|
Activity Number:
|
643
- Detection of Changes and Structural Breaks in Business and Industrial Data Streams
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Quality and Productivity Section
|
|
Abstract #305330
|
|
|
Title:
|
Pattern Detection via Biclustering in High-Frequency Financial Time Series
|
|
Author(s):
|
Haitao Liu* and Nalini Ravishanker and Jian Zou
|
|
Companies:
|
Worcester Polytechnic Institute and University of Connecticut and Worcester Polytechnic Institute
|
|
Keywords:
|
Bicluster;
High-Frequency Financial Data;
Structure breaks
|
|
Abstract:
|
As high-frequency transaction-by-transaction data are widely available, it is critical for researchers and investors to dynamically study patterns of co-movement over multiple trading days. Exploring high-frequency transaction-level financial data is of considerable interest to researchers and investors. To this end, we have developed a multiple day time series biclustering algorithm based on aggregating the transaction-by-transaction data to regular (one to five minute) time intervals within each trading day. We examine the robustness of co-movement probabilities of selected m-tuples of stocks to stay within the same bicluster over multiple trading days to a) the sampling aggregation frequency or sampling rate and b) the bliclustering metric. Additionally, we describe an approach to describe patterns and monitor the structure of high-dimensional daily or weekly time series that track linkages between any given m-tuple of stocks over a long time period.
|
Authors who are presenting talks have a * after their name.
