Trend Detection Using Auto-Associative Neural Networks

In section 2, a definition of “trend” is given. In section 3, it is shown how to detect a trend using an auto-associative neural network. Experimental methods and results are reported in sections 4 and 5, and concluding remarks are given in section 6. Abstract — This paper reports the results of a new neural network based trend detector. An auto-associative neural network was trained with the “trend” data obtained from the intra-day KOSPI 200 future price. It was then used to predict a trend. Simple investment strategies based on the detector achieved a one-year return of 31.2 points with no leverage. 2. Definition of Trend The definition of a Trend in the financial market is ambiguous and subjective. In order to obtain a training data set, a Trend pattern needs to be defined.