top of page
website logo.png

Quantitative investment science via
Financial Big data Analysis.

We are FBA Quant




About FBA Quant


FBA Quant is a quantitative finance research group built at the intersection of financial engineering and data science. We have educated future quantitative researchers pursuing careers in the U.S. since 2016.


We share a common spirit of academic excellence and collective intelligence. Learning is the cornerstone of our culture and plays an active role in group activities – through weekly collaboration and interaction with members at all levels.

Can Machine Learning Help

Portfolio Management?

Machine learning can help with most portfolio tasks like idea generation, alpha-factor design, asset allocation, weight optimization, position-sizing, and the testing of strategies. However, applying machine learning in portfolio management can limit the performance in a risk-return relationship. To complement this approach, we explore how machine learning techniques may be able to adjust the proportion between long and short positions and evaluate individual assets.

Read more   >

Intro to FBA-Quant: Python Toolkit for Quantitative Finance

FBA-Quant is a Python toolkit for quantitative finance, which is created by quantitative developers at FBA Quant to provide access to derivatives pricing and risk management. FBA-Quant can also be used to accelerate the development of quantitative trading strategies, analyze derivative products, and backtest portfolio management solutions as a set of statistical packages for data analytics applications.

Read more   >

Trade Execution Optimization via Reinforcement Learning

The optimal trading execution problem is that a trader seeks to maximize the proceeds from trading a given quantity of shares of a financial asset over a fixed duration trading period, considering that trading impacts the future trajectory of prices. Owing to the complexity, however, traditional approaches for order execution are plagued by intractability under generalized conditions. Alternatively, deep Reinforcement Learning has previously been applied to the problem of optimal execution and has shown promise, both in simulated environments and on historical data.

Read more   >

Meet our Members

bottom of page