The Challenge Background states that "A quote event occurs whenever the best bid or the ask price is updated", and the figure indicates that a quote event appears at a change in bid or ask price. However, looking at the training data provided, first row,\r\n the first few events I see are (event type, timestamp, bid, ask):
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2373.5'
\r\n 'Q' '08:00:20.801' '2393' '2394'
So there are a good number of quote events with identical time, bid and ask price. What does that mean? Why is it an event?
\r\nFurthermore, from what I understand, for the prediction task the timestamps aren't given, and from what I see in the training data, I can very well expect that all bid,ask prices at t=51-100 might very well be identical, as they are sampled at identical\r\n times. Or they could be sampled hours apart.
\r\nAm I missing something? The lack of a prediction timestamp appears to me to render the problem useless.
\r\nThanks!
\r\n", "messages": [ { "id": "6667", "postDate": "11/21/2011 18:37:53", "content": "
The Challenge Background states that "A quote event occurs whenever the best bid or the ask price is updated", and the figure indicates that a quote event appears at a change in bid or ask price. However, looking at the training data provided, first row,\r\n the first few events I see are (event type, timestamp, bid, ask):
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2314.5'
\r\n 'Q' '08:00:20.799' '2225' '2373.5'
\r\n 'Q' '08:00:20.801' '2393' '2394'
So there are a good number of quote events with identical time, bid and ask price. What does that mean? Why is it an event?
\r\nFurthermore, from what I understand, for the prediction task the timestamps aren't given, and from what I see in the training data, I can very well expect that all bid,ask prices at t=51-100 might very well be identical, as they are sampled at identical\r\n times. Or they could be sampled hours apart.
\r\nAm I missing something? The lack of a prediction timestamp appears to me to render the problem useless.
\r\nThanks!
\r\n", "rawMarkdown": "", "votes": null }, { "id": "6718", "postDate": "11/22/2011 23:09:41", "content": "
Thanks for your reply.
\r\nFrom reading your background I got the impression that the main goal of the project was trying to best predict the shape of the liquidity replenishment curve (as shown in Figure 1 of the background page).
\r\nLet the curve be a function r(t), and we care about predicting r(t) for the range t = t0..t0+deltat, where t0 is the time of the liquidity shock, and deltat is some distance in the future.
\r\nHowever, the way this competition is evaluated is that you look at unknown, quasi-random points in {t0...t0+delta_t}, and evaluate my predictions at those. So I guess the project is still doable, but I expect lots of noise to be introduced into the result,\r\n and chance might contribute much more to the winner's score than having a good model for predicting r(t).
\r\nI think that the competition would be much more focused on predicting the shape of r(t) if you would provide the timestamps for t=51..100 in the test data.
\r\nBut I'll give it a shot and see what happens.
", "rawMarkdown": "", "votes": null }, { "id": "7167", "postDate": "12/15/2011 05:05:35", "content": "In real life surely the volume of securities exchanged at a trade would be important and used for prediction of recovery.
", "rawMarkdown": "", "votes": null } ], "comments": [ { "id": 6718, "author_name": "gabiteodoru", "author_url": "", "post_date": "11/22/2011 23:09:41", "content": "Thanks for your reply.
\r\nFrom reading your background I got the impression that the main goal of the project was trying to best predict the shape of the liquidity replenishment curve (as shown in Figure 1 of the background page).
\r\nLet the curve be a function r(t), and we care about predicting r(t) for the range t = t0..t0+deltat, where t0 is the time of the liquidity shock, and deltat is some distance in the future.
\r\nHowever, the way this competition is evaluated is that you look at unknown, quasi-random points in {t0...t0+delta_t}, and evaluate my predictions at those. So I guess the project is still doable, but I expect lots of noise to be introduced into the result,\r\n and chance might contribute much more to the winner's score than having a good model for predicting r(t).
\r\nI think that the competition would be much more focused on predicting the shape of r(t) if you would provide the timestamps for t=51..100 in the test data.
\r\nBut I'll give it a shot and see what happens.
", "votes": null, "replies": [] }, { "id": 7167, "author_name": "jc3626439", "author_url": "", "post_date": "12/15/2011 05:05:35", "content": "In real life surely the volume of securities exchanged at a trade would be important and used for prediction of recovery.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "6667": "", "6718": "", "7167": "" }, "source": "meta" }