Skip to content

Latest commit

 

History

History
22 lines (20 loc) · 2.33 KB

project_proposal.md

File metadata and controls

22 lines (20 loc) · 2.33 KB

Project Outline:

  • Introduction: A brief background on the impact of the problem you're working on. Why is this project important?
  • Problem Description: In-depth discussion of the Problem to be solved. What is this project about?
  • Existing Solution: Has this problem been solved? What did they do?
  • Proposed Method: Proposed approach to solving the problem. What do you plan to do differently? Make sure that your solution adheres to the DS/ML pipeline that we have introduced you to in this cohort i.e it includes Data Sourcing, Data Cleaning and prep, ML Model and Model Deployment (where possible).
  • Proposed Split: Who will be doing what? Make sure to list each member of your team, and clearly state what they will be doing to ensure the project's success. Every member of the team must have a defined role. For example, you can have Data Sourcing sub team, Data Cleaning and Prep sub team, Model sub team and Model Deployment sub team (Front End and Backend skills required). Even though the work is splitted amongst team members, all team members should be knowledgeable about the proposed solution and should be able to present this solution if needed.
  • Proposed Timeline: Give a rough estimate of how long you want to spend on each component of your proposed method. For example, 1-3 days for data scraping, 3-5 days for data cleaning/validation, etc.
  • Conclusion: A discussion of the usefulness of your application. Possible extensions of your project.
  • References: We are assuming you referenced some article. You can keep all the references here.

Requirements:

Your project should involve the following components:

  • Data Sourcing: Web scraping or any other data sourcing method.
  • Data Cleaning and Prep: Data Cleaning, preparation and basic statistics reporting
  • Modeling: Base Model, Model Comparison, Hyper-parameter Tuning and monitoring with experiment management
  • Model Deployment : Deploy on the web or mobile. You can leverage Google Colab/Streamlit/Huggyface where possible.

Format:

  • Submission is to be done in pdf and uploaded to your Team's repo.
  • Content must be in a minimum of 2 pages with reference separated in a third page.
  • Standard font size of 12 should be used with the exception of title which should be 18.
  • Include a list of all active members of your team, and your team mentor.