Member: QA7uiXy8vIbUSPOkCf9RwQ3FsT8jVq2OxDr8zqa7bRQ: https://imgur.com/UUuNZei
\n\nSome points:
\n\nThe member renews his suscription automatically many times.
In 20150430, the member renews his suscription with payment_plan_days=0 and plan_list_price=0. Some explanation?
In 20160505 the user cancels his suscription and renews with other plan in the next transaction, in 20160621. I think that must be an offer, because the member keeps going with the previous plan in the following transactions after cancelation.
This member is obviously in test dataset as the expiration date of the last transaction falls in 2017-3.
But this member is also in the train dataset and with is_churn=1! Can someone explain why? Because the user renews his subscription before the expiration date arrives.
Member: QA7uiXy8vIbUSPOkCf9RwQ3FsT8jVq2OxDr8zqa7bRQ: https://imgur.com/UUuNZei
\n\nSome points:
\n\nThe member renews his suscription automatically many times.
In 20150430, the member renews his suscription with payment_plan_days=0 and plan_list_price=0. Some explanation?
In 20160505 the user cancels his suscription and renews with other plan in the next transaction, in 20160621. I think that must be an offer, because the member keeps going with the previous plan in the following transactions after cancelation.
This member is obviously in test dataset as the expiration date of the last transaction falls in 2017-3.
But this member is also in the train dataset and with is_churn=1! Can someone explain why? Because the user renews his subscription before the expiration date arrives.
The last 4 transactions for such member are listed below
\n\ntransaction_date,membership_expire_date,is_cancel
\n\n20161130,20170121,0
\n\n20161231,20170221,0
\n\n20170131,20170321,0
\n\n20170224,20170321,1
\n\nIn data description,
\n\n\n\n\n\n
\n- \n
The criteria of \"churn\" is no new valid service subscription within 30 days after the current membership expires.
- \n
The train data consists of users whose subscription expires within the month of February 2017, and the test data is with users whose subscription expires within the month of March 2017
There was a record with membership_expire_date on 20170221 and no valid transaction between 20170221 and 20170321 (20170224 is a canceled transaction), which satisfies the train data condition and defines as \"churn\".
\n\nThere was a record with membership_expire_date on 20170321, which satisfies the predict data condition. If the member had any valid transaction between 20170321 and 20170421, he was not a churned member.
", "rawMarkdown": "The last 4 transactions for such member are listed below\n\n**transaction_date,membership_expire_date,is_cancel**\n\n20161130,20170121,0\n\n20161231,20170221,0\n\n20170131,20170321,0\n\n20170224,20170321,1\n\nIn data description, \n\n> 1. The criteria of \"churn\" is no new valid service subscription within 30 days after the current membership expires.\n\n> 2. The train data consists of users whose subscription expires within the month of February 2017, and the test data is with users whose subscription expires within the month of March 2017\n\nThere was a record with membership_expire_date on 20170221 and no valid transaction between 20170221 and 20170321 (20170224 is a canceled transaction), which satisfies the train data condition and defines as \"churn\". \n\nThere was a record with membership_expire_date on 20170321, which satisfies the predict data condition. If the member had any valid transaction between 20170321 and 20170421, he was not a churned member.", "votes": null }, { "id": "231277", "postDate": "10/14/2017 08:13:51", "content": "\"the member renews his suscription with payment_plan_days=0 and plan_list_price=0.\", Do you have any new idea?
\nthks.
The last 4 transactions for such member are listed below
\n\ntransaction_date,membership_expire_date,is_cancel
\n\n20161130,20170121,0
\n\n20161231,20170221,0
\n\n20170131,20170321,0
\n\n20170224,20170321,1
\n\nIn data description,
\n\n\n\n\n\n
\n- \n
The criteria of \"churn\" is no new valid service subscription within 30 days after the current membership expires.
- \n
The train data consists of users whose subscription expires within the month of February 2017, and the test data is with users whose subscription expires within the month of March 2017
There was a record with membership_expire_date on 20170221 and no valid transaction between 20170221 and 20170321 (20170224 is a canceled transaction), which satisfies the train data condition and defines as \"churn\".
\n\nThere was a record with membership_expire_date on 20170321, which satisfies the predict data condition. If the member had any valid transaction between 20170321 and 20170421, he was not a churned member.
", "votes": null, "replies": [] }, { "id": 231277, "author_name": "casscw", "author_url": "", "post_date": "10/14/2017 08:13:51", "content": "\"the member renews his suscription with payment_plan_days=0 and plan_list_price=0.\", Do you have any new idea?
\nthks.