ShockWave AI

Logo

Inspiration

Modern economies behave like complex systems where small changes can trigger massive global consequences — much like the butterfly effect in chaos theory. Events such as the 2008 financial crisis or the dot-com bubble showed that early warning signs often existed but were difficult to interpret.

We wanted to create a tool that helps people see economic cause-and-effect visually, bridging Computer Science and Economics. Instead of static charts, ShockWave AI lets users explore how shocks propagate through markets and understand how past economic patterns relate to present conditions.

Our goal was educational impact: making macroeconomics interactive, intuitive, and explainable using AI.

What it does

ShockWave AI is an Economic Butterfly Effect Simulator that models how small economic changes can cascade into large market events.

The platform:

Simulates economic shocks and ripple effects across markets Compares current economic indicators with historical datasets Predicts the likelihood of events such as: Market recessions Asset bubbles Volatility spikes Visualizes causal relationships between economic variables Provides interactive exploration using both real data and user-controlled parameters

Users can adjust economic factors or observe live market conditions and watch how potential “shockwaves” evolve over time.

How we built it

We used a hybrid AI + simulation approach:

Frontend

Vite + modern web UI Interactive visualization dashboards Dynamic graphs showing ripple propagation

Backend

FastAPI for API handling and simulation logic Python-based economic modeling pipeline

Data Sources

Historical macroeconomic indicators Market indices and financial time-series datasets

Core Techniques

Time-series similarity matching Pattern comparison between historical and current trends Causal graph modeling Scenario simulation engine

High-level workflow:

current_state -> feature extraction -> historical similarity search -> shock propagation simulation -> risk prediction output

The system combines real-world data with adjustable simulations to balance realism and experimentation.

Challenges we ran into

Economic complexity: Real economies are nonlinear and noisy, making modeling difficult without oversimplifying.

Data alignment: Historical datasets had different frequencies and formats.

Explainability vs prediction: We wanted users to understand why predictions occur, not just see results.

Visualization design: Representing cascading effects clearly required multiple iterations.

Balancing realism and interactivity: Too much realism reduced usability; too much abstraction reduced credibility.

Accomplishments that we're proud of

Built an interactive economic simulation rather than a static predictor

Successfully linked historical crises with modern economic scenarios

Created intuitive visualizations for complex macroeconomic dynamics

Designed a hybrid input system combining real data with user exploration

Delivered an educational AI system accessible to non-experts

Most importantly, we transformed abstract economic theory into something users can experience.

What we learned

Economics behaves more like a complex adaptive system than a predictable machine.

Visualization is as important as modeling when communicating AI insights.

Small UX decisions dramatically affect how users interpret predictions.

Combining simulation with AI creates stronger educational tools than prediction alone.

Interdisciplinary projects require translating concepts between domains.

We also learned how to design AI systems that prioritize understanding, not just accuracy.

What's next for ShockWave AI

Future development plans include:

Real-time economic data streaming Reinforcement-learning-based policy simulations Country-specific economic models Scenario sharing and collaborative simulations Explainable AI modules showing causal reasoning paths Educational classroom mode for economics students

Long term, we envision ShockWave AI as an interactive economic sandbox where policymakers, students, and researchers can safely explore “what-if” economic futures.