50 AI in Finance Project Ideas for High School Students

At the high school level, a good AI + finance project teaches you something a business class never can: how a model actually performs against real, messy financial data, not just a clean textbook example. Most students start by trying to predict stock prices directly, and that is fine as a first exercise, but the projects that actually build skill, and the ones that stand out in a portfolio or research paper, ask a narrower, more specific question about real financial data. We compiled this list of 50 AI in finance project ideas for high school students, organized by domain, from stock market analysis to fraud detection to macroeconomic forecasting.

If you want structured guidance, turning any of these into a polished, defensible research project rather than a tutorial clone, a mentored program like Veritas AI pairs you directly with an AI researcher to build something original. More on that at the end.

What Makes an AI + Finance Project Worth Doing at the High School Level?

Before the list, a quick framing question that will save you a lot of wasted effort: are you trying to answer something you don't already know, or are you trying to demonstrate a technique? Both are valid reasons to do a project, but they should be approached differently.

If you are learning a technique, pick a clean, well-documented dataset and focus on getting the mechanics right. If you are trying to answer a real question, like whether sentiment in earnings calls actually predicts price movement, expect the data to be messier, expect your first model to need revision, and expect the most interesting part of the project to be explaining what you found and why it matters, including where your model fell short.

The second kind of project is what makes a portfolio, research paper, or competition submission memorable.

Stock Market and Trading Projects

These projects focus on price prediction, technical indicators, and trading strategy, and they are the most common entry point into AI + finance, so the bar for a genuinely original angle is a little higher here than elsewhere on this list.

1. Predicting next-day stock price direction using historical price and volume data, with an honest evaluation of how much better than random the model actually performs

2. Comparing the predictive power of technical indicators like moving averages and RSI against a simple baseline model

3. Building a backtesting framework for a simple trading strategy and measuring it against a buy-and-hold baseline

4. Analyzing whether stock volatility spikes around earnings announcements can be predicted from pre-announcement trading patterns

5. Building a reinforcement learning agent that learns a basic trading strategy in a simulated market environment

6. Investigating whether combining multiple weak predictive signals outperforms any single signal alone

7. Studying how a specific sector's stocks correlate with a macroeconomic indicator like interest rates or oil prices

8. Building a portfolio simulation comparing a model-driven rebalancing strategy against a fixed allocation over several years

Personal Finance and Budgeting Projects

1. Categorizing personal transaction data into spending categories using natural language processing on transaction descriptions

2. Designing a savings recommendation tool that predicts a realistic monthly savings target from spending history

3. Analyzing anonymized spending data to identify patterns that predict financial stress before it happens

4. Building a tool that detects recurring subscriptions a user may have forgotten about from the transaction history

5. Studying how spending categories shift around a specific life event, like starting college, using public survey data

6. Forecasting a household's monthly cash flow based on historical income and expense patterns

Fraud Detection and Risk Projects

1. Building a classification model that detects fraudulent credit card transactions using a public, anonymized dataset

2. Investigating which features, like transaction time, location, or amount, are most predictive of fraud in a specific dataset

3. Studying how class imbalance, where fraud cases are rare, affects model performance, and comparing techniques for handling it

4. Flagging anomalous account activity, like a sudden change in login location, as a proxy for account takeover

5. Analyzing how fraud detection accuracy changes as available features are reduced, simulating a real-world data constraint

6. Building a rule-based fraud detection baseline and comparing it against a machine learning model on the same data

Credit Scoring and Lending Projects

1. Predicting loan default risk using a public lending dataset and analyzing which features matter most

2. Investigating whether a model trained on historical lending data shows bias across demographic groups

3. Comparing a traditional credit scoring approach against a machine learning model on the same loan outcomes

4. Studying how removing a specific feature, like zip code, changes both a lending model's accuracy and its fairness

5. Predicting which loan applicants are likely to pay off a loan early, and considering what that means for lenders

6. Using model confidence, not just its final decision, to flag loan applications that need human review

Cryptocurrency and Blockchain Projects

1. Predicting short-term cryptocurrency price volatility using historical trading data

2. Studying whether social media sentiment about a specific cryptocurrency correlates with its price movement

3. Analyzing transaction patterns on a public blockchain to identify wallet clusters that behave like trading bots

4. Building an anomaly detection model to flag unusual transaction volume on a specific token or exchange

5. Comparing the volatility of a basket of cryptocurrencies against a basket of traditional stocks

Robo-Advising and Portfolio Optimization Projects

1. Building a simple robo-advisor that recommends a portfolio allocation based on stated risk tolerance and time horizon

2. Comparing a model-optimized portfolio against a standard index fund over a multi-year backtest

3. Investigating how diversification recommendations change when optimizing for volatility versus return

4. Simulating how a specific portfolio would have performed through a historical downturn like 2008 or 2020

5. Studying how rebalancing frequency affects long-term portfolio performance using historical price data

Financial NLP and Sentiment Analysis Projects

1. Scoring the sentiment of earnings call transcripts and testing whether it predicts short-term stock movement

2. Analyzing how financial news sentiment correlates with market volatility for a specific sector

3. Summarizing a company's quarterly earnings report into a short, plain-language summary of key changes

4. Studying whether the tone of Federal Reserve statements predicts short-term movement in bond yields

5. Flagging unusually vague or evasive language in corporate earnings calls as a possible red flag

6. Comparing sentiment extracted from social media discussion of a stock against professional financial news coverage

Insurance and Actuarial Projects

1. Building a model that predicts insurance claim likelihood from policyholder and policy features

2. Investigating whether a claims prediction model shows unfair bias across demographic proxies

3. Comparing a model-based premium pricing approach against a traditional actuarial table for the same risk pool

Real Estate and Mortgage Projects

1. Predicting mortgage default risk using historical loan performance and borrower features

2. Building a home price prediction model and analyzing which features drive predictions most

3. Studying how mortgage rate changes historically affected regional home sales volume

Macroeconomic Forecasting Projects

1. Forecasting a specific economic indicator, like unemployment or inflation, using historical macroeconomic data

2. Comparing model-based economic forecasts against professional economist forecasts for the same period, and analyzing where each was wrong

How Should You Choose the Right Project?

With this many options, the hardest part is often deciding where to start. A few questions worth asking yourself:

1. Does this project use a skill I haven't tried yet, or does it deepen a skill I'm still shaky on?

2. Is there a real, accessible dataset available for this, and is it clean enough, or appropriately messy, for what I want to do?

3. Can I state, in one sentence, the specific question I'm trying to answer?If you cannot answer that last question clearly, the project needs more thinking before you open a notebook. The strongest AI + finance work, at any level, starts with a sharp, specific question rather than a broad ambition to "predict the market."

How Can You Get Feedback on Your Work?

The single biggest difference between a project that looks like a tutorial exercise and one that looks like real research is feedback from someone who actually knows what they are looking at. A mentor can tell you when your model's high accuracy is actually a sign of data leakage, when your backtest is quietly cheating by using future information, or when an interesting result needs one more robustness check before you can trust it.

While a mentor can be a teacher, an online community, or an older student further along than you, a structured program built around mentorship is usually the most reliable way to get that feedback consistently rather than occasionally.

Veritas AI offers two paths depending on where you are. The Deep Dive: AI + Finance program is a ten-week, small-group course with a 5:1 student-to-mentor ratio, covering machine learning applications in markets, banking, and fraud detection through lectures, code walkthroughs, and a team project. If you are ready to take a specific idea from this list further, the AI Fellowship pairs you one-on-one with a mentor, often a PhD or PhD candidate from a school like Harvard, Stanford, or Oxford, for twelve to fifteen weeks of original research, with support toward publication if the work merits it.

If one of the ideas on this list is the one you keep coming back to, that is usually a sign it is worth doing properly, with someone who can help you do it right.

Frequently Asked Questions About AI in Finance Project Ideas

1. Do I need advanced math or finance knowledge to start one of these projects?

No, though it helps to build as you go. Most of these projects are approachable with a working knowledge of Python and basic statistics, and finance-specific concepts, like what a moving average or a credit default actually means, can be learned alongside the project rather than as a prerequisite.

2. Where can I find real financial data for these projects?

The yfinance Python library pulls historical stock price and volume data directly from Yahoo Finance. Kaggle hosts dozens of cleaned finance datasets covering fraud, lending, and cryptocurrency data. FRED, the Federal Reserve's economic database, is the standard free source for macroeconomic indicators like interest rates and inflation.

3. What is the biggest mistake students make with AI finance projects?

Claiming a model predicts stock prices with high accuracy without acknowledging how genuinely difficult that is. Financial markets are famously hard to predict, and a project that is honest about its limitations reads as far more credible than one that overstates its results.

4. How long should an AI + finance project take?

A focused exploratory or classification project can be completed in one to two weeks. Projects involving backtesting or model comparison typically take two to four weeks. The most ambitious original research projects, suitable for a journal submission, often take two to three months, including iteration and write-up.

5. Can a high school AI + finance project be published?

Yes. Journals like the Journal of Emerging Investigators accept rigorous quantitative research from high school students, and a project with a clear question, honest methodology, and a defensible conclusion has a real shot, particularly with mentorship from someone who can help you meet the bar for publication.