“Feasibility Study Report”
Submitted By: Submitted To:
Arunima Upreti (5) Dr. Pranita Upadhyaya
Bibek Nayak (10)
Bishnu Kumar Shrestha (13)
Jitendra Kumar Yadav (17)
Manjul Gopal Sharma (22)
Date:2081/02/03
Stock Market Analysis and Prediction
Using Machine Learning
Client Information:
Stock investors, stock traders, stakeholders and companies along with the citizens that highly
engage in stock market across the country.
Statement of the task:
The main motive of stock market prediction is to create a system that analyzes the data of the
stock market and predict the price and the values of the stock. The system supports real time
data for current stock prices and predict the upcoming value using machine learning algorithm.
Preliminary Requirement Analysis
Functional Requirements:
• Create a system that predicts the future price of the stocks and provide the previous
information of the stock.
• Able to generate charts and graph of the stock prices of the market.
• Develop user friendly interface along with login and multifactor authentication.
Non-Functional Requirements:
• Reliability: The reliability of the product will be dependent on the accuracy of the data,
date of purchase, how much stock was purchased, high and low value range as well as
opening and closing figures. Also, the stock data used in the training would determine
the reliability of the software.
• Security: The user will only be able to access the website using his login details and will
not be able to access the computations happening at the back end.
• Portability: The website is completely portable and the recommendations completely
trustworthy as the data is dynamically updated.
• Interoperability: The interoperability of the website is very high because it synchronizes
all the database with the Wamp server
Suggested Deliveries
• The user is provided with a login, logging into which enables the user to view his past
stock purchases and future recommendations.
• The user can look previous data Information which was collected.
• Each user has a friend list and can also be recommended on their buying patterns.
• The user can also be recommended on the basis of the trending stocks which would
require the data regarding the stocks
• investment portfolios to manage the stocks of the user.
Development process
• Program Implementation
• Getting to Visualizing the Stock Market Prediction Data
• Checking for Null Values by Printing the Data Frame Shape
• Plotting the True Adjusted Close Value
• Setting the Target Variable and Selecting the Features
• Scaling
• Creating a Training Set and a Test Set for Stock Market Prediction
• Data Processing For LSTM
• Building the LSTM Model for Stock Market Prediction
• Training the Stock Market Prediction Model
• Making the LSTM Prediction
Outline Plan and Milestone
1. Requirements gathering and analysis: [June 10] - [June 20]
• Collect the data of the stock market.
2. Application design and prototyping: [June 21] - [June 30]
• Create a system blueprint
• Develop a prototype of the system architecture with appropriate machine
learning algorithm.
3. Development and testing: [July 1] - [July 20]
• Develop a model to predict the price of stock.
• Combine the data of current stock prices to generate a graph.
• Constant testing to ensure the accuracy of the system.
4. User acceptance testing and refinements: [July 21] - [July 20]
• Certify the testing with the user and draw the feedback.
5. Deployment and app store submission: [August 1] - [August 6]
• Deploy the system in the domain
• Training and workshops for the users.
6. Post-implementation support and maintenance: [August 7] - [August 10]
Visibility Plan:
• Weekly progress reports: A complete report on the work that is done, to be done
and the problems encountered.
• Biweekly meetings: Conduct biweekly meetings with the investors and gather
feedback.
• Utilization of project management software ‘Jira’ task tracking and document
sharing
Discussion Of Business Consideration
1. Feasibility Analysis:
• Technical Feasibility:
Our team fulfill the requirements of necessary technical parameters along with team
members skillful in the field of machine learning, python, data extraction for the
development of the system.
• Economic Feasibility:
The system is cost effective for the development process as per the financial plan of the
team. Also, the system proceeds the long-term financial benefit and customer
satisfaction.
• Schedule Feasibility:
The recommended plan is feasible with the available resources and systematic blueprints
in the proposed time schedule considering the potential complexities in the
development.
• Operational Feasibility:
The system can be incorporated with the stock market data infrastructure .
2. Risk Analysis:
• The system may not function accurately according to the market trends.
• High risk to unauthorized external access and cyberattacks along with the data loss
• Market instability due to the changes in regulation of the government.
Fallback Plan
• For cyberattacks and data loss execute the multifactor authentication and data
encryption.
• Gather as large amount of data as possible for better accuracy.
• Implement different alternative prediction models in case of failure.
• Seek information from the expert of the domain regarding the current and future
scenario of the market.
