|
on Market Microstructure |
| By: | Damian Kisiel; Denise Gorse |
| Abstract: | Previous attempts to predict stock price from limit order book (LOB) data are mostly based on deep convolutional neural networks. Although convolutions offer efficiency by restricting their operations to local interactions, it is at the cost of potentially missing out on the detection of long-range dependencies. Recent studies address this problem by employing additional recurrent or attention layers that increase computational complexity. In this work, we propose Axial-LOB, a novel fully-attentional deep learning architecture for predicting price movements of stocks from LOB data. By utilizing gated position-sensitive axial attention layers our architecture is able to construct feature maps that incorporate global interactions, while significantly reducing the size of the parameter space. Unlike previous works, Axial-LOB does not rely on hand-crafted convolutional kernels and hence has stable performance under input permutations and the capacity to incorporate additional LOB features. The effectiveness of Axial-LOB is demonstrated on a large benchmark dataset, containing time series representations of millions of high-frequency trading events, where our model establishes a new state of the art, achieving an excellent directional classification performance at all tested prediction horizons. |
| Date: | 2022–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2212.01807&r=mst |
| By: | Nadav Steinberg (Bank of Israel); Avi Wohl (Tel-Aviv University) |
| Abstract: | Bond repurchases are widespread in the US and other markets but data limitations have thus far prevented market-timing analysis. We fill this gap using unique daily data from Israel and show that firms time the market in their actual open-market bond repurchases. Firms repurchase their bonds following a decline in bond prices. The disclosure of bond repurchases results in significantly positive abnormal returns on the repurchased bonds and is followed by a positive drift in subsequent 5 trading days. The market reaction to actual bond repurchases is timelier when conducted within a preannounced repurchase program, and the impact is stronger when the firm repurchases high-yield bonds. Insiders’ net purchases increase prior to bond repurchases, and the abnormal return following a bond repurchase tends to be higher when it is preceded by positive net insider purchases. The results lend support to the information motive for bond repurchases. |
| Keywords: | Fixed income securities, Capital structure, Financial policy, Payout policy, Event studies, Information and disclosure |
| Date: | 2022–08 |
| URL: | http://d.repec.org/n?u=RePEc:boi:wpaper:2022.15&r=mst |
| By: | Dimitrios Kanelis; Pierre L. Siklos |
| Abstract: | We combine modern methods from Speech Emotion Recognition and Natural Language Processing with high-frequency financial data to analyze how the vocal emotions and language of ECB President Mario Draghi affect the yield curve of major euro area economies. Vocal emotions significantly impact the yield curve. However, their impact varies in size and sign: positive signals raise German and French yields, while Italian yields react negatively, which is reflected in an increase in yield spreads. A by-product of our study is the construction and provision of a synchronized data set for voice and language. |
| Keywords: | Communication, ECB, Neural Networks, High-Frequency Data, Speech Emotion Recognition, Asset Prices |
| JEL: | E50 E58 G12 G14 |
| Date: | 2022–12 |
| URL: | http://d.repec.org/n?u=RePEc:cqe:wpaper:10322&r=mst |