Different Stock Market Models Using Support Vector Machines

Abstract

Abstract-The goal of this research is to analyse the different results that can be achieved using Support Vector Machines to forecast the weekly change movement of the different simulated markets. The data cover 3000 daily close for each simulated market. The main characteristic of these markets are: high volatility, bearish movement, bullish movement and low volatility. The inputs of the SVM are the Relative Strength Index (RSI) and the Moving Average Convergence Divergence (MACD). SVM-KM is used by Matlab in order to design the algorithm. The outputs of the SVM are the degree of set membership and the market movement (bullish or bearish).The configuration for the SVM shows that results are better in high volatility markets or low volatility markets than trend markets.Index Terms-Support vector machines, quantitative trading, stock market models, technical analysis. I. INTRODUCTIONDifferent market situations such us high volatility, low volatility, bullish movements and bearish movements are shown in this paper. The SVM helps to investor in the quantitative decision making choosing a weekly forecast (bullish or bearish). We analyse in which market situation the SVM can achieve the best results.The rest of the paper is structured as follows. Section II, the literature review of SVM is presented. Section III explains the design of the trading rule. The results are shown in section IV. Finally section V provides some concluding remarks. with extremely promising results. In this study, we apply SVM in the classification way. II. LITERATURE REVIEW OF SVM III. TRADING RULEThe design of the trading rule is presented in this section. A. Simulated MarketsThe simulated markets are 4 in this experiment. An especially characteristic has been chosen in order to differentiate each series. We want to analyse how SVM help to investors in bullish trend (Fig. 2), bearish trend (Fig. 3), high volatility (Fig. 4) and low volatility (Fig. 5). B. InputsThe inputs of the SVM are the quantitative analysis indicators RSI and MACD. In [10] it is explained that RSI gets good profits in blue chips and Momentum indicator gets good profits in Small Caps, MACD and Stochastic indicators have been analysed over the Spanish Continuous Market too.  Relative Strength Index (RSI)It was designed by [11]. A brief explanation of this indicator is shown below in equation 1. If more details are needed it can be seen in [11].The RSI is an oscillator that shows the strength or speed of the asset price by means of the comparison of the individual upward or downward movements of the consecutive closing prices.For each day, an upward change (U) or downward change (D) is calculated. "Up days" are characterised by the daily close St being higher than the close of previous day St-1 (Ut = St -St-1, Dt = 0). "Down days" are characterised by the daily close being lower than the close of the previous day (Ut = 0, Dt = St-1 -St).The average Ut and Dt are calculated using an n-period exponential moving average (EMAn).Relative Strength Index at time t (RSIt) is t...

Applying the Support Vector Machine for Testing Pricing Inefficiency on the Stock Exchange of Mauritius

“…Model inputs for the SVM are as observed in literature (Kim, 2003;Ni et al, 2011;Rosillo et al, 2013 andRosillo et al, 2014) and are as described in table 1 below. These inputs are based on strategies adopted by market traders and which try to depict trends in the performance of a stock.…”

“…However, techniques in revealing patterns in past price information have evolved over time. While the prices may not be good indicators of future prices, market traders now use more complex methodologies to study movements and deviations so as to adopt different strategies on stock markets for short selling and arbitrage generally (Kim, 2003;Ni, Ni & Gao, 2011;Rosillo, Giner, Puente, &Ponte, 2013 andDe la Fuente, 2014). The use of some of these techniques, has been proposed in this study as a better way in studying the predictability power of trends from past stock returns rather than just the returns themselves.…”