top of page

Investo Stock Market Prediction

Predicting how the stock market will perform is one of the most difficult things to do. There are so many factors involved in the prediction – physical factors vs. psychological, rational and irrational behavior, etc. All these aspects combine to make share prices volatile and very difficult to predict with a high degree of accuracy.  Machine learning techniques have the potential to unearth patterns and insights we didn’t see before, which can be used to make unerringly accurate predictions.

DATE

December 2020 - March 2021

MY ROLE

Back-end & Front-end Developer

TOOLS

  • figma
  • visual-studio
  • html-5
  • css
  • bootstrap

Problem

Share Market is an untidy place for predicting since there are no significant rules to estimate or predict the price of shares in the share market.

Many methods like technical analysis, fundamental analysis, time series analysis and statistical analysis, etc. are all used to attempt to predict the price in the share market but none of these methods are proved as a consistently acceptable prediction tool.

Target Audience

confused.png

Indian investors seeking trend analysis.

Objective

Simplifying stock trend predictions.

Develop a user-friendly application for trend analysis.

Empower investors with data-driven insights to facilitate informed decision-making.

Solution

The system utilizes Long Short-Term Memory (LSTM) and Artificial Neural Network (ANN) which allows us to to view past trends and future predictive trends.

This software is aimed at Indian users consisting of pre-trained models for the top 30 companies listed on the Bombay Stock Exchange Ltd. 

Model

The software will work with historical data about stock prices of a publicly listed company which is collected using the Yahoo finance API

The software aims at providing an accurate prediction for trends in the company's stock price for 30 days into the future by basing its prediction on the previous 500 days data.

Language: Python             Libraries : Tensorflow & Keras 

The product is a subscription model available for functioning by two types of users namely:
Registered and Unregistered users.

The two functions of the module are analysis and prediction, an unregistered user is only allowed to access the analysis mode while a registered user is allowed to view the prediction as well

SRS- Software Requirement Specification

Graphs:

Analysis:

anal.png

Prediction

test.png

Data flow diagrams:

The software can be represented using three levels of data flow diagrams:

Level 0:

1.PNG

Level 1:

2.PNG

Level 2:

Picture1.jpg

Prototype:

bottom of page