MULTIFRAKTALITAS DAN STUDI KOMPARATIF PREDIKSI INDEKS DENGAN METODE ARIMA DAN ARTIFICIAL NEURAL NETWORK (ANN)

Abstract

This paper discusses technical analysis widely used by investors. There are many methods that exist and used by investor to predict the future value of a stock. In this paper we startfromfinding the value of Hurst (H) exponent of LQ 45 Index to lmow the form of the Index. From H vulue, we could determinate that the time series datq is purely random, or ergodic and ant persistent, or persistent to q certain trend. Two prediction tools were chosen, ANMA (Auto Regressive Integrated Moving Average) which is the de facto standqrd for univariate prediction model in econometrics and Artificial Neural Network (A]r{N) Back Propagation. Data leftfrom ANMA is used as an inputfor both metltods. We compared prediction error fro* each method to determine which method is better. The result shows that LQ45 Index is persistent to a certain trend therefore predictable and for outputted sample data ANMA outperforms ANN.