Designing an Optimal Piotroski F-score

Creating a Much Better F-Score

Piotroski’s F-score approach to identifying winners and losers is a good first step, but the F-score measure is, in the words of the author, ad hoc. Nobody wants their investment process to be ad hoc, but we do like the simplicity associated with the F-Score. In this section we do not intend to reinvent the wheel. Instead, we look to make intelligent changes to the F-Score that improve performance.

Using the F-Score as a foundation, we have created a new financial strength score (FS-Score), which we divide into the same three categories as the F-Score:

Current profitability,
Stability, and
Recent operational improvements.


Like the F-Score, the FS-Score seeks to find the financially strongest stocks. We have modified the F-Score to tweak three variables and moved the variables into slightly more intuitive categories. The variables in our FS-Score are set out in the following manner.
Current Profitability

We use three variables to measure a stock’s current profitability and cash flow realization:

ROA and FCFTA are net income before extraordinary items and free cash flow, respectively, divided by most recent total assets. If the stock’s ROA or FCFTA is positive, we define the respective variable FS_ROA or FS_FCFTA as one, and zero if otherwise.

ACCRUAL is the stock’s current year’s net income before extraordinary items less cash flow from operations, scaled by beginning of the year total assets. The variable FS_ACCRUAL is marked one if CFO is greater than ROA, and zero if otherwise.

Our current profitability variables are similar to Piotroski’s profitability variables, except that we replace the CFO variable with free cash flow divided by total assets (FCFTA). We make this change to take into account the impact of capital expenditures on the stock’s cash flows. We also exclude the variable ΔROA from this category and put it and ΔFCFTA in our “recent operational improvements” category because we believe it is a more intuitive category for these variables.
Stability

Like Piotroski, we assume that an increase in leverage, deterioration in liquidity, or the use of external financing is a bad signal about financial health. Our stability signals measure changes in capital structure and the stock’s ability to meet future debt service obligations:

ΔLEVER is the historical change in the ratio of total long-term debt to total assets. FS_ΔLEVER is marked one if the stock’s leverage ratio fell in the preceding year, and zero if otherwise.
ΔLIQUID is defined as the year-over-year change in the ratio of current assets to current liabilities. The variable FS_ΔLIQUID is marked one if the stock’s liquidity improved (higher ratio), and zero if otherwise.
NEQISS is equity repurchases minus equity issuance, or net equity issuance. FS_NEQISS is set to one if repurchases exceed equity issuance, and zero otherwise.


Our stability category differs from Piotroski’s in one important way: We replace the F-Score’s equity issuance variable, EQISS, with net equity issuance, or NEQISS, which is defined as repurchases minus issuances. We make this small, but important, change because we believe EQISS can be a misleading metric.

For example, many firms issue shares for a variety of reasons unrelated to financial health, including management or employee incentive programs. A company may issue a small number of shares to compensate a CEO, but simultaneously initiate a substantial repurchase program that dwarfs the number of shares issued to the CEO. Piotroski’s EQISS would penalize this stock because of the small equity issuance, while NEQISS would consider the relative size of both the buyback and the issuance and score accordingly. In this example, each metric would be scored in the following way: EQISS would be zero and have no effect on F-Score; NEQISS would increase by one and increase FS-Score.

(Note: We calculate NEQISS using the technique used in the August 2004 NBER working paper “On the Importance of Measuring Payout Yield: Implications for Asset Pricing,” by Jacob Boudoukh, Roni Michaely, Matthew Richardson and Michael Roberts.) Recent Operational Improvements

We introduce a new section for the FS-Score: recent operational improvements. This category is roughly equivalent to the F-Score’s operating efficiency section, except that the focus in our FS-Score is on improvements. We include in our recent operational improvements category the following:

ΔROA is the current year’s ROA less the prior year’s ROA. If ΔROA is greater than 0, the variable FS_ΔROA scores a one, and zero otherwise.
ΔFCFTA is the current year’s FCFTA less the prior year’s FCFTA. If ΔFCFTA is greater than 0, the variable FS_ΔFCFTA is marked one, and zero otherwise.
ΔMARGIN is the stock’s current gross margin ratio (gross margin divided by total sales) less the prior year’s gross margin ratio. The indicator variable FS_ΔMARGIN equals one if ΔMARGIN is positive, and zero if otherwise.
ΔTURN is the stock’s current year asset turnover ratio (total sales scaled by beginning of the year total assets) less the prior year’s asset turnover ratio. The indicator variable FS_ΔTURN equals one if ΔTURN is positive, and zero if otherwise.


We examine recent operational improvements to ascertain whether the business has operational momentum. We don’t want to buy a seemingly cheap stock that gets increasingly expensive relative to its fundamentals because the business deteriorates. For example, a stock with $100 million in EBIT (earnings before interest and taxes) trading at a market value of$300 million is trading at a 3x multiple. If operations deteriorate to the extent that next year’s EBIT is only \$50 million, the “bargain” price-to-EBIT ratio of 3.0 becomes a more expensive ratio of 6.0. If this halving of EBIT continues, we will be left holding a very expensive stock after a few years. more on http://www.aaii.com/journal/article/simple-methods-to-improve-the-piotroski-f-score

2 responses

It looks like an interesting paper. Are you working to implement the idea here on Quantopian?

Disclaimer

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.

I agree with Dan