en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Machine Learning for Stock Selection
Published on Aug 14, 200723563 Views
In this paper, we propose a new method called Prototype Ranking (PR) designed for the stock selection problem. PR takes into account the huge size of real-world stock data and applies a modified compe
Related categories
Chapter list
Machine Learning for Stock Selection Robert J. Yan Charles X. Ling University of Western Ontario, Canada {jyan, cling}@csd.uwo.ca00:00
Outline-part0100:18
Introduction00:21
Outline-part0201:14
Stock Selection Task01:19
Outline-part0302:39
Prototype Ranking02:41
Step 1: Finding Prototypes03:14
Finding prototypes using competitive learning03:39
Modifications for Stock data04:05
Step 2: Predicting Test Data04:39
Outline-part0404:48
Data04:51
Testing PR05:11
Results of Experiment 106:21
Experiment 2: Comparison to Cooper’s method07:11
Results of Experiment 2 07:19
Outline-part0508:02
Conclusions08:05