Predicting stock market index using fusion of machine learning techniques

Patel, Jigar; Shah, Sahil; Thakkar, Priyank; Kotecha, Ketan

doi:10.1016/j.eswa.2014.10.031

Cited by 443 publications

(210 citation statements)

References 16 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…Namun, perubahan pada faktor-faktor mikroekonomi menyebaban ketidakpastian harga saham sehingga dibutuhkan prediksi untuk melihat pergerakan pasar saham dimasa depan [2].…”

Section: Pendahuluanunclassified

“…Parameter hari ke-t digunakan sebagai variabel input untuk memprediksi harga penutup hari ke-t+n. Namun, jika nilai n bertambah maka prediksi akan berdasarkan niai parameter input yang bertambah tua sehingga hasil prediksi tidak cukup akurat (Patel, et al, 2015). Berdasarkan permasalahan tersebut, penelitian dilakukan dengan dua tahap untuk mengurangi tingkat kesalahan.…”

Section: Pendahuluanunclassified

“…Selain itu indikator -indikator tersebut sudah pernah dikasi oleh Jigal Patel dan Yakup Kara. Mereka menggunakan indikator analisa teknis untuk memprediksi pergerakan harga saham CNX Nifty dan SP Bombay Stock Exchange [2,3]. Tabel 1 adalah indikator (fitur) yang digunakan untuk memprediksi indeks harga saham.…”

Section: Metode Penelitian a Indikator Analisa Teknisunclassified

See 2 more Smart Citations

Prediksi Indeks Harga Saham dengan Metode Gabungan Support Vector Regression dan Jaringan Syaraf Tiruan

Siahaan

2017

IndoJC

View full text Add to dashboard Cite

The stock price has changed rapidly over time . The movement of the stock price index is the benchmark for the investors to make a decision when the stock should be sold or retained . So we need a model that can predict stock price index to monitor the movement and help investors in making decisions . This paper proposes two stage fusion approach for predicting the movement of stock prices involving Support Vector Regression (SVR) in the first stage and Artificial Neural Network (ANN) in the second stage . In this paper Genetic Algorithm will be used to identify the optimal solution of choosing best parameter of SVR . The predictions are made for 1 , 3 , 5 , 7 , 10 , 15 , and 30 days in advance. From a series of experiments, it can be concluded SVR -JST ( SVR optimized GA ) gives the error rate is smaller than the ANN model. Keywords:Artificial Neural Network, Genetic Algorithm, Hybrid Models, Predict, Stock Price, Supper Vector Regression, AbstrakHarga suatu saham berubah secara cepat dari waktu ke waktu. Pergerakan indeks harga saham menjadi tolak ukur para pemilik saham untuk membuat keputusan kapan sebaiknya saham dibeli, dijual atau dipertahankan. Untuk itu diperlukan suatu model yang dapat memprediksi indeks harga saham untuk memantau pergerakan tersebut dan membantu para pemilikk saham dalam mengambil keputusan. Penelitian ini mengusulkan metode untuk memprediksi pergerakan harga saham dengan menggunakan metode gabungan Support Vector Regression (SVR) pada tahap dan Jaringan Syaraf Tiruan (JST) pada tahap kedua. Pada penelitian ini, Algoritma Genetika atau Genetic Algorithm (GA) akan digunakan untuk melakukukan optimasi parameter SVR. Prediksi dibuat untuk 1, 3, 5, 7, 10, 15, dan 30 hari kedepan. Dari serangkaian uji coba yang dilakukan, SVR-JST (SVR dioptimasi GA) memberikan tingkat kesalahan lebih kecil dibandingkan dengan metode JST.

show abstract

“…Namun, perubahan pada faktor-faktor mikroekonomi menyebaban ketidakpastian harga saham sehingga dibutuhkan prediksi untuk melihat pergerakan pasar saham dimasa depan [2].…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Prediksi Indeks Harga Saham dengan Metode Gabungan Support Vector Regression dan Jaringan Syaraf Tiruan

Siahaan

2017

IndoJC

View full text Add to dashboard Cite

show abstract

“…Many researchers Meesad and Rasel (2013); Nametala et al (2016); Persio and Honchar (2016); Patel et al (2015); Pimenta et al (2014) have worked towards the improvement of already existing predictors. Many of these studies are based on recent machine learning techniques, such as Support Vector Machines (SVM) (Vapnik;1995), Arti cial Neural Networks (ANNs) (McCulloch and Pitts;1943) and Genetic Programming (GP) (Koza;1992).…”

Section: Introductionmentioning

confidence: 99%

Hybrid deep learning approach for financial time series classification

Assis¹,

Machado²,

Pereira³

et al. 2018

RBCA

View full text Add to dashboard Cite

This paper proposes a combined approach of two machine learning techniques for nancial time series classi cation. Boltzmann Restricted Machines (RBM) were used as the latent features extractor and Support Vector Machines (SVM) as the classi er. Tests were performed with real data of ve assets from Brazilian Stock Market. The results of the combined RBM + SVM techniques showed better performance when compared to the isolated SVM, which suggests that the proposed approach can be suitable for the considered application. ResumoEste trabalho propõe uma abordagem combinada de duas técnicas de aprendizado de máquina para classi cação de séries temporais nanceiras. Foram utilizadas Máquinas de Boltzmann Restritas (RBM) como o extrator de características latentes e Máquinas de Vetores de Suporte (SVM) como o classi cador. Cinco conjuntos de dados reais de ativos ou ações da BM&FBOVESPA foram usados para validação da abordagem. Em geral, as técnicas RBM + SVM combinadas apresentaram resultados superiores ao SVM isolado, con rmando o potencial da abordagem proposta.

show abstract

“…(Xu and Keelj, 2014) collected stock price charts and tweets from a social media platform used (Nassirtoussi et al, 2015) collected currency price and news data related to foreign exchange market (Forex). (Patel, 2015) collected stock price data from CNX Nifty, S&P BSE Sensex exchanges and finally (Roy et al, 2015) collected thirteen years of stock price charts data related to Goldman Sachs Group Inc. (Gong and Sun, 2009), (Patel, 2015), and (Roy et al, 2015) used only stock price as input to predict stock price or direction with accuracies varying between 83% and 90%. (Hagenau et al,06), (Kaya and Karsligil, 2010), (Lauren and Harlili, 2014), and (Nassirtoussi et al, 2015) are examples of papers which utilize news as well as stock prices to predict price direction with varying accuracies between 51% and 83%.…”

mentioning

confidence: 99%

Directional prediction of stock prices using breaking news on Twitter

Alostad

Davulcu

2017

WEB

View full text Add to dashboard Cite

Stock market news and investing tips are popular topics in Twitter. In this dissertation, first I utilize a 5-year financial news corpus comprising over 50,000 articles collected from the NASDAQ website matching the 30 stock symbols in Dow Jones Index (DJI) to train a directional stock price prediction system based on news content.Next, I proceed to show that information in articles indicated by breaking Tweet volumes leads to a statistically significant boost in the hourly directional prediction accuracies for the DJI stock prices mentioned in these articles. Secondly, I show that using document-level sentiment extraction does not yield a statistically significant boost in the directional predictive accuracies in the presence of other 1-gram keyword features. Thirdly I test the performance of the system on several time-frames and identify the 4 hour time-frame for both the price charts and for Tweet breakout detection as the best time-frame combination. Finally, I develop a set of price momentum based trade exit rules to cut losing trades early and to allow the winning trades run longer. I show that the Tweet volume breakout based trading system with the price momentum based exit rules not only improves the winning accuracy and the return on investment, but it also lowers the maximum drawdown and achieves the highest overall return over maximum drawdown.

show abstract

Predicting stock market index using fusion of machine learning techniques

Cited by 443 publications

References 16 publications

Prediksi Indeks Harga Saham dengan Metode Gabungan Support Vector Regression dan Jaringan Syaraf Tiruan

Prediksi Indeks Harga Saham dengan Metode Gabungan Support Vector Regression dan Jaringan Syaraf Tiruan

Hybrid deep learning approach for financial time series classification

Directional prediction of stock prices using breaking news on Twitter

Contact Info

Product

Resources

About