zcakhaa / DeepLOB-Deep-Convolutional-Neural-Networks-for-Limit-Order-Books

This jupyter notebook is used to demonstrate our recent work, "DeepLOB: Deep Convolutional Neural Networks for Limit Order Books", published in IEEE Transactions on Singal Processing. We use FI-2010 dataset and present how model architecture is constructed here. The FI-2010 is publicly avilable and interested readers can check out their paper.
374 stars 205 forks source link

LSE data avaliable? #25

Open ownnaruto opened 1 year ago

ownnaruto commented 1 year ago

你好,LSE LOB 数据目前公开了吗?在哪里可以找到呢?

ownnaruto commented 1 year ago

另外,我想问一下,数据是5只股票混合在一起的,如果使用窗口的概念,那是不是会出现不同股票的event混合在一起呢?(如果数据是5只股票stack在一起,那影响可能不是很大,但我看FI-2010的论文中似乎并没有详细说明5只股票是怎样混合的?)

wangxk15 commented 4 months ago

同样的问题,在这篇论文和code里都没有看到是怎么处理5支股票混在一起的情况的。在data_classification()函数里直接对整个数据集做了处理,这样不会把所有股票的混在一起吗?