TickrTap

Inspiration

We want to make stock research more efficient and accessible.

What it does

We use web scraping to retrieve recent news related to a company, aggregate the information, and then use an LLM to summarize key information.

How we built it

We built the webpage with React and Express. We used NewsAPI and AlphaVantage to get recent data about a stock. We used the OpenAI API to summarize our information.

Challenges we ran into

LLMs take a while to run and summarize information. We needed to find a way to improve run time without sacrificing quality. We optimized how we aggregated the data in the first place and worked with different models to find the best fit.

Accomplishments that we're proud of

We are proud that we came up with an idea that can improve productivity. We also think it improves accessibility for those not experienced in trading/investing.

What we learned

We learned a lot about how to integrate LLMs with web apps.

What's next for TickrTap

We plan to improve the design of our project, further reduce the latency when generating reports, and increase output stability.

Built With

• alphavantage
• express.js
• newsapi
• openai
• pinatacloud
• react