Google Analytics earlier this year launched a new report called conversion probability\nhttps://plus.google.com/+GoogleAnalytics/posts/QmG4yXmhfec
\n\nEven though this metric in not available in the competition dataset, it is quite interesting because, according to the definition: \n it is used to \"determine a user’s likelihood to convert during the next 30 days\"\nref: https://support.google.com/analytics/answer/7551092?hl=en
\n\nDoes this sound familiar ?\nSeems we are working on something that Google has already solved and in fact productionised.
\n\nTo the extent that this is possible, it would be great if after the submission deadline, \nsomeone from Kaggle/Google who's knowledgeable about the feature could share some more information around it, how it was developed and so on. It would be great feedback after working on this competition to see how the industry has addressed the task, so I am using the forum here to make a kind suggestion for this.
", "messages": [ { "id": 422978, "postDate": "2018-11-17T06:59:45.727Z", "content": "Google Analytics earlier this year launched a new report called conversion probability\nhttps://plus.google.com/+GoogleAnalytics/posts/QmG4yXmhfec
\n\nEven though this metric in not available in the competition dataset, it is quite interesting because, according to the definition: \n it is used to \"determine a user’s likelihood to convert during the next 30 days\"\nref: https://support.google.com/analytics/answer/7551092?hl=en
\n\nDoes this sound familiar ?\nSeems we are working on something that Google has already solved and in fact productionised.
\n\nTo the extent that this is possible, it would be great if after the submission deadline, \nsomeone from Kaggle/Google who's knowledgeable about the feature could share some more information around it, how it was developed and so on. It would be great feedback after working on this competition to see how the industry has addressed the task, so I am using the forum here to make a kind suggestion for this.
", "rawMarkdown": "Google Analytics earlier this year launched a new report called conversion probability\nhttps://plus.google.com/+GoogleAnalytics/posts/QmG4yXmhfec \n\nEven though this metric in not available in the competition dataset, it is quite interesting because, according to the definition: \n it is used to \"determine a user’s likelihood to convert during the next 30 days\"\nref: https://support.google.com/analytics/answer/7551092?hl=en \n\nDoes this sound familiar ?\nSeems we are working on something that Google has already solved and in fact productionised. \n\nTo the extent that this is possible, it would be great if after the submission deadline, \nsomeone from Kaggle/Google who's knowledgeable about the feature could share some more information around it, how it was developed and so on. It would be great feedback after working on this competition to see how the industry has addressed the task, so I am using the forum here to make a kind suggestion for this. ", "votes": 10 }, { "id": 423739, "postDate": "2018-11-19T00:44:45.460Z", "content": "Thanks for sharing good ref, Alexdandros!
\n\nThese sentenses will give us a little insight to make some good features:
\n\n\n", "rawMarkdown": "Thanks for sharing good ref, Alexdandros!\n\nThese sentenses will give us a little insight to make some good features:\n\n> Users who are on the threshold of converting are more easily convinced to complete those conversions. \nFor example, users who have studied product details or added items to their carts have given strong signals that they’re already taking ownership of those products. ", "votes": 1 }, { "id": 423179, "postDate": "2018-11-17T17:17:02.220Z", "rawMarkdown": "", "votes": 2, "isDeleted": true } ], "comments": [ { "id": 423739, "author_name": "Tak", "author_url": "", "post_date": "2018-11-19T00:44:45.460000", "content": "Users who are on the threshold of converting are more easily convinced to complete those conversions. \n For example, users who have studied product details or added items to their carts have given strong signals that they’re already taking ownership of those products.
\n
Thanks for sharing good ref, Alexdandros!
\n\nThese sentenses will give us a little insight to make some good features:
\n\n\n", "votes": 1, "replies": [] }, { "id": 423179, "author_name": "", "author_url": "", "post_date": "2018-11-17T17:17:02.220000", "content": "", "votes": 2, "replies": [] } ], "raw_markdown_by_id": { "422978": "Google Analytics earlier this year launched a new report called conversion probability\nhttps://plus.google.com/+GoogleAnalytics/posts/QmG4yXmhfec \n\nEven though this metric in not available in the competition dataset, it is quite interesting because, according to the definition: \n it is used to \"determine a user’s likelihood to convert during the next 30 days\"\nref: https://support.google.com/analytics/answer/7551092?hl=en \n\nDoes this sound familiar ?\nSeems we are working on something that Google has already solved and in fact productionised. \n\nTo the extent that this is possible, it would be great if after the submission deadline, \nsomeone from Kaggle/Google who's knowledgeable about the feature could share some more information around it, how it was developed and so on. It would be great feedback after working on this competition to see how the industry has addressed the task, so I am using the forum here to make a kind suggestion for this. ", "423739": "Thanks for sharing good ref, Alexdandros!\n\nThese sentenses will give us a little insight to make some good features:\n\n> Users who are on the threshold of converting are more easily convinced to complete those conversions. \nFor example, users who have studied product details or added items to their carts have given strong signals that they’re already taking ownership of those products. ", "423179": "" } }Users who are on the threshold of converting are more easily convinced to complete those conversions. \n For example, users who have studied product details or added items to their carts have given strong signals that they’re already taking ownership of those products.
\n