IR@AIKTC-KRRC

Acknowledgements

I would like to take the opportunity to express my sincere thanks to my guide

Prof.Javed Shaikh, Assistant Professor, Department of Computer Engineering, AIKTC,
School of Engineering, Panvel for his invaluable support and guidance throughout
my project research work. Without his kind guidance & support this was not possi-
ble.

I am grateful to him/her for his timely feedback which helped me track and schedule
the process effectively. His/her time, ideas and encouragement that he gave is help
me to complete my project efficiently.

We would like to express deepest appreciation towards DR. ABDUL RAZAK

HONNUTAGI, Director, AIKTC, Navi Mumbai, Prof. TABREZ KHAN, Head of
Department of Computer Engineering and Prof. JAVED SHAIKH, Project Coordi-
nator whose invaluable guidance supported us in completing this project.

At last we must express our sincere heartfelt gratitude to all the staff members of
Computer Engineering Department who helped me directly or indirectly during this
course of work.

RAAFIL RIZWAN DESHMUKH

HUZEFA MUNAF SURME
SHAIKH TANVEER ALAM
AKHTAR ALI

ir.aiktclibrary.org
IR@AIKTC-KRRC

ABSTRACT

We analyse existing and new methods of stock market prediction. We take three
different approaches at the problem: Fundamental analysis, Technical Analysis, and
the application of Machine Learning. We find evidence in support of the weak form
of the Efficient Market Hypothesis, that the historic price does not contain useful
information but out of sample data may be predictive. We show that Fundamental
Analysis and Machine Learning could be used to guide an investor’s decisions. We
demonstrate a common flaw in Technical Analysis methodology and show that it
produces limited useful information.

In the finance world stock trading is one of the most important activities. Stock
market predic-tion is an act of trying to determine the future value of a stock other
financial instrument tradedon a financial exchange.The technical and fundamental
or the time series analysis is used bythe most of the stockbrokers while making the
stock predictions. The programming languageis used to predict the stock market us-
ing machine learning is Python. In our project we proposea Machine Learning (ML)
approach that will be trained from the available stocks data and gainintelligence and
then uses the acquired knowledge for an accurate prediction. In this contextstudy
uses a machine learning technique called Support Vector Machine (SVM) or Long
ShortTerm-Memory (LSTM) to predict stock prices.

Keywords: Mechine Learning, Data Mining, Training set, Training Data, Au-
tomated System, pattern Recognition, Deep learning, Knowledgeextraction, Data
preprocess- ing, knowledge extraction, Web mod-ule,Artificial Intelligence.

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

Chapter 4

Software Requirements Specification

1. Overall Description
1. Product Perspective
The stock market is basically an aggregation of various buyers and sellers of
stock. A stock (also known as shares more commonly) in general represents
ownership claims on business by a particular individual or a group of people. The
attempt to determine the future value of the stock market is known as a stock market
prediction. The prediction is expected to be robust, accurate and efficient. The
system will be working according to the real-life scenarios and should be well
suited to real-world settings. The system is also expected to take into account all the
variables that might affect the stock’s value and performance. There are various
methods and ways of implementing the prediction system like Fundamental
Analysis, Technical Analysis, Machine Learning, Market Mimicry, and Time series
aspect structuring. With the advancement of the digital era, the prediction has
moved up into the technological realm. The most prominent and promising
technique involves the use of Artificial Neural Networks, Recurrent Neural
Networks, that is basically the implementation of machine learning.slope of linear
model applied on tick data of the respective hour, which gives an idea about the
trend during the last hour

4.1.2 Product Features

a. Maximum price received during the selected hour.
b. Minimum price received during the selected hour.
c. Average price received during the selected hour.
d. Standard deviation of prices received during the selected hour
e. logarithmic difference between average prices of two consecutive hours.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 12

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

f. slope of linear model applied on tick data of the respective hour, which gives an
idea about the trend during the last hour

3. User Classes and Characteristics

This project is a share market software.This can be used by normal people as well
as by agents to identify the market high and low prices depend on the company they
want to lookout.It is a good software for beginner to identify the market value as per
it’s choice.

4. Operating Environment
a. Jupyter Notebook
b. Python 3.0
c. LSTM
d. Pandas
e. Datasets

4.1.5 Design and Implementation Constraints

This system focuses one of the features at time. It is not able to provide two or
more services at a time.At any instant only one of the services is accessible

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 13

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

4.2 System Features

It is used to predict the stock price based on the company which we choose to
be predicted. Using the previous data the software is used to predict the future
prediction of a selected company. Data is coverted into graph to let us know what
will be high and low price the stock can go for the particular day, month or year.

1. System Feature
Using the text data to get converted into graph form to easily identify the predicted
stock of a company.

Description and Priority

Well it is the most important feature in our prediction software.

This helps in extraction of text from the background.
Our software read the previous data and do some operations with the data to identify
the predicted price of a company stock.

Stimulus/Response Sequences

Stimulus:User choose the particular company stock. Responses:Software uses the

training testing results to identify the further process. Responses:After testing train-
ing the data alogrithm is used to predict the data.

Functional Requirements

REQ-1: Covertion Of Text Data to Graph.

REQ-2: Training Testing the data.

2. User Interfaces
User Interface Design focuses on anticipating what users might need to do and en-
suring that the interface has elements that are easy to access, understand, and use to
facilitate those actions.

3. Hardware Interfaces
Depending on executing the system our hardware should be well maintained and
able to execute the program in a well upgraded hardware.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 14

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

4.2.4 Software Interfaces

LSTM models are powerful, especially for retaining a long-term memory, by design.
in a pure machine learning interest. In my opinion, the model has observed certain
patterns in the data, thus giving it the ability to correctly predict the stock
movements most of the time.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 15

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

3. Nonfunctional Requirements
1. Performance Requirements
Performance of overall system is very efficient and well optimize. From the time
taken to capture and process it everything is well organized.While processing the
stock price it will take time depending on the hardware we will be executing this on.

2. Safety Requirements
This system does not contain any critical data. Still it provide. The databases that
are accessed are locally executed.In case of any updates in libraries used can lead to
the failure in systems.

3. Security Requirements
All the libraries used are certified and standard. As it is a demo based
program .After that is released.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 16

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

Chapter 5

System Design

1. System Requirements Definition

System requirement definitions specify [1] what the system should do, its functional-
ity and its essential and desirable system properties. The techniques applied to elicit
and collect information in order to create system specifications and requirement def-
initions involve consultations, interviews, requirements workshop with customers
and end users. The objective of the requirements definition phase is to derive the
two types of requirement:

1. Functional requirements
They define the basic functions that the system must provide and focus on the needs
and goals of the end users.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 17

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

Use-case Diagram

A use case diagram at its simplest is a representation of a user’s interaction with

the system that shows the relationship between the user and the different use cases
in which the user is involved.In our system User will interact with use cases like
Capture Image,Audio Input,Save text,Retrieve Text,Audio output.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 18

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

Data-flow Diagram

A data-flow diagram is a way of representing a flow of a data of a process or a

system. The DFD also provides information about the outputs and inputs of each
entity and the process itself.Given below is Level 0 Level 1 and Level 2 DFD of
system.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 19

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 20

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

5.1.2 System requirements (non-functional requirements)

These are non-functional system properties such as availability, performance and
safety etc. They define functions of a system, services and operational constraints in
detail.

5.2 System Architecture Design

A system architecture is the conceptual model that defines the structure, behavior,
and more views of a system. An architecture description is a formal description and
representation of a system, organized in a way that supports reasoning about the
structures and behaviors of the system.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 21

ir.aiktclibrary.org
IR@AIKTC-KRRC
STOCK PREDICTION USING MACHINE LEARNING

5.3 Systems Integration

System integration (SI) is an engineering process or phase concerned with join-
ing different subsystems or components as one large system. It ensures that each
integrated subsystem functions as required. SI is also used to add value to a system
through new functionalities provided by connecting functions of different systems

5.3.1 Class Diagram

In software engineering, a class diagram in the Unified Modeling Language is a
type of static structure diagram that describes the structure of a system by showing
the system’s classes, their attributes, operations, and the relationships among objects.

Department of Computer Engineering, AIKTC, New Panvel, Navi Mumbai 22

ir.aiktclibrary.org