Research Paper

Hypothesis on Stocks In Indian Oil Trading Using Big Data Analytics

In this paper, I present a robust approach to analyzing Indian oil trading stocks using big data analytics, with a focus on predicting profits based on real-time data from Yahoo Finance API. Leveraging the Cloudera and Hadoop framework, this research explores the potential of machine learning algorithms to forecast stock prices and optimize trading strategies.

Big data analytics holds immense potential across various industries, including finance, for precise forecasting and analysis of large datasets. This paper aims to harness this potential by examining Indian oil trading stocks and their impact on the financial market. By utilizing advanced analytics techniques, we seek to identify profitable trading opportunities and enhance decision-making processes for traders and investors.

The Hadoop framework serves as the cornerstone of our analysis, providing a distributed computing environment for processing large datasets efficiently. Key components of the Hadoop ecosystem, including the Hadoop Distributed File System (HDFS) and MapReduce, are utilized to manage and process stock market data effectively.

Our methodology involves five key steps: Data Acquisition and Characterization, Data Transfer, Storage, Pre-processing, and Machine Learning. We leverage Flume for data transfer, HDFS for storage, and PySpark for pre-processing and machine learning tasks. This pipeline enables us to extract insights from raw data and develop predictive models for stock price forecasting.

Through regression-based learning models, we analyze historical stock market data and evaluate performance metrics such as R-squared value and Mean Average Error. Our findings indicate potential correlations between Indian oil stocks and other market indices, providing valuable insights for traders and investors.

All In All, To sum up, this research demonstrates the efficacy of big data analytics in analyzing Indian oil trading stocks and forecasting market trends. Moving forward, we aim to automate analysis processes and explore advanced machine learning techniques to further enhance predictive accuracy.