Timeline for Predicting the probability of product to be bought
Current License: CC BY-SA 3.0
17 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 3, 2017 at 15:45 | history | edited | kjetil b halvorsen♦ |
edited tags
|
|
| S Dec 9, 2016 at 16:24 | history | bounty ended | CommunityBot | ||
| S Dec 9, 2016 at 16:24 | history | notice removed | CommunityBot | ||
| Dec 7, 2016 at 16:04 | vote | accept | Pop | ||
| Dec 7, 2016 at 16:03 | vote | accept | Pop | ||
| Dec 7, 2016 at 16:04 | |||||
| Dec 6, 2016 at 13:38 | answer | added | Pop | timeline score: 0 | |
| Dec 6, 2016 at 8:06 | history | edited | Pop | CC BY-SA 3.0 |
edited body
|
| Dec 6, 2016 at 7:56 | history | edited | Pop | CC BY-SA 3.0 |
added 168 characters in body
|
| Dec 5, 2016 at 16:42 | comment | added | Drey | Do you have an exaple dataset? Your described approach is very crude one. You omit many important details in the data analysis pipeline... well your approach may or may not work. To tackle imbalanced data, see what other people did at kaggle for example (recently there was a bosch challange). If you want to combine probabilities take a look into Generalized Boosted Regression Models. | |
| S Dec 1, 2016 at 14:35 | history | bounty started | Pop | ||
| S Dec 1, 2016 at 14:35 | history | notice added | Pop | Authoritative reference needed | |
| Dec 1, 2016 at 14:33 | history | edited | Pop | CC BY-SA 3.0 |
added 24 characters in body
|
| Nov 30, 2016 at 8:56 | comment | added | Pop | Thanks for the idea but that does not answer my main concern. Even if I consider only one model learnt on an under-sampled dataset (with modified proportions of minority and majority classes), I do not know if it is an estimate of the probability. And if not, how to transform it make it become one. | |
| Nov 30, 2016 at 8:24 | comment | added | Tim | Mean may be not the best choice and there are more clever ways to proceed, see: stats.stackexchange.com/questions/155817/… | |
| Nov 30, 2016 at 8:08 | history | edited | Pop | CC BY-SA 3.0 |
deleted 5 characters in body
|
| Nov 28, 2016 at 16:57 | history | edited | Pop | CC BY-SA 3.0 |
added 44 characters in body
|
| Nov 28, 2016 at 16:23 | history | asked | Pop | CC BY-SA 3.0 |