You are on page 1of 19

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

SCHOOL OF COMPUTING
1156CS601- MINOR PROJECT
WINTER SEMESTER(2022-2023)
REVIEW - I

“STOCK MARKET ANALYSIS USING SUPERVISED MACHINE


LEARNING”

SUPERVISED BY PRESENTED BY

Mr. K.Suresh 1. D. Rajadhanasai (16876)(20UECS0263)


Assistant Professor 2. S. Venkateswarlu (12319)(20UECS0898)
3. G. Balaji (17327)(20UECS0348)

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023


AGENDA

• ABSTRACT
• OBJECTIVE
• INTRODUCTION
• LITERATURE REVIEW
• DESIGN AND METHODOLOGIES
• IMPLEMENTATION
• CONCLUSION

• REFERENCES

BATCH NO: 261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 2


ABSTRACT

 Stock prices are correlated  within the nature of market;


hence it will be difficult to predict the costs.
 The proposed algorithm using the market data to predict the
share price using machine learning techniques like recurrent
neural network named as long short-term memory, in that
process weights are corrected for each data points using
stochastic gradient descent.
 The system will provide accurate outcomes in comparison to
currently available stock price predictor algorithms.
 The network is training and evaluated with various sizes of
input data to urge the graphical outcomes
BATCH NO: 261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 3
OBJECTIVES

Aim of the Project:


The main aim of the project is to improve and develop a
system for predicting future prices in financial markets with
higher accuracy using machine learning methods. 

Scope of the Project:


The scope of the project is to predict the stock market
shares .The future stock prices are predicted by using
previous stock market prices data.

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 4


INTRODUCTION

This model considers the historical equity share price of a


company price and applies RNN (Recurrent) techniques called
long short-term memory (LSTM).
The proposed approach considers available historic data in
share, and it provides prediction on a particular feature.
The features of shares are opening price, day high ,day low,
previous day o price , close price , date of trading, total trade
quantity and turnover.

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 5


LITERATURE REVIEW

1. “A Supervised Machine Learning Algorithm for Stock Price


Forecasting” by Manisha Gupta and Vishal Bhatnagar (2017)
 In this study, the authors propose a supervised machine
learning algorithm for stock price forecasting based on a
combination of technical analysis indicators and fundamental
analysis variables.
 They use an ensemble learning approach that combines
multiple regression models to improve the accuracy of their
predictions
 Their results show that their proposed algorithm outperforms
traditional statistical models like ARIMA and GARCH.
BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 6
LITERATURE REVIEW

2.“Stock price prediction using machine learning algorithms” by


Ravindra Agrawal and Deepti Agrawal (2018)

 In this study, the authors explore the use of machine learning


algorithms like Linear Regression, Decision Tree, and
Random Forest for stock price prediction.
 They use technical analysis indicators like moving average,
Bollinger Bands, and Relative Strength Index (RSI) as input
features
 Their results show that Random Forest outperforms the other
algorithms in terms of accuracy.

BATCH NO: 261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 7


LITERATURE REVIEW

3.“Stock Price Prediction Using Support Vector Regression on


Daily and Weekly Data” by Christos Laskaris and Antonis
Maronidis (2018)

 In this study, the authors propose a Support Vector


Regression (SVR) model for stock price prediction based on
daily and weekly data.
 They use technical analysis indicators like moving
averages, RSI, and MACD as input features.
 Their results show that their proposed SVR model
outperforms traditional statistical models like ARIMA and
GARCH.
BATCH NO: 261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 8
LITERATURE REVIEW

4.“Stock Price Prediction using Deep Learning Techniques” by


Divya Agrawal and Deepti Gupta (2018)

 In this study, the authors explore the use of deep learning


techniques like Convolutional Neural Networks (CNN) and
Long Short-Term Memory (LSTM) for stock price
prediction.
 They use technical analysis indicators like moving average
and RSI as input features.
 Their results show that their proposed LSTM model
outperforms traditional machine learning algorithms like
Random Forest and Gradient Boosting in terms of accuracy.
BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 9
DESIGN AND METHOLOGIES

MODULE 1:

  Data Collection
Preprocessing
Feature selection

MODULE 2:

Train the Model


       Testing the input data.

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 10


MODULE:1

 Data Collection and preprocessing

Step:1 Collection of data

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 11


Step 2: Processing of data

Step 3: Implementation of algoritham

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 12


IMPLEMENTATION

Architecture Diagram
Data –Flow Diagram
E-R Diagram

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 13


ARCHITECTURE DIAGRAM

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023


14
DATA FLOW DIAGRAM
COLLECTION OF
DATA

PRE- PROCESS THE

DATA

NORMALIZE THE

DATA

 APPLY MACHINE
LEARNNING
ALGORTHMS

TRAINING THE
DATA

TESTING THE DATA

GET THE OUTPUT

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 15


E-R DIAGRAM

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 16


CONCLUSION

 This study  focuses on the share prices of the market in


future which can get loss in shares or gain in shares.
 Prediction could be more reliable if the model trains a greater
number of datasets using LSTM modules.
 Moreover , in the case of prediction of various shares , there
may be some scope of specific business analysis. we
can study the different pattern of the share price of
different sectors and can analyze a graph with more different
time span to fine tune the accuracy. 

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 17


REFERENCES

Menon A, singh s, parekh h. A review of stock market prediction using


neural networks.2019 IEEE int conf syst compute autom networking,
ICSCAN2019.publishedonline2019:16.Dol:10.1109/ICSCAN.2019.887
8682.
Bruno "Machine learning techniques applied to financial market
prediction" vol.8 No.4(2019).Articles,pages 97-116.
Google Developers, Oct 2018, “Descending into ML: Linear
Regression”,GoogleLLC,https://developers.google.com/machine-
learning/crash-course/descending-into-ml/linear-regression

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 18


THANK YOU

BATCH NO:261 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING 27/03/2023 19

You might also like