Activity Number:
|
670
- Statistical Computing in Data Science
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 3, 2017 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #323063
|
View Presentation
|
Title:
|
Trends and Volatility of Stock Prices Following Occurrence of Specific Technical Patterns
|
Author(s):
|
James Shine* and James Gentle and Charles Perry
|
Companies:
|
US Army (retired) and George Mason University and USDA retired
|
Keywords:
|
financial data ;
time series ;
prediction ;
trend ;
pattern detection ;
volatility
|
Abstract:
|
A well-known heuristic in financial time series is that a "head and shoulders" pattern (a small peak, a larger peak, and a second small peak) after a long upward trend is a predictor of a future downward trend. We look to assess this and other heuristics against actual financial time series data. We define specific technical patterns and then detect these patterns on real stock data over multiple stocks, time intervals and step sizes. We then compare trend and volatility measures of the stock after the pattern occurs. Our results and their comparison with other studies will be presented and discussed.
|
Authors who are presenting talks have a * after their name.