Projects
Build an Impactful AI Powered Project
At BetterMind Labs, our students choose a problem they care about and turn it into a Passion Project.
With a dedicated mentor guiding them at every step they’ll build a project that reflects their passion, not just another generic activity.
The result is work that feels authentic, meaningful, and strong enough to set you apart in applications.
Student Projects
AI & ML Projects developed by our students
These real world projects were made by the students during previous cohorts. These projects aim to solve some critical problem by harnessing AI/ML.
.
Change the text and make it your own. Click here to begin editing.
Add a Title
Change the text and make it your own. Click here to begin editing.
.
Change the text and make it your own. Click here to begin editing.
Add a Title
Change the text and make it your own. Click here to begin editing.
.
Change the text and make it your own. Click here to begin editing.
Add a Title
Change the text and make it your own. Click here to begin editing.
.
Change the text and make it your own. Click here to begin editing.
Add a Title
Change the text and make it your own. Click here to begin editing.
.
Change the text and make it your own. Click here to begin editing.
Add a Title
Change the text and make it your own. Click here to begin editing.
Student Projects
AI & ML Projects developed by our students
These real world projects were made by the students during previous cohorts. These projects aim to solve some critical problem by harnessing AI/ML.
AI + Quant
Intraday Price Prediction with LSTM
Leverage sequential models to forecast short‑term price movements. Backtest a simple “long if up, short if down” strategy and report metrics.
AI + Quant
AI-based Startup Risk Scorer
Build a tool that predicts the financial survival chances of early-stage startups based on limited available data. Train a classifier (Random Forest, Logistic Regression) to output a risk score (0–1).
Backtest a simple “long if up, short if down” strategy and report metrics.
AI + Quant
Clutch Player Predictor – NBA/NFL Edition
Use machine learning to predict which players consistently perform under high-pressure situations. Identify clutch scenarios (e.g., final 2 minutes, close scores).
AI + Quant
Yield Curve Fitting (Nelson–Siegel)
Build a smooth term‑structure model to price interest‑rate products. Pull government bond yields for various maturities (e.g., 1M, 3M, 2Y, 10Y).
AI + Quant
Sentiment analysis on financial news
Track the emotional tone of daily financial news and analyze how it correlates with market moves. Create a daily sentiment index and chart it over time.
AI + Quant
Statistical Arbitrage Strategy Backtester
Identify and exploit mean‑reversion opportunities across paired assets. Backtest the strategy over historical data, reporting P&L, drawdowns, and Sharpe ratio.
How We Form Teams
Step 1
Student Selection Based on Profile
~12 students who are interested in
finance, healthcare, finance and other domains.
Step 2
Grouping 12 Students by Major
Computer Science
Olivia Reddy
Noah Mehta
Emily Sharma
Liam Patel
Ava Nair
Ethan Kapoor
Business/Finance
Sophia Iyer
Jackson Verma
Sanya Nair
Neel Kapoor
Healthcare
Maya Iyer
Aarav Patel
Step 3
Team formation based
on skillset
We divide students into teams of 2 to 4 members, and assign a different mentor to every team, ensuring that no mentor is responsible for more than two teams.
Prior Programming Knowledge
Prior
Programming
Experience
Some Programming
Experience
No Programming
Experience
Team 1: Olivia Reddy, Noah Mehta
Team 2: Emily Sharma, Liam Patel
Team 3: Ethan Kapoor, Ava Nair
Step 4
Selecting Personal Mentors according to the teams
Mentor 1: Aman
Generative AI Expert
Team 1
Mentor 2: Katy
FinTech Expert
Team 2
Mentor 3: Rohan
Healthcare Expert
Team 3
Program Outline
Structure of Projects
Hover to Expand
Team Assignment
Students are grouped into small teams of 2-3 members based on their skill sets, interests, geography, and other factors to foster collaboration and diversity.
Defining a Problem Statement
Teams identify pressing problems in their chosen domain that can be addressed using AI/ML. This step focuses on understanding real-world challenges.
Topic Finalization
Through mutual discussion within the team and mentor guidance, a specific project topic is finalized, ensuring alignment with team interests and goals.
AI/ML Solution Development
Data Extraction & Preprocessing: Collecting, cleaning, and organizing datasets to ensure they're ready for model training. Model Development: Building and training AI/ML models to solve the problem.
Deployment and Presentation
Teams share their project results through detailed presentations. Students interested in showcasing their work further can create and deploy an app, adding a tangible, interactive dimension to their project and enabling real-world access.
FAQs
Got Questions? We’ve Got Answers
