p>I&nbsp;did some experiments with this and also get slightly smaller scores</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "49001",
      "postDate": "06/11/2014 14:53:57",
      "content": "<p>I tried repeat trips and it helped me to improve a little bit.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "49018",
      "postDate": "06/11/2014 18:08:17",
      "content": "<p>It would be very helpful if you say what was your logic to weighting</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "49159",
      "postDate": "06/15/2014 17:41:03",
      "content": "<p>I am struggling to understand how to make use of repeat trips. Currently I am not able to make sense out of it since its not part of test. Weighting seems to be a good option, but it will be helpful to understand how one should apply the weighting.&nbsp;I tried a derived feature based on the ratio of transactions of brand(plus repeater trips) by overall transactions. My score went down.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "49385",
      "postDate": "06/22/2014 19:32:19",
      "content": "<p>If you wanted to look at repeattrips rather than repeater, you'd probably want to use a Tobit model. But I don't know if it will be helpful with this competition objective since we don't really care about how many repeat trips the customer makes, so long as they make 1.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 41712,
      "author_name": "muthujothi",
      "author_url": "",
      "post_date": "04/11/2014 12:19:46",
      "content": "<p>I too guess the same.</p>\n<p>If repeatTrips &gt; 0 then repeaters = t else repeaters = f.</p>\n<p>I think the repeatTrips measure the intensity of the customer's repeated purchase. (a.k.a) how many times he came for the repeat purchase.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 41713,
      "author_name": "abhishek",
      "author_url": "",
      "post_date": "04/11/2014 13:00:23",
      "content": "<p>So its reapeat to the shop/brand/category?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 41715,
      "author_name": "wcukierski",
      "author_url": "",
      "post_date": "04/11/2014 13:22:39",
      "content": "<p>Yes, this much is in the data description</p>\n<p style=\"padding-left: 30px\">repeater - A boolean, equal to repeattrips &gt; 0</p>\n<p>It indicates they repeat purchased the item for which they got on offer.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 41819,
      "author_name": "decipher",
      "author_url": "",
      "post_date": "04/12/2014 21:53:02",
      "content": "<p>Can someone pls confirm that If&nbsp;repeattrips = 0 then it means that customer has never redeemed the offer in the very first place ?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 43700,
      "author_name": "codingneo",
      "author_url": "",
      "post_date": "05/05/2014 07:34:03",
      "content": "<p>@Decipher, from the problem description, you can see that if repeattrips=0, it only means that the shopper doesn't come back to purchase the same item again. it is not necessarily to indicate that he didn't redeem the offer.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44299,
      "author_name": "vkuznet",
      "author_url": "",
      "post_date": "05/09/2014 13:58:53",
      "content": "<p>It seems to me that repeattrips is useless since it's not present in test history file. How we can take advantage to use this attribute?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44469,
      "author_name": "dave31415",
      "author_url": "",
      "post_date": "05/13/2014 16:00:30",
      "content": "<p>It's possible to use repeattrips to train the model but not use it explicitly as a feature.&nbsp;</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44470,
      "author_name": "abhishek",
      "author_url": "",
      "post_date": "05/13/2014 16:01:46",
      "content": "<p>[quote=David;44469]</p>\n<p>It's possible to use repeattrips to train the model but not use it explicitly as a feature.&nbsp;</p>\n<p>[/quote]</p>\n<p>Do let us know if you find out how</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44516,
      "author_name": "decipher",
      "author_url": "",
      "post_date": "05/14/2014 11:20:14",
      "content": "<p>@Yiqun Hu -&nbsp;So going by your line of thought we are modeling whether customer will become repeat buyer or not, instead of if customer will buy/redeem the offer. Right?</p>\n<p>Also, here being repeater means purchasing the same item more than once so in the testhistory.csv we have to predict the probability of customer making more than 1 purchase of the same item. Am i understanding this correct?</p>\n<p>Thanks&nbsp;</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44523,
      "author_name": "dremovd",
      "author_url": "",
      "post_date": "05/14/2014 12:59:08",
      "content": "<p>One possible weight is to use it as a weight, so your model will know, that in this concrete case it's definitely repeater. Or use as a weight something like log(1 + repeats), or just say if it's more then 1 it have doubled weight and in other case it have ordinal weight. I hope I find out best way using CV :)</p>\n<p>I think it's natural for many algorithms to have some kind of weighted scheme, I didn't get to the testing of this for now, but I definitely will try this in some way.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44759,
      "author_name": "vkuznet",
      "author_url": "",
      "post_date": "05/18/2014 00:13:20",
      "content": "<p>I tried to use repatertrips for weighting but I always get worse results, so at least in my approach it seems useless.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44763,
      "author_name": "dremovd",
      "author_url": "",
      "post_date": "05/18/2014 04:39:28",
      "content": "<p style=\"padding-left: 30px\">Did you try to scale that values? For example set 0.8 weight for repeattrips == 1, and 1.0 weight for others?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44802,
      "author_name": "vkuznet",
      "author_url": "",
      "post_date": "05/19/2014 00:56:17",
      "content": "<p>Yes, I did roughly that and did see worse results, and I used different variables too with and without this weight assignment.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 44809,
      "author_name": "dremovd",
      "author_url": "",
      "post_date": "05/19/2014 05:23:50",
      "content": "<p>I&nbsp;did some experiments with this and also get slightly smaller scores</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 49001,
      "author_name": "potato",
      "author_url": "",
      "post_date": "06/11/2014 14:53:57",
      "content": "<p>I tried repeat trips and it helped me to improve a little bit.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 49018,
      "author_name": "dremovd",
      "author_url": "",
      "post_date": "06/11/2014 18:08:17",
      "content": "<p>It would be very helpful if you say what was your logic to weighting</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 49159,
      "author_name": "vishwanathanraman",
      "author_url": "",
      "post_date": "06/15/2014 17:41:03",
      "content": "<p>I am struggling to understand how to make use of repeat trips. Currently I am not able to make sense out of it since its not part of test. Weighting seems to be a good option, but it will be helpful to understand how one should apply the weighting.&nbsp;I tried a derived feature based on the ratio of transactions of brand(plus repeater trips) by overall transactions. My score went down.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 49385,
      "author_name": "omalleyt",
      "author_url": "",
      "post_date": "06/22/2014 19:32:19",
      "content": "<p>If you wanted to look at repeattrips rather than repeater, you'd probably want to use a Tobit model. But I don't know if it will be helpful with this competition objective since we don't really care about how many repeat trips the customer makes, so long as they make 1.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "41701": "",
    "41712": "",
    "41713": "",
    "41715": "",
    "41819": "",
    "43700": "",
    "44299": "",
    "44469": "",
    "44470": "",
    "44516": "",
    "44523": "",
    "44759": "",
    "44763": "",
    "44802": "",
    "44809": "",
    "49001": "",
    "49018": "",
    "49159": "",
    "49385": ""
  },
  "source": "meta"
}