“Left Shoulder”Detection in Korea Composite Stock Price Index Using an Auto-Associative Neural Network and Sign Variables

자기연상 학습 신경망과 부호 입력 변수를 이용한 종합주가지수 "왼쪽어깨" 패턴 검출

  • 백진우 (서울대학교 산업공학과) ;
  • 조성준 (서울대학교 산업공학과)
  • Published : 2000.10.01

Abstract

We proposed a neural network based “left shoulder”detector. The auto-associative neural network was trained with the “left shoulder”patterns obtained from the Korea Composite Stock Price Index, and then tested out-of-sample with a reasonably good result. A hypothetical investment strategy based on the detector achieved a return of 132% in comparison with 39% return from a buy and hold strategy

Keywords