Timeline for What's a real-world example of "overfitting"?
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 11, 2020 at 14:32 | history | edited | CommunityBot |
Commonmark migration
|
|
| Dec 12, 2014 at 22:00 | comment | added | whuber♦ | @rolando2 I did not include a sort-of legend that appears in the original; it indicates that the truncated heavy blue line is for the 2014 season and the lighter blue lines are for "past years." It's actually a control you can use to limit the blue lines to a single year--you'll have to link to the site to use it. | |
| Dec 12, 2014 at 21:27 | comment | added | rolando2 | Interesting discussion. I'll add just that the graph might support the argument better if the lines were labeled. | |
| Dec 12, 2014 at 20:30 | comment | added | whuber♦ | @Tom I will stand by the quotation given here, which is an accurate one, as adequate support for why the Google Flu model is worthy of consideration in the present context. | |
| Dec 12, 2014 at 19:57 | comment | added | Tom Minka | The article only says that overfitting is a standard concern in data analysis. It does not claim that overfitting was the reason. Reference (2) goes into more detail, but again says that overfitting is only a "possible issue", with the statement "Because the search algorithm and resulting query terms that were used to define the original and updated GFT models remain undisclosed, it is difficult to identify the reasons for the suboptimal performance of the system and make recommendations for improvement." | |
| Dec 12, 2014 at 19:46 | comment | added | whuber♦ | @Tom The article is not written as if the allegation of overfitting is speculation: the authors flatly assert that. I think it's a reasonable statement. They also address the reason why they have to be somewhat speculative: Google was not open or transparent about the algorithm. It seems to me immaterial for the present purpose whether the overfitting occurred only in one version or many, but as I recall the authors address this too and point out evidence of continued overfitting in the current algorithm. | |
| Dec 12, 2014 at 19:36 | comment | added | Tom Minka | Unfortunately this example has some problems. The paper suggests two rather different reasons why GFT was making bad predictions: overfitting and changes to the search engine. The authors admit that they are not in a position to determine which reason (if any) is correct, so it is essentially speculation. Furthermore, the paragraph about overfitting refers to the original version of the system, while the predictions in the graph were made with a modified system. | |
| S Dec 11, 2014 at 23:36 | history | answered | whuber♦ | CC BY-SA 3.0 | |
| S Dec 11, 2014 at 23:36 | history | made wiki | Post Made Community Wiki by whuber♦ |