Optimized Feature Extraction Based Artificial Intelligence Technique for Empirical Analysis of Stock Market Data
Vani Kansal1, Rakesh Kumar2

1Vani Kansal, Department of Computer Science, NITTTR, Chandigarh, India.
2Rakesh Kumar, Department of Computer Science, NITTTR, Chandigarh, India.

Manuscript received on 04 July 2019 | Revised Manuscript received on 08 July 2019 | Manuscript published on 30 August 2019 | PP: 527-532 | Volume-8 Issue-10, August 2019 | Retrieval Number: J88370881019/2019©BEIESP | DOI: 10.35940/ijitee.J8837.0881019
Open Access | Ethics and  Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Stock market forecasting is considered as a challenging task in financial time series forecasting. The core idea of a successful stock market forecast is to get the best results with the least amount of input data required and the least complex stock market model. So in this paper, to achieve these goals, this paper proposes a new algorithm Cuckoo Neural for Financial Market (CN_FM), which integrates Cuckoo Search (CS) with a Feed forward back propagation Neural Network (FFBPNN) and build a stock price forecasting proficient system. This research follows some basic steps to design a model for sentiment analysis from Stock market dataset and firstly data is pre-processed to remove the unwanted text. In pre-processing steps the techniques such as normalization, punctuation, stop word removal and tokenization are applied. The extracted features are optimized using CS and in turns used to train the FFBPNN. The results obtained from experiments in the stock market show that the proposed method can reduce the dimensions and produce accurate results for emotion-based text categorization with an accuracy of 99.44%.
Keywords: Sentiment Analysis, Stock market, Cuckoo Search, Feed forward back propagation Neural Network
Scope of the Article: Artificial Intelligence