Inspiration

Traditional trading decisions often rely heavily on financial indicators, historical prices, and market news. However, people's interests, cultural preferences, entertainment choices, and brand affinities can also provide interesting signals about market trends.

We wanted to explore how AI and cultural intelligence could work together with financial data to create a smarter trading assistant. This inspired us to build TRADING AGENT, an AI-powered project that connects cultural insights with financial market information.

What it does

TRADING AGENT is an intelligent trading assistant designed to combine cultural intelligence and financial market data.

Its key objectives include:

Using Qloo API to explore cultural intelligence and entity relationships.
Integrating Twelve Data and Finnhub for financial market information.
Connecting with Alpaca's paper trading API.
Analyzing market information to generate useful trading insights.
Supporting data-driven decision-making.
Exploring relationships between cultural trends, brands, and financial markets.

Our goal is to make financial analysis more intelligent by bringing different types of information together.

How we built it

We developed PAPER TRADING AGENT using Python and a modular development approach.

Our technology stack includes:

Python: Core programming language.
Qloo API: Cultural intelligence and entity-based insights.
Twelve Data API: Financial market data.
Finnhub API: Financial information and market research.
Alpaca API: Paper trading integration.
Requests: API communication.
Python-dotenv: Secure environment variable management.

We organized the project into separate components to make the code easier to maintain, test, and extend.

We also created a Jupyter Notebook to support experimentation and testing during development.

Challenges we ran into

During development, we faced several technical challenges:

Integrating multiple external APIs with different response formats.
Managing API credentials securely using environment variables.
Understanding and connecting cultural intelligence with financial market information.
Handling API communication and potential request failures.
Managing dependencies and maintaining a consistent Python environment.
Configuring Git and GitHub to organize and publish the project.

Each challenge helped us improve our debugging, integration, and development skills.

Accomplishments that we're proud of

We are proud of building a project that explores the connection between cultural intelligence and financial markets.

Our key accomplishments include:

Integrating multiple external API services into one project.
Bringing Qloo's cultural intelligence capabilities into a financial use case.
Developing a Python-based trading agent architecture.
Creating a dedicated notebook for experimentation.
Organizing the project with requirements and test files.
Exploring how AI-driven insights can support smarter financial analysis.

Most importantly, we transformed an interesting idea into a working software project.

What we learned

This project helped us understand how cultural intelligence and financial data can complement each other.

We learned:

How to integrate multiple REST APIs.
How to manage API keys and environment variables.
How to structure modular Python applications.
How to handle API requests and errors.
How to use Git and GitHub for version control.
How to approach complex problems through experimentation and testing.

We also learned that combining different data sources can create opportunities for innovative AI applications.

What's next for TRADING AGENT

We want to continue improving TRADING AGENT by introducing more intelligent capabilities.

Our future plans include:

Developing more advanced AI-powered market analysis.
Improving the connection between cultural trends and financial signals.
Building a user-friendly dashboard for insights and market information.
Adding more sophisticated risk management features.
Improving paper trading and strategy evaluation.
Exploring machine learning for pattern recognition and predictive analysis.
Expanding integrations with additional financial and intelligence platforms.

Our long-term vision is to build an intelligent trading assistant that connects cultural intelligence, AI, and financial data to support more informed decision-making.