Forecasting Stock Index Movement using Support Vector Machines and Random Forest Method

Kumar, Manish; Thenmozhi, M.
March 2009
IIMB Management Review (Indian Institute of Management Bangalore;Mar2009, Vol. 21 Issue 1, p41
Academic Journal
The authors predict the direction of movement of the S&P CNX NIFTY Market Index using Support Vector Machines (SVM) and Random Forest Method (RFM). The performance of these techniques is benchmarked against the neural network, logit and discriminant models. The experimental analysis suggests that SVM outperforms RFM, which in turn outperforms neural network, discriminant analysis and logit. SVM models will be useful in evolving successful investment strategies while operating in the stock market.


Related Articles

  • Construction and Evaluation of Trading Systems: Warsaw Index Futures. Witkowska, Dorota; Marcinkiewicz, Edyta // International Advances in Economic Research;Feb2005, Vol. 11 Issue 1, p83 

    This paper presents and compares 15 trading systems constructed for the Warsaw Stock Exchange futures contracts. These trading systems are constructed applying technical analysis and artificial neural networks (ANN). The efficiency of constructed trading systems is measured by the profit, which...

  • Combination Neural Network and Financial Indices for Stock Price Prediction. Ramezanian, Mohamad Rahim; Shaverdi, Meysam; Faridi, Ako // Journal of Applied Sciences;2011, Vol. 11 Issue 19, p3429 

    As the stock market data is non-stationary and volatile the investors feel insecure during investing. In the recent years lots of attention has been devoted to the analysis and prediction of future values and trends of the financial market. In recent years, mathematical methodology has been used...

  • STOCK MARKET INDICES PREDICTIVE MODEL BASED ON ARTIFICIAL NEURAL NETWORKS. Sharma, Dinesh K.; Rababaah, Aaron R. // Allied Academies International Conference: Proceedings of the Ac;Apr2012, Vol. 16 Issue 1, p71 

    In this study, we propose a stock index predictive model based on Artificial Neural Networks/Multi-Layered Perceptron (ANN-MLP). In this approach, we model the input feature vectors to the MLP network as k-element vector of stock index close day entries. The classes of vectors are modeled as the...

  • MODELOS DE ALGORITMOS GENÉTICOS Y REDES NEURONALES EN LA PREDICCIÓN DE ÍNDICES BURSÁTILES ASIÁTICOS. Parisi, Antonino; Parisi, Franco; Díaz, David // Cuadernos de Economía;nov2006, Vol. 43 Issue 128, p251 

    This study analyzes the capacity of multivariated models constructed from genetic algorithms and artificial neural networks to predict the sign of the weekly variations of the Asian stock-market indexes Nikkei225, Hang Seng, Shanghai Composite, Seoul Composite and Taiwan Weighted. The results...

  • FORECASTING STOCK INDICES USING TWO DIFFERENT SIGNAL PROCESSING TECHNIQUES WITH BACK PROPAGATION NEURAL NETWORK. Rababaah, Aaron R.; Sharma, Dinesh K. // Allied Academies International Conference: Proceedings of the Ac;Fall2013, Vol. 17 Issue 2, p13 

    Back Propagation Artificial Neural Network (PBANN) has been used for stock market forecasting. However, predictions exhibit more variations when security markets are more volatile. We believe that by integrating a signal processing based filtering technique can improve predictability when data...

  • Stock Index Return Forecasting and Trading Strategy Using Hybrid ARIMA-Neural Network Model. Kumar, Manish; Thenmozhi, M. // International Journal of Financial Management;2012, Vol. 2 Issue 1, p1 

    This study presents the application and development of hybrid methodology that combines both ARIMA and Artificial Neural Network model to take advantage of the unique strengths of both linear and non-linear modeling to model and predict the stock market index returns. The performance of the...

  • FORECASTING OMX VILNIUS STOCK INDEX -- A NEURAL NETWORK APPROACH. Dzikevičius, Audrius; Stabužytė, Neringa // Business: Theory & Practice;2012, Vol. 13 Issue 4, p324 

    Predicting a stock market is a challenging task for every investor. Stock market contains difficult relations and its behavior is heavily forecasted. As the investment's profitability is directly related to the market's predictability, the need for more accurate and sophisticated forecasting...

  • Abnormal Effects of Weekdays on Forecasting Stock Prices by Neural Networks. Zor, Israfil; Guzel, Ali; Ozyurek, Hamide; Erdogan, Elif // European Journal of Social Sciences;Mar2012, Vol. 29 Issue 2-4, p244 

    Artificial Neural Network (ANN) is different from classical models because of its learning and generalizing capabilities. ANN can asses lacking or mistaken data and it can produce a solution for complex problems. Recently, ANN has been utilized especially for the resolution of financial problems...

  • Index Prediction in Tehran Stock Exchange Using Hybrid Model of Artificial Neural Networks and Genetic Algorithms. KARIMI, Farzad; DASTGIR, Mohsen; SHARIATI, Monireh // International Journal of Academic Research in Accounting, Financ;Jan2014, Vol. 4 Issue 1, p352 

    Nowadays, investment in the bource organizes the important part of country economy. So the prediction of stocks index is very important for stockholders to earn the highest return from their investment. The changes of stock market influence by several factors such as political, economical and...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics