Embedded Files
ML Driven Portfolio Framework to Adapt to Regime Change
"Do you still remember the chill these words sent down your spine? Dot-com Bubble. Great Financial Crisis (GFC). COVID-19 Pandemic."
Every time the market dynamic undergoes a major shift, billions vanish—first in financial markets, then often rippling through the economy.
Think it doesn’t affect you? Think again. Even if you don’t trade stocks, your pension and insurance funds could take a sudden hit when markets plunge.
OUR MISSION
OUR MISSION
Build a machine learning–driven portfolio framework that empowers retail and institutional investors to navigate market regime shifts, capture dynamic trends, and preserve capital during periods of uncertainty
MVP Demo
MVP Demo
Here we showcase our Minimum Viable Product, built in Streamlit.
Users can input their current portfolio allocations, and the DeepLearning Sentiment Portfolio (DSP) intelligently analyzes these inputs to generate an optimized portfolio—designed to preserve capital and enhance returns, especially during volatile market regimes.
Technical Approach Overview
Technical Approach Overview
Our Team
Our Team
We are a team of UC Berkeley data scientists committed to using advanced machine learning to help investors navigate uncertainty, adapt to market shifts, and make smarter portfolio decisions
Irene Na
Elaine Keung
Mia Kobayashi
Austen Lowitz
Page updated
Report abuse