Modelling volatility of Kuala Lumpur composite index (KLCI) using SV and garch models

Abstract

It is well-known that financial time series exhibits changing variance and this can have important consequences in formulating economic or financial decisions. In much recent evidence shows that volatility of financial assets is not constant, but rather that relatively volatile periods alternate with more tranquil ones. Thus, there are many opportunities to obtain forecasts of this time-varying risk. The paper presents the modelling volatility of the Kuala Lumpur Composite Index (KLCI) using SV and GARCH models. Thus, the aim of this study is to model the KLCI stock market using two models; Stochastic Volatility (SV) and Generalized Auto-Regressive Conditional Heteroscedasticity (GARCH). This study employs an SV model with Bayesian approach and Markov Chain Monte Carlo (MCMC) sampler; and GARCH model with MLE estimator. The best model will be used to forecast the future volatility of stock returns. The study involves 971 daily observations of KLCI Closing price index, from 2 January 2008 to 10 November 2016, excluding public holidays. SV model is found to be the best based on the lowest RMSE and MAE values.

Analytics of stock market prices based on machine learning algorithms

“…Though so there are other studies which have used combination of words as the feature set [22][23], and this representation is hardly found in stock market financial news. This effort in text mining have been employed to enhance the relevance and accuracy of results [24][25][26][27][28].…”

Forecasting rupiah exchange rate with learning vector quantization neural network

“…Therefore, the risk of failure can be minimized and profit opportunities can be optimized. There are several methods that can be used in analyzing and forecasting [5][6][7][8][9][10][11][12][13][14][15], which are classified into statistical techniques and artificial neural networks. Each of these categories has a lot of techniques and algorithms that can be chosen according to the purpose of data processing.…”

Improving Graph-based methods for computing qualitative properties of markov decision processes

“…Because of the stochastic behaviors of many computer systems, probabilistic structures are more useful for modeling such systems [4][5][6]. Markov chains and Markov decision processes (MDPs) are wellknown structures for modelling stochastic systems and are widely used in artificial intelligence, economy, operations research and software engineering [7][8][9].…”