Predicting mid-to-mid price change over ~100 ticks is table stakes for a big quant fund (and easy even without ML). If you can monetise the prediction after accounting for latency, commissions, bid/offer spread and slippage, *then* I’ll be interestedhttps://www.bloomberg.com/news/articles/2021-06-08/man-group-oxford-quants-say-their-ai-can-predict-stock-moves …
-
Show this thread
-
Replying to @macrocephalopod
What if I trade only in those stocks where the mid-to-mid predicted price change is high enough for the costs to be amply compensated and then some?
2 replies 0 retweets 2 likes -
Replying to @ExpReturns @macrocephalopod
Simple linear models do well enough on that. You can't guarantee that you can directly monetize even large changes in midprice because it doesn't imply that both the bid and ask move, only one.
1 reply 0 retweets 6 likes
Replying to @ZakDavid @ExpReturns
Yeah, need to take into account how monetizable the move is, ideally at the prediction stage. One approach I’ve seen is to drop observations where the spread is large, or at least downweight them a lot.
6:14 AM - 9 Jun 2021
0 replies
0 retweets
5 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.