Kavya Case Study: A high school student built AI Quantitative Risk Analysis Project

Introduction: A High School Student built AI Quantitative Risk Analysis Project

In high school, finance is often simplified into investing games or surface-level stock analysis. Quantitative finance, however, is not about predicting the market or picking winning stocks. At its core, quant work is about risk, uncertainty, and decision-making under incomplete information.

Admissions officers understand this distinction. They also know that most students who claim interest in finance have never seriously engaged with risk modeling. That’s why a project like Risk Wise, a quantitative risk analysis system built by Kavya Mohanakrishnan, stands out immediately. It demonstrates not just technical interest, but intellectual discipline.

Grades and AP math courses show capability. A quant project shows how that capability is applied.

Why risk analysis is the foundation of quantitative finance

Most people think finance is about returns. Professionals know it is about risk-adjusted returns.

According to a 2024 report from J.P. Morgan Asset Management, institutional investors evaluate strategies primarily on volatility, drawdowns, and downside exposure rather than raw gains. In other words, risk is the central variable.

From an AI and data science perspective, risk analysis matters because:

• Markets are noisy and non-deterministic

• Historical data is incomplete and biased

• Models must handle uncertainty explicitly

• Decisions must be robust, not optimal under ideal conditions
  

A student who chooses to model risk rather than chase predictions is already thinking at a college-level depth.

What makes a quant risk project meaningful

Quantitative finance projects are easy to oversimplify. Many student projects fail because they treat finance as a math exercise instead of a systems problem.

Weak quant projects often:

• Assume clean, stationary data

• Ignore volatility clustering

• Focus only on returns

• Lack interpretation of outputs
  

Strong quant projects show:

• Understanding of uncertainty

• Use of probabilistic or statistical reasoning

• Risk metrics beyond averages

• Clear explanation of assumptions and limits

Risk Wise belongs firmly in the second category.

Case study: Kavya Mohanakrishnan’s Risk Wise project

Kavya Mohanakrishnan approached quantitative finance with curiosity but also caution. Rather than asking “How do I beat the market?”, the project started with a more grounded question:

How can risk be measured, understood, and communicated clearly to support better decisions?

The problem Risk Wise addresses

Many retail investors and even students studying finance misunderstand risk. They focus on upside outcomes without accounting for:

• Volatility

• Downside probability

• Exposure concentration

• Market shocks
  

Risk Wise was designed to help users visualize and quantify risk, rather than blindly chase performance.

What Risk Wise does

Risk Wise is a quantitative risk analysis tool that:

• Ingests historical financial data

• Analyzes volatility and variability over time

• Evaluates downside risk using statistical measures

• Presents risk metrics in a clear, interpretable format
  

The emphasis is not on prediction, but on risk awareness.

Technical approach and tools

The project follows a realistic quant workflow:

• Financial time-series data processing

• Statistical analysis using Python

• Risk metrics such as volatility, variance, and drawdown

• Scenario-based evaluation to test robustness

• Visualizations to communicate complex results clearly
  

Comparing Risk Wise to typical finance projects

Typical Student Finance Project	Risk Wise
Focuses on returns	Focuses on risk
Deterministic thinking	Probabilistic reasoning
Simplistic assumptions	Acknowledges uncertainty
Minimal interpretation	Deep explanation of metrics
Low differentiation	Strong differentiation

This contrast explains why risk-centric quant projects carry disproportionate admissions value.

The hidden skill Risk Wise develops: thinking under uncertainty

Most high school learning rewards certainty. Quantitative finance punishes it.

Risk Wise required decisions about:

• How much data is enough

• Which metrics capture downside best

• How to interpret conflicting signals

• How to communicate uncertainty honestly
  

These are the same decisions students face later in research, trading, policy modeling, and AI system design. Admissions committees recognize this kind of thinking immediately.

What an ideal quant learning environment looks like

Projects like Risk Wise rarely emerge from unguided exploration alone. Strong outcomes usually come from environments that provide:

• Mentorship

  Guidance on financial reasoning and statistical rigor.

• Structured progression

  Moving from theory to applied analysis step by step.

• Critical feedback

  Challenging assumptions rather than validating them.

• Outcome clarity

  A system that can be demonstrated, explained, and defended.
  

These conditions reflect how quant skills are developed in universities and industry.

FAQ

1. Is quantitative finance too advanced for high school students?

Not if approached through risk and statistics rather than prediction. Many concepts are accessible with proper structure.

2. Do colleges prefer quant projects over general AI projects?

Colleges prefer depth and reasoning. Quant projects stand out because they demand both.

3. Does a risk analysis project help outside finance admissions?

Yes. It supports applications in applied math, economics, data science, and engineering.

4. Is mentorship important for quant projects?

Strong mentorship helps students avoid false confidence and build models grounded in reality.

Closing perspective: why Risk Wise matters

From a mentor’s perspective, Risk Wise reflects an important intellectual shift. Instead of asking how to win, the project asks how to avoid losing. That mindset is foundational in finance, engineering, and AI.

Kavya Mohanakrishnan’s Risk Wise project shows how structured guidance and serious thinking can turn quantitative curiosity into applied understanding.

Programs like BetterMind Labs are designed to support this level of work through mentorship, realistic workflows, and outcome-driven projects. For families evaluating advanced AI and quant pathways, exploring structured programs at bettermindlabs.org is a logical next step when the goal is depth, not shortcuts.

To see the impact of Student’s like Kavya, Read Why AI Projects Are a Must for Students Targeting Top Colleges