ABSTRACT

In the past decades, there is an increasing interest in predicting markets among

economists, policymakers, academics and market makers. The objective of the
proposed work is to study and improve the supervised learning algorithms to
predict the stock price. Stock Market Analysis of stocks using data mining will be
useful for new investors to invest in stock market based on the various factors
considered by the software. Stock market includes daily activities like Sensex
calculation, exchange of shares. The exchange provides an efficient and
transparent market for trading in equity, debt instruments and derivatives. Our
aim is to create software that analyses previous stock data of certain companies,
with help of certain parameters that affect stock value. We are going to
implement these values in data mining algorithms and we will be able to decide
which algorithm gives the best result. This will also help us to determine the
values that particular stock will have in near future. We will determine the
patterns in data with help of machine learning algorithms.

v
 TABLE OF CONTENTS

Chapter TITLE Page

No. No.

ABSTRACT v
viii
LIST OF FIGURES
ix
LIST OF ABBREVIATIONS

1 INTRODUCTION 1

1.1 OVERVIEW 1

1.2 AIM AND OBJECTIVE 1

1.3 STOCK MARKET 1

1.4 MOTIVATON 2

3
2 LITERATURE REVIEW

3 REQUIREMENT ANALYSIS AND DESIGN 7

3.1 OBJECTIVES 7
3.2 EXISTING SYSTEM 9
3.3 PROPOSED SYSTEM 10

4 SYSTEM IMPLEMENTATION 11

4.1 INTRODUCTION 11
4.2 SYSTEM REQUIREMENTS 11
4.2.1 HARDWARE REQUIREMENTS 11
4.2.2 SOFTWARE REQUIREMENTS 11
4.3 ARCHITECTURE 12
4.4 MODULE DESCRIPTION 12
4.4.1 DATA PREPROCESSING 13
4.4.2 FEATURE SELECTION 13
4.4.3 BUILDING AND TRAINING MODEL 13
4.5 PYTHON TECHNOLOGY 13
4.5.1 PYTHON PLATFORM 23

vi
 4.5.2 PYTHON LIBRARY 14

RESULTS AND DISCUSSIONS 25

26
5.1 DEVCAMPER HOME PAGE
26
5.2 USER REGISTRATION PAGE
27
5.3 USER LOGIN PAGE
28
5.4 CREATE NEW BOOTCAMP PAGE
28
5.5 ALL BOOTCAMPS PAGE
5.6 MANAGE BOOTCAMP PAGE
5.7 ADD NEW COURSE PAGE
5.8 MANAGE COURSES PAGE
5.9 MANAGE ACCOUNTS PAGE

5 SUMMARY, RECOMMENDATIONS AND 29

CONCLUSION

5.1 SUMMARY 29
5.2 FURTHER WORKS 29
5.3 CONCLUSION 30

REFERENCES 31

APPENDIX 33

A SOURCE CODE 33
B PAPER WORK 46

vii
 LIST OF FIGURES

FIGURE No. FIGURE NAME PAGE No.

3.1 SOFTWARE ARCHITECTURE 8

3.2 USE CASE DIAGRAM 14
3.3 ADMINISTRATION AND INTERACTION 15
SUBSYSTEM
3.4 REGISTRATION SUBSYSTEM 16
3.5 SEQUENCE DIAGRAM 17
3.6 ACTIVITY DIAGRAM 18
5.1 HOME PAGE 23
5.2 REGISTRATION PAGE 24
5.3 LOGIN PAGE 24
5.4 CREATE BOOTCAMP PAGE 25
5.5 ALL BOOTCAMPS PAGE 26
5.6 MANAGE BOOTCAMP PAGE 26
5.7 ADD NEW COURSE PAGE 27
5.8 MANAGE COURSES PAGE 28
5.9 MANAGE ACCOUNT 28

viii
 LIST OF ABBREVIATIONS

API Application Programming Interface

CMS Content Management System
CSS Cascading Style Sheets
CRUD Create, Read, Update, Delete
GIF Graphics Interchange Format
GUI Graphical User Interface
HTML Hypertext Markup Language
MVC Model View Controller
OOAD Object Oriented Analysis and Design
RAM Random Access Memory
SQL Structured Query Language
UX User Experience

ix
 CHAPTER 1

INTRODUCTION

1.1 OVERVIEW

In recent times stock market predictions is gaining more attention, maybe due to the
fact that if the trend of the market is successfully predicted the investors may be
better guided. The profits gained by investing and trading in the stock market greatly
depends on the predictability. If there is a system that can consistently predict the
direction of the dynamic stock market will enable the users of the system to make
informed decisions. More over the predicted trends of the market will help the
regulators of the market in taking corrective measures.

1.2 AIM AND OBJECTIVE

The aim of the project is to examine a number of different forecasting techniques to

predict future stock returns based on past returns and numerical news indicators to
construct a portfolio of multiple stocks in order to diversify the risk. We do this by
applying supervised learning methods for stock price forecasting by interpreting the
seemingly chaotic market data.

1.3 STOCK MARKET

A stock market, equity market or share market is the aggregation of buyers and
sellers (a loose network of economic transactions, not a physical facility or discrete
entity) of stocks (also called shares), which represent ownership claims on
businesses; these may include securities listed on a public stock exchange as well
as those only traded privately. Examples of the latter include shares of private
companies which are sold to investors through equity crowd funding platforms. Stock
exchanges list shares of common equity as well as other security types, e.g.
corporate bonds and convertible bonds.
Stock price prediction is one of the most widely studied problem, attracting
researchers from many fields. The volatile nature of the stock market makes it really
difficult to apply simple time-series or regression techniques. Financial institutions
and active traders have created various proprietary models to beat the market for

1
themselves or their clients, but rarely did anyone achieve consistently higher than
the average returns on investment. The challenge of stock market price forecasting
is so appealing because an improvement of just a few points of percentage can
increase the profit by millions of dollars. This paper discusses the application of
Support Vector Machines and Linear Regression in detail along with the pros and
cons of the given methods. The paper introduces the parameters and variables
which can be used to recognize the patterns in stock prices which can be helpful in
future stock prediction and how boosting can be integrated with various other
machine learning algorithms to improve the accuracy of our prediction systems.

1.4 MOTIVATION

Stock price prediction is a classic and important problem. With a successful model
for stock prediction, we can gain insight about market behavior over time, spotting
trends that would otherwise not have been noticed. With the increasingly
computational power of the computer, machine learning will be an efficient method
to solve this problem.
Thus, our motivation is to design a public service incorporating historical data and
users predictions to make a stronger model that will benefit everyone.

2
 CHAPTER 2
LITERATURE SURVEY

1. Survey of stock market prediction using machine learning approach

Authors: Ashish Sharma ; Dinesh Bhuriya ; Upendra Singh
2017 International conference of Electronics, Communication and Aerospace
Technology (ICECA)

Stock market is basically nonlinear in nature and the research on stock market is
one of the most important issues in recent years. People invest in stock market
based on some prediction. For predict, the stock market prices people search such
methods and tools which will increase their profits, while minimize their risks.
Prediction plays a very important role in stock market business which is very
complicated and challenging process. Employing traditional methods like
fundamental and technical analysis may not ensure the reliability of the prediction.
To make predictions regression analysis is used mostly. In this paper we survey of
well-known efficient regression approach to predict the stock market price from stock
market data based. In future the results of multiple regression approach could be
improved using more number of variables.

2. Short-term prediction for opening price of stock market based on self-

adapting variant PSO-Elman neural network

Authors: Ze Zhang ; Yongjun Shen ; Guidong Zhang ; Yongqiang Song ; Yan

Zhu, 2017 8th IEEE International Conference on Software Engineering and
Service Science (ICSESS)

Stock price is one of intricate non-linear dynamic system. Typically, Elman neural
network is a local recurrent neural network, having one context layer that memorizes
the past states, which is quite fit for resolving time series issues. Given this, this
paper takes Elman network to predict the opening price of stock market. Considering
that Elman network is limited, this paper adopts self-adapting variant PSO algorithm
to optimize the weights and thresholds of network. Afterwards, the optimized data,
regarded as initial weight and threshold value, is given to Elman network for training,
accordingly the prediction model for opening price of stock market based on self-

3
adapting variant PSO-Elman network is formed. Finally, this paper verifies that
model by some stock prices, and compares with BP network and Elman network, so
as to draw the result that shows the precision and stability of this predication model
both are superior to the traditional neural network.

3. Combining of random forest estimates using LSboost for stock market

index prediction

Authors: Nonita Sharma ; Akanksha Juneja,2017 2nd International Conference

for Convergence in Technology (I2CT)
This research work emphases on the prediction of future stock market index values
based on historical data. The experimental evaluation is based on historical data of
10 years of two indices, namely, CNX Nifty and S&P Bombay Stock Exchange
(BSE) Sensex from Indian stock markets. The predictions are made for 1-10, 15, 30,
and 40 days in advance. This work proposes to combine the predictions/estimates of
the ensemble of trees in a Random Forest using LSboost (i.e. LS-RF). The
prediction performance of the proposed model is compared with that of well-known
Support Vector Regression. Technical indicators are selected as inputs to each of
the prediction models. The closing value of the stock price is the predicted variable.
Results show that the proposed scheme outperforms Support Vector Regression
and can be applied successfully for building predictive models for stock prices
prediction.

4. Using social media mining technology to assist in price prediction of

stock market

Authors: Yaojun Wang ; Yaoqing Wang,2016 IEEE International Conference on

Big Data Analysis (ICBDA)

Price prediction in stock market is considered to be one of the most difficult tasks,
because of the price dynamic. Previous study found that stock price volatility in a
short term is closely related to the market sentiment; especially for small-cap stocks.
This paper used the social media mining technology to quantitative evaluation
market segment, and in combination with other factors to predict the stock price
trend in short term. Experiment results show that by using social media mining
combined with other information, the stock prices prediction model can forecast

4
more accurate.

5. Stock market prediction using an improved training algorithm of neural

network

Authors: Mustain Billah ; Sajjad Waheed ; Abu Hanifa,2016 2nd International

Conference on Electrical, Computer & Telecommunication Engineering
(ICECTE)

Predicting closing stock price accurately is an challenging task. Computer aided

systems have been proved to be helpful tool for stock prediction such as Artificial
Neural Net-work(ANN), Adaptive Neuro Fuzzy Inference System (ANFIS) etc. Latest
research works prove that Adaptive Neuro Fuzzy Inference System shows better
results than Neural Network for stock prediction. In this paper, an improved
Levenberg Marquardt(LM) training algorithm of artificial neural network has been
proposed. Improved Levenberg Marquardt algorithm of neural network can predict
the possible day-end closing stock price with less memory and time needed,
provided previous historical stock market data of Dhaka Stock Exchange such as
opening price, highest price, lowest price, total share traded. Morever, improved LM
algorithm can predict day-end stock price with 53% less error than ANFIS and
traditional LM algorithm. It also requires 30% less time, 54% less memory than
traditional LM and 47% less time, 59% less memory than ANFIS.

6. Efficacy of News Sentiment for Stock Market Prediction

Authors: Sneh Kalra ; Jay Shankar Prasad,2019 International

Conference on Machine Learning, Big Data, Cloud and Parallel Computing
(COMITCon)

Stock Market trend prediction will always remain a challenging task due to stochastic
nature. The enormous amount of data generated by the news, blogs, reviews,
financial reports and social media are considered a treasure of knowledge for
researchers and investors. The present work focuses to observe fluctuations in stock
prices with respect to the relevant news articles of a company. In this paper, a daily
prediction model is proposed using historical data and news articles to predict the
Indian stock market movements. Classifier Naïve Bayes is used to categorize the

5
news text having negative or positive sentiment. The count of the positive and
negative sentiment of news articles for each day and variance of adjacent days
close price along with historical data is used for prediction purpose and an accuracy
ranging from 65.30 to 91.2 % achieved with various machine learning techniques.

7. Literature review on Artificial Neural Networks Techniques Application for

Stock Market Prediction and as Decision Support Tools

Authors: Muhammad Firdaus ; Swelandiah Endah Pratiwi ; Dionysia Kowanda ;

Anacostia Kowanda

This literature review is aiming to explore the use Artificial Neural Network (ANN)
techniques in the field of stock market prediction. Design: Content analysis research
technique. Data sources: Information retrieved from ProQuest electronic databases.
Review methods: Utilizing key terms and phrases associated with Artificial Neural
Network Stock Market Prediction from 2013-2018. Out of the 129 scholarly journal
reviewed, there are 4 stock market studies met the inclusion criteria. The analysis
and the evaluation includes 6 ANN derivatives techniques used to predict. Results:
Findings from the reviewed studies revealed that all studies shows consistency that
the accuracy rate of ANN stock market prediction is high. 2 Studies shows accuracy
above 90%, 2 studies shows accuracy above 50%. Conclusion: This study reveals
that the ability of ANN shows consistency of an accuracy rate of stock market
prediction. Four method in predicting stock market had an accuracy above 95%. The
highest accuracy achieved by using Signal Processing/Gaussian Zero-Phase Filter
(GZ-Filter) with 98.7% prediction accuracy.
2018 Third International Conference on Informatics and Computing (ICIC)

8. Stock Market Movement Prediction using LDA-Online Learning Model

Authors:Tanapon Tantisripreecha ; Nuanwan Soonthomphisaj, 2018 19th

IEEE/ACIS International Conference on Software Engineering, Artificial
Intelligence, Networking and Parallel/Distributed Computing (SNPD)

In this paper, an online learning method namely LDA-Online algorithm is proposed to

predict the stock movement. The feature set which are the opening price, the closing
price, the highest price and the lowest price are applied to fit the Linear Discriminant