GPT Investor

Leveraging the power of AI to empower your financial decision-making

Comment

Inspiration

We were inspired by the potential of AI to revolutionize financial decision-making. While there were existing scripts that attempted to provide investment insights, we saw an opportunity to create a user-friendly mobile application that could harness the power of AI to deliver personalized, actionable recommendations.

What it does

GPT Investor is an AI-powered mobile application that generates investment insights by synthesizing financial data from various sources across the internet, including Yahoo Finance, financial publications, and more. The AI model analyzes this data and provides users with valuable insights to help them make informed decisions when choosing stocks to invest in.

How we built it

  1. We compiled a list of S&P 500 companies and stored it in a MongoDB database, serving as the default entry point for users in the app, where they can browse through a list of companies.
  2. We developed a Flask app to serve as the link between the Android app and the MongoDB database.
  3. The Android app was created using MVVM and Clean Architecture principles, with each action modeled as a use case.

Challenges we ran into

  • Learning to prompt the AI model (Gemini) effectively, as it differs from other generative AI products in terms of system prompts.
  • Formatting the response text from Gemini on Android, including rich-text formatting.
  • Dealing with the potential downtime and latency issues of using a free server for the backend.

Accomplishments that we're proud of

  • Developing a fully functional application within two weeks.
  • Implementing a server as a fallback strategy to overcome API usage limits.
  • Providing users with the ability to export results as PDF on-demand.
  • Maintaining a small app size for optimal performance.
  • Incorporating authentication for secure requests.

What we learned

Perhaps the most important thing we learnt was the role of hyperparameters like top-k and temperature in fine-tuning the AI model's outputs.

What's next for GPT Investor (in no particular order)

  • App UI redesign for an improved user experience.
  • Ability to export results as images.
  • Filtering capabilities for companies based on market cap and other indicators.
  • Comparing multiple companies simultaneously.
  • Streaming generated responses instead of waiting for the request to complete.
Share this project:

Updates