Stock Market
Analysis and
Prediction
6
1
Avinash Joshi (15794/074)
Indra Kishor Chaudhary (15797/074)
0
Pawan Chaudhary (15804/074)
Introduction
• The stock analysis and prediction is a web-based application which helps
investors and traders to analyze the future trend and approximate price of stocks.
• Stock price prediction system considers the historical equity share price of a
company price.
• ARIMA model on this data to predict the future prices of the stock.
• The proposed system is considering stock NASDAQ (TESLA).
Problem Statement
• Financial analysts investing in stock market usually are not aware of the stock
market behavior.
• Analyzing all this information individually or manually is tremendously difficult-
Automation is required.
• This will allow financial analysts to foresee the behavior of the stock that they are
interested in and thus act accordingly.
Objective
• To develop the web-based application that can predict the future price of stock.
• To help user to analyze the trend of particular stock.
Requirement Analysis
• Functional Requirements
– Login Module
– User function
– Admin Function
• Use Case Diagram
– Use case diagram in the system represents the methodology used in system analysis to
identify, clarify, and organize system requirements of Stock Analysis System.
• Use Case Diagram
System Design
• In the system, Designs like modules, architectures, components and
their interface and data for a system based specified requirements were
made.
• Flow Chart
– Flow chart shows the procedure followed during system design.
Algorithm Description
• And at last, using ARIMA (Auto Regression Integrated Moving Average) model
we use TESLA stock and predict the stock price of that stock.
– p is the order of the autoregressive model (number of time lags). In the project we used the
order 1.
– d is the degree of differencing (number of times the data have had past values subtracted). We
used degree of differencing 1 for this.
– q is the order of moving average model. Before building an ARIMA model. We used value 0 to
calculate the order of moving average.
Module Description
• Login Module:
– This system has both user and admin login module. Admin login are used to give access to
admin panel and user login module is used by general user to access stock details and view the
predicted result.
• User function:
– Registered users are allowed to see their stock details as well as manage it. They can view the
predicted output of the system.
• Admin Function:
– Admin is in charge of maintaining database of the system. The response and possible queries
are updated and managed by the admin.
Tools
• PyCharm: • Bootstrap:
– We have used PyCharm for the – Bootstrap is a free and open-source front
programming part in the project. end development framework for the
• HTML: creation of websites and web apps.
– We used it for creating web pages and web • Django:
applications. – We used Django for the database part of
• CSS: the system along with backend design.
– CSS is used to describe the presentation of • Draw.io:
a document written in markup language – Draw.io was used to draw the diagrams
such as HTML or XML. used in the document.
Testing
Training & Testing Dataset Predicting Price
• Result:
– After collection of data the future share price is predicted using ARIMA model. We got the
accuracy of 58%.
Conclusion
• Conclusion:
– We implemented the application of ARIMA to the task of stock price prediction with salient
feature. Our initial analysis shows significant correlation between different input parameters.
– After training and testing the stock prices using historic values, we got testing mean square
error of 42.086% and symmetric mean absolute percentage error of 56.459%. This shows that
the system can predict actual value of stock with the accuracy of 58%. If we change the order
of p, d and q terms then it affects the accuracy of the predicted result.
• Future Improvement:
– There are plenty of way to expand on the work done in this project. The potential
improvement can be made to our data collection and analysis method.
References
• [1] https://www.analyticsvidhya.com/blog/2021/07/stock-market-forecasting-using-time-series-analysis-with-arima-
model/
• [2] https://analyticsindiamag.com/hands-on-guide-to-lstm-recurrent-neural-network-for-stock-market-prediction/
• [3https://www.semanticscholar.org/paper/Forecasting-of-Stock-Prices-Using-Multi-Layer-Devadoss-Ligori/
f99beac140b6c7c52d721dd38bce953f95ff5156
• [4] https://peerj.com/articles/cs-408/
• [5] https://1library.net/document/7q0wp19y-multi-forward-neural-network-knowledge-future-market-
prediction.html
• [6] https://www.jimsindia.org/8i_journal/stock_price_prediction_revisedpaper.pdf
• [7] https://www.ijcse.net/docs/IJCSE18-07-01-012.pdf
Screenshots
Screenshots
Screenshots
Thank You
