Building Fundamental Stock Backtests with Ranked Factors and Rebalancing

Summary

The document outlines a common design for quantitative fundamental equity research. Investors select company measures spanning value, momentum, quality, and growth, rank stocks on those measures, and group them into deciles. They then choose a portfolio strategy and a relatively low-frequency rebalance schedule, and compare performance across the resulting groups using measures such as returns, compound annual growth rate, and Sharpe ratio.

The original question is about finding an open source framework that can accept custom market data, since the author cannot use Yahoo data for the relevant exchange. It does not report a framework comparison or implementation details. The answer points to Quantopian as a platform that then offered Morningstar fundamentals alongside a backtesting system. That recommendation is tied to a specific service and includes a disclosure that the respondent was its chief executive. The document gives no evidence about data coverage, survivorship bias, point-in-time fundamentals, or whether the platform remains available, so those issues would need separate evaluation before reproducing published research.

Key ideas

• Fundamental backtests can rank stocks using value, momentum, quality, and growth measures.
• Stocks can be sorted into deciles to compare factor performance.
• A research design should specify the portfolio strategy and rebalancing frequency.
• Returns, compound annual growth rate, and Sharpe ratio are examples of comparison metrics.
• Custom data support and point-in-time data quality matter when selecting a backtesting framework.

Tags

# Backtesting with fundamentals


# Backtesting with fundamentals












Recently I've read some books about quantative approach to fundamental investing: - What works on Wall Street - James O'Shaughnessy - Quantitative Value - Wesley Gray, Tobias Carlisle - Quantitative Strategies - Richard Tortoriello Basically, their research methodology, can be summarized as, we have a set of indicators: - value (E/P, EBIT/TEV, S/P, ...) - momentum (RSI, ...) - quality (Piotroski score,...) - growth (PEG, ...) We rank stocks and assign to deciles. We decide how often we rebalance portfolio (rather low frequency) and which strategy to apply. We calculate return,cagr, sharpe etc. for every decile/strategy.

I'm looking for free/open-source framework/library to reproduce similar research. I can't use yahoo data (non-yahoo stock exchange), so I need to load my own data. I consider to use python pandas for this, but maybe a better solution exists. Unfortunately, I've only found libraries for pair trading and technical analysis for single stock.

## Answer by fawce (score 5)

https://quant.stackexchange.com/a/15822

Quantopian provides both the fundamental data (from Morningstar), as well as the backtest platform to reproduce results from the books you mentioned. Here's the introduction to our fundamentals offering: https://www.quantopian.com/posts/fundamental-data-from-morningstar-now-available-for-backtesting

(disclosure: I'm the ceo of quantopian)

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.