Total views : 231
Hybrid Model for Stock Trading System
Background/Objectives: Stock Trading is the action of buying or selling the products. In this complex habitat, generating the future trend is such a difficult process. Methods: Methods such as Sentiment survey, Technical survey and Trend based segmentation method are used in this system. The segmentation process, a hybrid model using Support Vector Regression and Naïve Bayes classification is used to extract the intensity levels of the gathered information. Findings: This is the application where the trading decisions can be automatically predicted to gain profit. Based on the reviews and ratings of a product from users, the system concludes whether to invest in that product or not. By using hybrid model, the predictive signals may be accurate. Decision for investors for investing in a better profit earning product is given by the system itself. The previous method uses the sentiments from the news articles and social networks, which is less reliable than getting the feedbacks from the users or the investors of that product. Applications: This framework may be used in real time applications such as trading activities, stock exchange in the stock market, etc.
Classification, Sentiment Survey, Stock Trading, Trend Based, Technical Survey.
- Yu L-C, Wu J-L, Chang P-C, Chu H-S. Using a contextual entropy model to expand emotion words and their intensity for the sentiment classification of stock market news.Knowledge based Systems. 2013 Mar; 41:89–97.
- Briza C, Naval PC. Stock trading system based on the multi-objective particles warm optimization of technical indicators on end-of-day market data. Applied Soft Computing. 2011 Jan; 11(1):1191–201.
- Yu LC, Wu JL, Chang PC, Chu HS. Using a contextual entropy model to expand emotion words and their intensity for the sentiment classification of stock market news.Knowledge Based Systems. 2013 Mar; 41:89–97.
- Karthika S, Sairam N. A Naïve Bayesian classifier for Educational Qualification. Indian Journal of Science and Technology. 2015 Jul; 8(16):1–5.
- Hafezi R, Shahrabi J, Hadavandi E. A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price. Applied Soft Computing.2015 Apr; 29:196–210.
- Rather AM, Agarwal A, Sastry VN. Recurrent neural network and a hybrid model for prediction of stock returns. Expert Systems with Applications. 2015 Apr; 42(6):3234–41.
- Patel J, Shah S, Thakkar P, Kotecha K. Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques. Expert Systems with Applications. 2015 Jan; 42(1):259–68.
- Wu J-L, Yu L-C, Chang P-C. An intelligent stock trading system using comprehensive features. Applied Soft Computing. 2014 Oct; 23:39–50.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.