Surendra S

- Research Program Mentor

Bio

Project ideas

Stock Price Prediction using Regression Models - Beginner

This project introduces students to the fundamentals of financial analytics and machine learning. Students will learn how to collect stock market data from APIs like Yahoo Finance, clean and preprocess the data using Pandas, and apply basic regression techniques such as Linear Regression, Lasso, and Ridge to predict stock prices. Additionally, students will create simple visualizations using Matplotlib and Seaborn to analyze stock trends. Skills Covered: Data collection and cleaning Exploratory data analysis (EDA) Introduction to regression models Basic financial market indicators Visualization techniques for stock trends Outcome: A Python-based stock price prediction model A research report explaining the prediction process and findings A presentation with key insights on market trends

Liquidity Forecasting and Investor Behavior Classification - Intermediate

This project builds on basic ML skills by introducing students to dual-model financial predictions. Students will implement both regression models (Random Forest, Gradient Boosting) for liquidity forecasting and classification models for investor behavior prediction. Feature engineering techniques will be applied to enhance model accuracy. The final results will be presented through an interactive dashboard for financial insights. Skills Covered: Advanced feature engineering for financial datasets Implementing Random Forest and Gradient Boosting Investor behavior classification using logistic regression and decision trees Model evaluation techniques (cross-validation, AUC-ROC) Interactive financial dashboards with Plotly Outcome: A dual-model system predicting liquidity and investor behavior A research paper analyzing feature importance and financial drivers An interactive visualization comparing model performance

AI-Powered Financial Analytics Platform for Market Forecasting - Advanced

This advanced project challenges students to develop a full-fledged financial analytics platform incorporating multiple machine learning models. Students will use ensemble techniques and time-series forecasting models to enhance prediction accuracy. They will also deploy the system with API endpoints, simulating real-world applications used by hedge funds and investment banks. Skills Covered: Time series forecasting (ARIMA, LSTM) Ensemble learning for boosting model performance API development for financial analytics services Real-world implementation of trading strategies Performance benchmarking against industry models Outcome: A production-ready financial analytics platform A research paper comparing ML-based market forecasting techniques A deployed API for real-time financial predictions

Building an AI-Powered Personal Investment Research Assistant: Multi-Agent System for Teen Financial Literacy

In this project, students will develop a sophisticated AI-powered investment research assistant designed specifically for young investors and financial literacy education. This hands-on project combines cutting-edge artificial intelligence with practical financial knowledge, creating a system that can help teenagers make informed decisions about their first investments while learning fundamental market concepts. What Students Will Build Students will create a multi-agent AI system using modern frameworks like OpenAI's Agent SDK or CrewAI that includes: Research Agent: Automatically gathers and analyzes company financial data, news sentiment, and market trends Risk Assessment Agent: Evaluates investment risk levels appropriate for young investors with limited capital Educational Agent: Explains complex financial concepts in teenager-friendly language Portfolio Tracker: Monitors simulated investments and provides performance insights Learning Objectives By the end of this project, students will: Understand how modern AI agents work and collaborate Learn fundamental investment principles and financial literacy concepts Gain hands-on experience with Python programming and API integration Develop skills in data analysis and visualization Create a practical tool they can actually use for their own financial learning Technical Skills Developed AI/ML Frameworks: OpenAI API, multi-agent orchestration, natural language processing Programming: Python, async programming, API integration Data Analysis: Financial data processing, sentiment analysis, trend identification Web Development: Building user interfaces with Gradio or similar frameworks Cloud Deployment: Deploying applications to platforms like HuggingFace Spaces Project Scope & Timeline This 8-12 week project is designed to be challenging yet achievable for motivated high school students: Weeks 1-3: Foundation building - Learn AI agent concepts, set up development environment, understand financial markets basics Weeks 4-6: Core development - Build individual agents for research, analysis, and risk assessment Weeks 7-9: Integration & testing - Connect agents into a collaborative system, implement safety guardrails Weeks 10-12: Enhancement & deployment - Add user interface, deploy to cloud platform, create project documentation Real-World Impact This project addresses the critical need for financial literacy among teenagers. According to recent studies, only 21 states require high school students to take personal finance courses. The AI assistant students build will: Help peers make informed decisions about their first investments Serve as an educational tool for learning market concepts Demonstrate how AI can be used responsibly in financial decision-making Provide a foundation for understanding algorithmic trading and fintech Sample Research Questions Students will explore questions such as: How can AI agents be designed to promote responsible investing among young people? What safeguards should be built into AI financial tools to prevent risky behavior? How effective are AI-generated explanations compared to traditional financial education? What types of investments are most suitable for teenagers just starting their financial journey? Deliverables Fully functional multi-agent AI investment research system Research paper documenting methodology, findings, and lessons learned Public deployment of the application for peer testing and feedback Presentation suitable for science fairs or academic conferences Prerequisites Basic programming experience (Python preferred but not required) Strong interest in both technology and finance Willingness to learn complex technical concepts Access to a computer capable of running Python development tools This project uniquely combines the excitement of cutting-edge AI technology with practical financial skills that students will use throughout their lives. It's designed to be both educational and personally valuable, giving students a head start in both technological literacy and financial responsibility.

Coding skills

Credentials