Short Term Stock Movements with Big Data and Market Sentiments Analytics
Sneh kalra1, Sachin Gupta2, Jay Shankar Prasad3

1Sneh Kalra, Department of Computer Science, MVN University, Palwal, India.
2Dr. Sachin Gupta, Department of Computer Science, MVN University, Palwal, India.
3Dr. Jay Shankar Prasad, Department of Computer Science, Krishna Engineering College, Ghaziabad, India.

Manuscript received on 24 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 2305-2313 | Volume-8 Issue-9, July 2019 | Retrieval Number: I8474078919/19©BEIESP | DOI: 10.35940/ijitee.I8474.078919

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 (

Abstract: Machine Learning Techniques and Big Data analytics are two central points of data science. Big Data is important for organizations to gain insights into it and machine learning techniques are one of the substantial assets for analyzing a massive amount of data. In this paper, a framework has been proposed to improve the short term stock trend prediction accuracy using Logistic Regression model by means of qualitative and quantitative data. This paper makes a comprehensive survey of stock market trend prediction with the accumulation of various data sources by applying machine learning techniques and by using big data analytics approach. The model has been implemented in Big data Framework with Hadoop and Apache Spark. For qualitative data Tweets sentiments and news sentiments has been taken in to account and for quantitative data Google trends and historical data are considered. The proposed system has enhanced the prediction accuracy about 3-4 % in comparison to existing models by supplying Google trend as input data in addition to market sentiments and historical data. The implemented model can help the investors to take short term decisions to make money in the security market and the survey would help in finding the most effective resources which overly influence the stock prices.
Keywords: Google Trends, Logistic Regression, News Sentiments, Sentiment Analysis, Tweet Sentiments

Scope of the Article: Big Data