Title:Big Data Analysis for Trend Recognition Using Machine Learning Techniques
VOLUME: 10 ISSUE: 4
Author(s):Cerene Mariam Abraham*, Mannathazhathu Sudheep Elayidom and Thankappan Santhanakrishnan
Affiliation:Division of Computer Science and Engineering, Cochin University of Science and Technology, Kerala, Division of Computer Science and Engineering, Cochin University of Science and Technology, Kerala, Defence Research and Development Organization, Naval Physical and Oceanographic Laboratory, Kerala
Keywords:Big data, derivative market, open interest, deliverable quantity, ARIMA, temporal data mining, machine learning.
Abstract:
Background: Machine learning is one of the most popular research areas today. It relates
closely to the field of data mining, which extracts information and trends from large datasets.
Aims: The objective of this paper is to (a) illustrate big data analytics for the Indian derivative
market and (b) identify trends in the data.
Methods: Based on input from experts in the equity domain, the data are verified statistically using
data mining techniques. Specifically, ten years of daily derivative data is used for training and
testing purposes. The methods that are adopted for this research work include model generation
using ARIMA, Hadoop framework which comprises mapping and reducing for big data analysis.
Results: The results of this work are the observation of a trend that indicates the rise and fall of price
in derivatives , generation of time-series similarity graph and plotting of frequency of temporal data.
Conclusion: Big data analytics is an underexplored topic in the Indian derivative market and the
results from this paper can be used by investors to earn both short-term and long-term benefits.
