Stock market prediction: Prediction of stocks using machine learning models.

Overview
The stock market is an important part of the economy of a country. The stock market plays a pivotal
role in the growth of the industry and commerce of the country that eventually affects the economy
of the country to a great extent. That is the reason that the government, industry and even the
central banks of the country keep a close watch on the happenings of the stock market. The stock
market is important from both the industry’s point of view as well as the investor’s point of view.

It’s more important to predict the stock market as it is not only providing the required funds for
boosting the business, but also providing a common place for stock trading.

stock price prediction has been at the focus for years since it can yield significant profits. Predicting
the stock market is not a simple task, mainly as a consequence of the close to the random-walk
behavior of a stock time series

In this project, we use Artificial Neural Network(ANN), which is a recent breakthrough in many areas.
In most cases, ANNs suffer from the over-fitting problem due to the large number of parameters to
fix, and the little prior user knowledge about the relevance of the inputs in the analyzed problem.
Also, Support vector machines (SVMs) had been developed as an alternative that avoids such
limitation

The proposed model is based on the study of historical data, technical indicators and optimizing
LS-SVM which is to be used in the prediction of daily stock prices

Inputs required for the project

 For implementing this project, we use a python’s pandas module to pull stock data.
 There are plenty of online sites by which we can get free access to historical data, one such
site we are using to get data is https://tinyurl.com/yc6rxeyv

Expected results
The results of the project are compared as follows-

 Out of all available data, 75% of data is used for training and 25% of data is used for testing
so that we can know the prediction variance as already values are present.

A Brief Survey - Different Techniques in Stocks Prediction

Prediction methodologies fall into three broad categories which can (and often do) overlap. They are
fundamental analysis, technical analysis (charting) and technological methods.

Fundamental analysis: Fundamental analysis is built on the belief that human society needs capital
to make progress and if a company operates well, it should be rewarded with additional capital and
result in a surge in stock price. Fundamental analysis is widely used by fund managers as it is the
most reasonable, objective and made from publicly available information like financial statement
analysis. Many performance ratios are created that aid the fundamental analyst with assessing the
validity of a stock, such as the price-earnings ratio.
Technical analysis: Technical analysts or chartists are not concerned with any of the company's
fundamentals. They seek to determine the future price of a stock based solely on the (potential)
trends of the past price (a form of time series analysis). Numerous patterns are employed such as
the head and shoulders or cup and saucer. Alongside the patterns, techniques are used such as the
exponential moving average (EMA). Candle stick patterns, believed to have been first developed by
Japanese rice merchants, are nowadays widely used by technical analysts.

Project Requirements
Hardware Used: A laptop with 4GB ram and 50mb cache memory.

Software Used: pycharm with help of libraries.

Algorithms and Tools used

The following are the algorithms, tools, and techniques used to handle the entire project.

Algorithms: LS-SVM-PSO, LS-SVM, and ANN

Tools: Pycharm

Project Plan
Stage-1 Gathering Requirements and Literature Survey 1 week
Stage-2 High Level and Detailed Design 4 weeks
Stage-3 Coding 3 weeks
Stage-4 Result Analysis 2 weeks
Stage-5 Documentation 2 weeks

Bibliography

Osman Hegazy, Omar S. Soliman and Mustafa Abdul Salam. (Faculty of Computers and Informatics,
Cairo University, Egypt and Higher Technological Institute (H.T.I)), 10th of Ramadan City, Egypt

A Machine Learning Model for Stock Market Prediction. Available from:

https://www.researchgate.net/publication/259240183_A_Machine_Learning_Model_for_Stock_Ma
rket_Prediction [accessed Oct 10 2018].