Quantitative Strategies for Selecting Stocks

by Richard Tortoriello

Quantitative Strategies For Selecting Stocks Splash image

A few years ago, I was asked to develop a series of quantitative stock-selection models for the equity research department of Standard & Poor’s.

In preparation for this project, we backtested more than 1,200 different investment strategies to determine which were predictive of future “excess returns.” (A backtest is simply a statistical look at historical data to determine whether employing a given investment factor, such as selecting stocks with low price-earnings ratios, results in excess returns over time; i.e., returns above a stock market benchmark.)

My goal was to determine the basic factors that drive future stock market returns, from an empirical point of view, using only historical data as our raw material (balance sheet, income statement, cash flow statement, and pricing data). In short, I set out to create a quantitatively drawn “road map” of the equity markets. To do our research, we used a sophisticated data-analysis program and Standard & Poor’s Point in Time database, which contains more than 20 years of “as originally reported” (unrestated) data for about 150 data items and 25,000 individual companies.

...To continue reading this article you must be registered with AAII.

Gain exclusive access to this article and all of the member benefits and investment education AAII offers.
JOIN TODAY for just $29.
Log in
Already registered with AAII? Login to read the rest of this article.

Register for FREE
to read this article and receive access to future articles.
Richard Tortoriello is the aerospace and defense analyst in the equity research division of Standard & Poor's and has conducted numerous quantitative investment studies for the company. He is author of "Quantitative Strategies for Achieving Alpha" (McGraw-Hill, 2009).


Patrick from Missouri posted over 3 years ago:

You might be better served using PROFIT MARGIN rather than ROE, along with only stocks that are within 95 perdcent of their 52 week high

Steve from South Carolina posted over 3 years ago:

Stock Selection - Tools and Rules

At least ten hands shoot into the air as the discussion turns to stock selection. The speaker smiles, responds to each, and observes: "You really need to know the depth of the water, its temperature, tides, and currents before you dive into the river --- and then, what kind of predators are in there?"

The investment planning stage is too often ignored by the young and the new, and too often over cooked by the older and beaten up. Most of the confused indecisiveness is due to constant media hype and an endless bombardment of data, news, software solutions, electronic tools, and expert opinions. But most actual investment errors are caused by invalid expectations, fear, greed, and lack of discipline.

Here's an overview, and it is expected to provide structure and provoke thinking while skimming over most of the detail and explanation that can be found in the "Brainwashing" book.

For the rest of the story:

Steve Selengut
Author of: "The Brainwashing of the American Investor: The Book that Wall Street Does Not Want YOU to Read"

Dave from Washington posted over 2 years ago:

Does anyone know what Steve's point was?

This comment just looks like an advertisement.

I liked the article, even though after 30 years of doing it, I am fading out of the stock picking game for a safer indexing strategy, because frankly I'm just not convinced that even the "average" expert can get this right in the long run.

Dan from Texas posted over 2 years ago:

I like this approach, which is confirmed by realistic backtesting. An important part of the analysis is that takes into account the dividends, spinoff values and cash payouts, which can be a significant part of the overall return, but which are not always reflected in many databases. This review confirms my belief that an investor makes his gain on the buy side; usually by recognizing an undervalued entry point for a quality company. Unfortunately, the ratios employed here are not obtainable in any of the simple stock screens I have at hand. Why not offer this method as one of the AAII model portfolios?

Fred from Pennsylvania posted over 2 years ago:

I am in a similar situation as Dan from Texas. I would have a difficult time obtaining most of the ratios used in the article and would think it would be nice to see this method as an AAII model portfolio.

Bruce from Colorado posted over 2 years ago:

I am with Dave and Dan and would welcome an easy way to obtain these ratios.

Nash from Georgia posted over 2 years ago:

Like Dan, Fred, and Bruce I will need more help to capitalize on this artical.

John from Florida posted over 2 years ago:

I also would like an easy referral source for ongoing updates for the data. AAII ?.

Choudary from Missouri posted over 2 years ago:

Can AAII add the above criteria in the model stock portfolio and help us in screening stocks.

Donald from Pennsylvania posted over 2 years ago:


Nishesh from Illinois posted over 2 years ago:

one question to author on 52 week price range strategy is that

what will be the exit strategy after entering buy in this strategy

can i constantly compute the ratio and continue hold it it dosent break 41%?

Paul from Ohio posted over 2 years ago:

There's always the X-Factor nothing is for sure, world events even national events, nature, management changes, new technologies and so on things change. Then there the unforseen surprizes that are in our favor.Controling risk is paramount. Don't concentrate in to few sectors of the economy.

John from Louisiana posted over 2 years ago:

Mr Tortoriello's book is in my library along with many others that I have collected over the past 40 years.Investing professionally and personally for most of that period I can attest to the value of disciplined approaches such as the one outlined in this article.In my opinion there isn't one best way to solve the investing puzzle. Lots of things work. You just need to keep doing it. And keep it simple. In my group's professional operation,we spend a great deal of time and money testing strategies and methods.After all is said and done, however, much of our stock selection process is still driven by basic inputs similar to those in this article and which were developed decades ago based on accepted and time-tested analytical techniques.

Melvin from Virginia posted over 2 years ago:

Does someone have a simple Stock Investor Pro screen worked our for this concept? If so, please include in your response.

John from Florida posted over 2 years ago:

I would be pleased to pay for this screen, if it is ever available as an AAII portfolio.

John from Maryland posted over 2 years ago:

Is this a "buy and hold" strategy. Probably not, so what criteria do you use to determine when to sell? I have some stocks where PM has dropped to .2(with, of course, resulting losses).

Jim from California posted over 2 years ago:

C'mon. Can't someone at AAII come up with a model stock portfolio for these strategies??? What can I do to spur this on?

Jean from Illinois posted over 2 years ago:

We have added the screen criteria and custom fields for use in Stock Investor Pro to the companion First Cut column on the Tortoriello approach: (it's linked above on the right under Related Articles, or just search on Tortoriello).

Charles from Illinois posted over 2 years ago:

As Jean noted, we posted the criteria for creating a Tortoriello approach in our Stock Investor Pro program. The First Cut article ( explains what how we did it: If you just want to see the criteria, you can download the excel file at: -Charles Rotblut, AAII

Dominick Sciola from Washington posted over 2 years ago:

Liked this article a lot.

Hope this isn't too ignorant of a question, but does Tortoriello, great Italian name by the way, advise holding onto stocks that fit this criteria (and perhaps others for that matter) for approximately 1 year?

I would assume that's the optimal holding period here since the portfolios formed over the course of the screen were held for 12 months.


Benster from New York posted about 1 year ago:

It would seem that price momentum and value are counterveiling measures, and almost mutually exclusive; e.g., how likely is it that a stock near it's 52-week high will still have a low relative valuation (measured, say, by P/E)?

Charles Rotblut from Illinois posted about 1 year ago:

Ben, if a stock has previously been out of favor with investors or has strong earnings growth, it can have both good momentum and a low valuation. It is more common than you might think. This said, at some point, upward momentum will drive the valuation higher, so you have to monitor the stock's price to ensure the P/E is still reasonable. -Charles

James Hargreaves from Georgia posted about 1 year ago:

The concept that value matters (although it isn't determinative) should NOT be a shock.

As was rightfully pointed out Graham figured that out back in the 1940s (or was it earlier).

Bart DiLiddo, PhD (in the 1980s) developed a VST (Value, Safety, Timing) model that was and is the basis of Vector Vest.

Finally, the real problem is HOW does one determine value (as one of the key factors to stock picking).

In the late 1990s, Copeland (et. al.) developed a new method of stock (company) valuation that focused on not just earnings but looked at cash flow. The Copeland model was widely adopted in the Financial Analytics community.

Finally, to simple say that stock valuation methods should be based (derived from) the company's financials and cash flow statements MISSES a key point.

Without making proper accounting adjustments to PUBLISHED (10K) financials, one is not able to make one to one (performance) comparisons between different companies.

The accounting NOTES to a set of financials are where the "gold" is found in analyzing a company's financials. That "gold" (and it's uses) can only be understood by someone with a working knowledge of accounting (policies, choices and adjustments).

You need to log in as a registered AAII user before commenting.
Create an account

Log In