Skip to content

EYAIChallenge/Stock-Agente

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 

Repository files navigation

alt text

Logo AI Challenge 2025 | Financial Agent Challenge


📊 Description

In this challenge, your team will act as strategic consultants for a sophisticated investment fund seeking to leverage AI in its daily operations. The fund manages a diverse portfolio of 11 different stocks and cryptocurrencies. Your team can choose to focus on the entire portfolio, a strategic selection, or an in-depth analysis of a single high-value asset.

Objective

Your mission is to create a decision support platform that transforms the fund's investment capabilities. Whether designing an intelligent trading agent, a sophisticated analytical dashboard, or a hybrid solution, you must demonstrate how AI can generate tangible business value in financial markets.


💡 Data

The dataset includes historical financial data from 11 different assets:

  • Stocks: AMZN, AAPL, GOOGL, MSFT, UDMY, NXE, SPY, CDR.WA, EH
  • Cryptocurrencies: BTC-USD, ETH-USD

All data is stored in .csv files in the data/ directory, named based on asset and frequency (e.g., AMZ_hourly.csv, AMZ_daily.csv), with the usage of the accelerator notebook.

Data Columns:

  • Datetime / Date: Timestamp of the market data entry (hourly or daily).
  • Close: Price at the end of the interval.
  • High: Highest price during the interval.
  • Low: Lowest price during the interval.
  • Open: Price at the beginning of the interval.
  • Volume: Number of shares/contracts/units traded.

🎯 Consulting Mindset Expectations

  • Strategic Advisors: Position yourselves as trusted advisors who understand both technology and financial markets. Balance technical innovation with practical considerations.
  • Value Architects: Articulate how your solution creates measurable business impact.
  • Sell the Solution, Not Just the Process: Present your solution as a valuable asset, highlighting business impact and suggesting clear next steps.

📦 Deliverables

  • ✅ A working prototype of your AI-powered investment solution.
  • ✅ An organized and well-documented code that can be reproduced.
  • ✅ A concise pitch presenting your solution to the judging panel as investment stakeholders.
  • (Optional) Performance analysis comparing your solution with traditional methods.

⚠️ **Important Submission Requirement** ⚠️

✅ Before the 14h00 deadline

Submit a zip folder with:

  • The Google Colab notebook (with all cells run & outputs shown).
  • Screenshots of all external tools/visualizations used.

Submit via email to: eyaichallenge@pt.ey.com

Subject: Stock Agent – GroupName

Include group member names in the email.


💡 Tips for Competitors

  • Master the Market Data: Dive deep into the stock and cryptocurrency data. Look for patterns, correlations, and anomalies that could inform strategic investment decisions.
  • Develop a Clear Value Proposition: Define exactly how your solution will add value—whether by improving decision speed, reducing risk, identifying overlooked opportunities, or enhancing portfolio performance.
  • Think Like the Client: Understand the day-to-day of investment professionals. What insights would improve their decisions? How can your solution seamlessly integrate into their workflow?
  • Establish a Performance Framework: Use metrics like ROI, risk-adjusted returns, prediction accuracy, and compare against market benchmarks.
  • Embrace Innovation with Purpose: Ensure innovations directly address the fund's business goals. Every feature should contribute to strategic value.
  • Craft a Business Case: When presenting, articulate not only the technical details but also the financial impact of your solution. Be ready to defend your approach.

🛠 Tech & Tools

🚨 Mandatory Requirement:
You must develop your solution in Google Colab using Python.

Beyond that, you are completely free to choose your own:

  • 📚 Libraries and packages
    Use any tools you need — e.g., Pandas, Scikit-learn, LangChain, etc.

  • 📈 Visualization tools
    Python-based: Matplotlib, Seaborn
    BI tools: Power BI, Tableau

  • 🤖 AI assistants
    Feel free to consult:
    ChatGPT, GitHub Copilot, Gemini, or any other


⏱ Time Management & Rules

  • ⏳ You have 4 hours total to complete your challenge
    🔒 No extensions will be allowed

  • 🗣 After the working session, deliver a 5-minute presentation
    🎯 Simulate a client-facing consulting pitch

  • 👥 Each group is allowed:

    • 1 technical support session (up to 5 minutes)
    • 1 business-related support session (up to 5 minutes)

🧠 Assistants will guide your thinking, not provide direct solutions


📋 Strategy & Workflow Tips

This is a consulting-style challenge with limited time. Keep these tips in mind:

  1. 👥 Assign roles early
    (e.g., a data person, a business analyst, and a presenter)

  2. 🔁 Work in parallel
    Don’t wait on each other. Split tasks and collaborate strategically.

  3. 🧑‍🏫 Keep the presentation in mind
    Start preparing early; don’t leave it to the last 10 minutes.

  4. Be realistic
    It’s better to deliver a focused, clear, and well-explained solution than a rushed or overly complex one.

💡 You are not being judged only on technical accuracy —
but also on how you think, structure, work as a team, and communicate your approach.


💬 Final Thought

This challenge invites you to bridge the worlds of cutting-edge AI technology and sophisticated financial strategy.

🏆 The most successful teams will demonstrate not just technical prowess,
but the ability to translate that technology into meaningful business advantage.

You are developing more than just a tool –
you are creating a strategic asset that could fundamentally enhance how investment decisions are made.


🏁 Brought to you by EY AI Challenge

About

EY AI Challenge 2025 | Stock Agent Challenge

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published