"Alien Cat team on Google Vertex AI Hackathon Hackathon"

Team Idea

Building a financial advisor that demystifies stock investing by providing real-time updates, dynamic visuals, and data insights. An accurate, cost-effective alternative to existing financial AI Agents, leveraging Google Vertex AI and MongoDB Vector Search.
arthurxin953
Arthur Xin
arthurxin953

Machine learning engineer

gchen
Grace Chen
gchen

aliceyh7
Alice Hu
aliceyh7

SunnyYuan
Sunny Yuan
SunnyYuan

yuh221
Yueyang Huang
yuh221

yuchen_pan779
yuchen pan
yuchen_pan779

Submission

StockSage AI - A Smart Finance ChatBot

StockSage AI - A Smart Finance ChatBot

The world of investing is complex and overwhelming, especially for those without a finance background. In particular, the prevalence of inaccurate and obsolete data often lead investors to uninformed decisions. While some existing financial AI agents attempt to mitigate this problem, they heavily rely on internet scraping, a method that is not only costly but also prone to inaccuracies and hallucinations "StockSage AI," our smart chatbot, simplifies financial market navigation by providing personalized, real-time advice and data visualizations. Leveraging Google Vertex AI and MongoDB, StockSage offers a cost-effective, accurate alternative to traditional AI tools. The core features of StockSage AI include: 1. Chat Interface: Users can ask personalized queries 2. Data Visualizations: Displays market trends and prices with colorful and intuitive graphics 3. Real-time Analysis: Bot evaluates reliable news data, updated multiple times daily 4. Efficient AI Search: Leverages databases over web scraping for acquiring information, optimizing cost and accuracy The first step in building our solution was to collect and analyze data from reliable sources. We embedded news and price information, then used Google Vertex AI's Text Generation and Text Embedding Services to analyze trends. Next, we used MongoDB as our database to store and retrieve this data. MongoDB's Vector Search feature allowed for efficient data retrieval, preventing AI hallucinations and providing a friendlier interaction model for AI agents. Finally, we used Google Vertex AI's Text Generation Service to handle client requests. When users interact with the chatbot, their request is dispatched to Vertex AI. Vertex AI retrieves the data from our MongoDB database before formulating a response to the user. In a world inundated with information, we hope our project can be a beacon of clarity and reliability to provide users with personalized insights, as they make more informed financial decisions.