Market Data Analysis by Using Support Vector Machine Learning Technique

  • Raghavendra ReddyEmail author
  • Gopal K. Shyam
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 28)


Stock market has been the goal of numerous market analyses which proves to be a challenge to characterize and appreciate the trends. This paper proposes a system of stock price trend prediction. It utilizes a supervised approach to cut raw transaction data of each stock into many products with a predefined value and classifies them into four main classes (open, high, low and close) according to their close prices. It contributes to analysis for market stock data classification that helps to study data in terms of stock rates where the polarity is often found to be highly unstructured. Once the data is preprocessed, then extraction of the feature from the dataset, which is meaningful, is known as feature vector. Then, the selected feature vector list is applied to the machine learning-based classification technique such as support vector machine (SVM) to predict the stock market data. The proposed method is evaluated on two publicly available markets to illustrate its effectiveness. Finally, the performance of the classifier is measured in terms of prediction accuracy.


Data cleaning Term Frequency–Inverse document frequency (tf-idf) Extraction technique Support vector machine (SVM) 


  1. 1.
    Rizvi SAR, Dewandaru G, Bacha OI, Masih M (2014) An analysis of stock market efficiency: developed vs Islamic stock markets using MF-DFA. Phys A: Stat Mech Appl 407:86–99 (Elsevier)CrossRefGoogle Scholar
  2. 2.
    Patel J, Shah S, Thakkar P, Kotecha K (2015) Predicting stock market index using fusion of machine learning techniques. Expert Syst Appl 42(4):2162–2172 (Elsevier)CrossRefGoogle Scholar
  3. 3.
    Gautam G, Yadav D (2014) Sentiment analysis of twitter data using machine learning approaches and semantic analysis. In: Contemporary Computing (IC3), IEEE, pp 437–442Google Scholar
  4. 4.
    Wu X, Zhu X, Wu G-Q, Ding W (2014) Data mining with big data. IEEE Trans Knowl Data Eng 26(1):97–107Google Scholar
  5. 5.
    Maldonado S, Montoya R, Weber R (2015) Advanced conjoint analysis using feature selection via support vector machines. Eur J Oper Res 241(2):564–574 (Elsevier)CrossRefGoogle Scholar
  6. 6.
    Da Silva, Nadia FF, Hruschka ER, Hruschka ER (2014) Tweet sentiment analysis with classifier ensembles. Decis Support Syst 66:170–179Google Scholar
  7. 7.
    Anjaria M, Guddeti RMR (2014) Influence factor based opinion mining of twitter data using supervised learning. In: Communication Systems and Networks (COMSNETS), IEEE, pp 1–8Google Scholar
  8. 8.
    Liu M, Yang J (2012) An improvement of TFIDF weighting in text categorization. In: International proceedings of computer science and information technology, pp 44–47Google Scholar
  9. 9.
    Ramos J (2003) Using tf-idf to determine word relevance in document queries. In: Proceedings of the first instructional conference on machine learning, vol 242, pp 133–142Google Scholar
  10. 10.
    Yi J, Yang G, Wan J (2016) Category discrimination based feature selection algorithm in Chinese text classification. J Inf Sci Eng 32(5):1145–1159Google Scholar
  11. 11.
    Barnett A, Santokhi J, Simpson M, Smart NP, Stainton-Bygrave C, Vivek S, Waller (2017) Image classification using non-linear support vector machines on encrypted data. In: IACR, p 857Google Scholar
  12. 12.
    Bhavsar H, Panchal MH (2012) A review on support vector machine for data classification. Int J Adv Res Comput Eng Technol (IJARCET) 1(10):185Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of C and ITREVA UniversityBangaloreIndia

Personalised recommendations