Date of Award
Master of Arts (AM/MA)
In this paper, we build a deep neural network for modeling spatial structure in limit order book and make prediction for future best ask or best bid price based on ideas of (Sirignano 2016). We propose an intuitive data processing method to approximate the data is non-available for us based only on level I data that is more widely available. The model is based on the idea that there is local dependence for best ask or best bid price and sizes of related orders. First we use logistic regression to prove that this approach is reasonable. To show the advantages of deep neural network, we try different activation functions and compare the performances and program running time with other algorithms, such as logistic regression, kNN and random forest. And the deep neural network is the model that most suitable for limit order book. Besides this, the model contains an effective way to reduce overfitting problems. Also, this paper presents the limitations of our model and gives several methods to make improvements.
Chair and Committee
Nan Lin, Jimin Ding
xu, xin, "Deep learning analysis of limit order book" (2018). Arts & Sciences Electronic Theses and Dissertations. 1506.