GithubHelp home page GithubHelp logo

carsonsgit / trademind Goto Github PK

View Code? Open in Web Editor NEW
6.0 2.0 0.0 23.25 MB

Project developed for AI Launch Lab's R&D program

Home Page: https://trademind.pages.dev/

CSS 31.83% HTML 11.11% JavaScript 44.24% Python 12.82%
machine-learning react stock-price-prediction research-and-development winning-project

trademind's Introduction

TradeMind AI Logo


๐Ÿ‘‹ Welcome to TradeMind AI - your intelligent stock analytics companion! This repository contains the codebase for TradeMind AI, a project developed as part of the AI Launch Lab's R&D AI Program. TradeMind AI leverages artificial intelligence techniques to provide insightful analysis and predictions in the stock market domain.

TradeMind AI is designed to provide insightful analysis and predictions in the stock market domain. Please read through the documentation thoroughly to understand its functionalities and limitations.

๐ŸŽ“ Project Overview

TradeMind AI is a stock analytics AI designed to assist users in making informed decisions in the stock market. Leveraging cutting-edge AI techniques, TradeMind AI provides insightful analysis, predictions, and recommendations, empowering users to navigate the complexities of stock trading with confidence.

Utilize TradeMind AI as a supplementary tool to your existing research and analysis. While it offers valuable insights, always consider multiple sources of information before making trading decisions.

See our colab notebook

Problem Identification and Scope

๐Ÿ“ˆ Problem Definition

Trading stocks can difficult, stressful and financially dangerous. It can be very difficult for individuals who don't have much free time to trade stocks. Watching the market, even when it only applies to long term investments, can require a large amount of time and focus that most people can't afford. Our goal in creating TradeMind is to make stock trading more accessible to all.

๐ŸŒŽ Target Audience

The core target audience for our stock analytics AI is primarily for those who are interested in investing and want a second opinion before putting money into the "pot". It should also be noted that this should be used for long term investments and growth as opposed to short term daily trading.

Remember that past performance is not indicative of future results. Use TradeMind AI as a tool to complement your investment strategy, but be aware of potential risks associated with stock market trading.

๐Ÿ“‹ Scope and Constraints

Our AI tool will analyze the closing data of each stock within the S&P 500 index. From this, it will be able to make long term predictions regarding the future of the stock so that the user has a helpful guide for their investments.

๐Ÿ† Success Criteria

Front-End: A working front-end website that is hosted online. The site should have four pages, home, about, roadmap, and analytics. The page should be visually appealing, user-friendly, and interactive. Users should be able to access the AI service easily.

Back-End: API should expose endpoints that provide all necessary information and services required by the front-end. The API should allow the front-end to perform interactions and queries with the AI model.

AI Model: The model should be trained sufficiently enough that it can reliably predict stock prices for all present indices in our stock index selection.

Data Collection and Preparation

๐Ÿ“Š Dataset

For our dataset, we have decided on the S&P 500 stock data created by Cam Nugent

This dataset provides historical stock price data for companies listed on the S&P 500 index from 2013 to 2018. It includes information on the opening, highest, lowest, and closing prices of stocks, as well as trading volume, all denominated in USD. The dataset is available in both individual files for each stock and as a merged CSV file. Users can leverage various formats to conduct analyses such as visualizations, stock comparisons, and predictive modeling for informed trading decisions.

๐Ÿ“ Data Attributes

Through the dataset, we are provided with the following data attributes:

  1. Date (Temporal data)
  2. Close (Closing stock price)

๐Ÿš€ Getting Started

To get started with TradeMind AI, follow these steps:

  • Head to our website: Our hosted website houses functionality for our AI, to find it, navigate to the "Analytics" page!

OR

  • Use our Colab Notebook: Dive into the provided colab notebook to explore data preprocessing, visualization, and initial modeling.

trademind's People

Contributors

kbaggott1 avatar carsonsgit avatar cristiano-fazi avatar github-actions[bot] avatar felixs123 avatar cindy-coulibaly avatar

Stargazers

 avatar  avatar  avatar TJ Klint avatar JACHacks avatar  avatar

Watchers

Lucian avatar  avatar

trademind's Issues

Create Hamburger Menu

Task Description

For when the user is on mobile, replace the navbar with a Hamburger menu with a flyout drawer.

Improve AI Reliability

Task Description

Tweak AI accuracy/reliability by modifying variables and retraining if necessary.

Additional Context

Please use more than one metric to measure reliability. Don't just use accuracy.

Collect Data

Task Description

Retrieve datasets that will be used to train the AI model. Datasets should contain individual stock data that is relevant to our users.

Additional Context

I understand we already have a good dataset but having more data couldn't hurt

Data Collection and Preparation

Requirement Description

Retrieve, clean and divide the data. This data is essential to training an effective model

Tasks

Effort Estimation

Most of this is already done so I don't image this Epic will take very long to complete

Create Companies Drop-Down Menu

Task Description

Create the dropdown menu that will contain companies the users can select to view their stock data.

Additional Context

This will non-functional right now, so either create a dummy endpoint that returns a hardcoded list or hardcode the data in the front-end. The first selection is preferable if time permits.

Fix "Analytics" page bugs

Task Description

Currently, when you go mobile on the "Analytics" page on computer, the navbar often breaks. Fix that & get on main.

Create "About Us" Page

Requirement Description

Create an "About Us" Page that shows off each developer.

Tasks

Effort Estimation

Not difficult but rather time consuming

Additional context

N/A

Divide Data

Task Description

Divide the data into training and testing sets. This is essential before feeding the data to the model.

Additional Context

DO NOT JUST DIVIDE THE DATA RANDOMLY. These are stocks so please take like 25 years of each stock data for training and 5 years of each stock data for testing. That way we can have it try to fill in the blanks

Fix Mobile Device Styling Issues

Task Description

The underlining of the names does not work properly on smaller screens. The Arrow next to the names should also remain "glued" to the last name.

Organize CSS files

Task Description

Create a "styles" directory and put in all .css files for organization.

Select An AI Model

Task Description

Research and determine which AI model would be best for us given our specific requirements.

Additional Context

Do not pick anything linear it will not be effective given the eb and flow of the stock market

Make the "Home" Page Pretty

Task Description

Prettify the home page

Additional Context

Just make it pretty and follow the same theme as the rest of the app

Add a Pull Request template

Task Description

  1. Create a new file named pull_request_template.md in the .github directory at the root of your repository.

  2. Paste the template content you provided into this new file (pull_request_template.md).

  3. Save the file.

  4. Commit the changes to your repository's main branch.

Add "Felix" Section to "About Us" Page

Task Description

I'd recommend you let someone else do their part first so you can use their code as an example. If you have any questions feel free to ask anyone.

Additional Context

Mention your game programming experience!

Navigation Bar Gets Smaller on Roadmap Page

Task Description

Carson fix your navbar please. It's smaller on the roadmap page

Additional Context

You will have to change /design_doc/design_document.css. It's not in the react folder

Chose a Color Palette

Task Description

Chose an appropriate color palette for the app.

Additional Context

Just pick a good one

Create Navigation Bar

Task Description

Modify the navigation bar to be at the top of the screen. The bar should have four(4) options; Home, About Us, Analytics and Design Document(Please decide on a better name for that one). Use CSS to make it pretty, use colors from or close to our color pallet. Make it consistent across all pages.

Add Content to the "Home" Page

Task Description

Home page should contain information relating to the project and maybe a few images for pazzas.

Additional Context

Not applicable

Research and Add Charts to "Analytics" Page

Task Description

Research and decide on a package we can use to display graph stock data to the user. If possible, please run your suggestion by the team.

Additional Context

I have used Highscharts in this past, but please look into it's feasibility for this project.

Create "Analytics" Page

Requirement Description

Create the Analytics page. This page will be non-functional but will be used to display the data from the the AI stock analytical tool.

Tasks

Effort Estimation

Page won't be functional therefore it should not challenging. Will be time consuming

Additional context

I'd recommend Highcharts for the graphing package but we may have to discuss that

Write Documentation / Add Comments

Task Description

The repo is full of reusable code & impactful CSS. Write documentation on code so that it's clear what does what to allow for tweaks at a later date.

Fill Analytics Page with temp info

Task Description

Right now, if someone were to go to the analytics page, they'd be met with some illogical graph and no information. Add some temporary content so that the page is more complete.

Train AI Model

Task Description

Using the data that was collected to train the AI model to make predictions of the stock market.

Additional Context

Use Sikit.learn for this

Create "Home" Page

Requirement Description

Create a "Home" page that covers the reason for making the app, the features and other important information a user may want to know when arriving at our site. Do you best to keep it brief.

Tasks

Effort Estimation

Not very complex, but rather time consuming

Additional context

Ensure that the style is consistent with the rest of the site

Clean Data

Task Description

Locate the NaN values in the .csv & either write a Python script to replace the NaN's with the mean of that stock 5-days back and 5-days forward OR if not many, go through each cell in the .csv & manually set the cell to calculate the mean of those +/-5 days.

Train and Improve AI Model

Requirement Description

Train the AI model and have it reach a point, in terms of reliability and accuracy, that we can be confident in it's decision making abilities.

Tasks

Effort Estimation

This may challenging, don't hesitate to collaborate or reach out to team members

Write a Document for the Group Folders

Task Description

The organizers of the program are requiring us to put in documents regarding our plan, our model, our progress, etc. Create a couple of documents & put them into the folder designated to our group.

Additional Context

Reference other groups

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.