Dataset_HFT300: The high frequency trading data.
In lweicdsor/OSTSC: Over Sampling for Time Series Classification
Description
Usage
Format
Details
References
Description
This dataset is a random subset of a high frequency trading dataset used to assess the performace of RNNs for prediction (Dixon, 2017).
Usage
1
Format
A dataset with 300 observations of sequence length = 10, with a single sequence per row.
The y data is labeled as -1,0,1.
The x data constructs time series sequences (numeric).
Details
The feature represents the instantaneous liquidity imbalance using the best bid to ask ratio. The labels represent the next-event mid-price movement - Y=1 is an up-tick, Y=-1 is a down-tick and Y=0 represents no-movement. The time series sequences length is set
to 10. In this package, the class 1 and -1 observations are random selected to yield 12 non-zero observations, while class 0 has 288 observations. Observations are ordered chronologically.
References
Matthew Dixon.(2017) Sequence Classification of the Limit Order Book using Recurrent Neural Networks.
arXiv:1707.05642.
lweicdsor/OSTSC documentation built on May 8, 2019, 1:13 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Description Usage Format Details References
Description
This dataset is a random subset of a high frequency trading dataset used to assess the performace of RNNs for prediction (Dixon, 2017).
Usage
1 |
Format
A dataset with 300 observations of sequence length = 10, with a single sequence per row.
The y data is labeled as -1,0,1.
The x data constructs time series sequences (numeric).
Details
The feature represents the instantaneous liquidity imbalance using the best bid to ask ratio. The labels represent the next-event mid-price movement - Y=1 is an up-tick, Y=-1 is a down-tick and Y=0 represents no-movement. The time series sequences length is set to 10. In this package, the class 1 and -1 observations are random selected to yield 12 non-zero observations, while class 0 has 288 observations. Observations are ordered chronologically.
References
Matthew Dixon.(2017) Sequence Classification of the Limit Order Book using Recurrent Neural Networks. arXiv:1707.05642.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.