Quant Picks performance
Results as of 2026-03-31
The performance data below reflects the returns of an equal-weight portfolio composed of our Quant Picks, rebalanced monthly since the strategy’s launch in January 2023.
These results illustrate the performance an investor would have achieved by systematically following each recommendation and executing all trades at the market open following each update, assuming no transaction costs. It is provided for informational purposes only. Past performance is not indicative of future results.
US equities
Cumulative returns
Risk metrics (3 years)
Civil year returns
Canadian equities
Cumulative returns
Risk metrics (3 years)
Civil year returns
About our Quant ratings and methodology
Quick and powerful insight
Our Quant ratings provide quick and powerful insights on stocks by addressing five factors that have historically been highly correlated to stock returns:
Growth, Valuation, Quality, Revisions, and Momentum.
For each factor, we compare a variety of quantitative metrics for each company with the rest of its sector to determine a score from A (best in sector) to D (worst in sector). Our overall Quant Rating considers the aggregation of the 5 factors.
Quant Picks
Our Quant Picks are the stocks rated with an overall Quant Rating of A+. Our Quant Picks highlight aboutapproximately 30 stocks with the best quantitative ratings in their sector. Our recommended stock weights always represent an equalweight and the sector weightings closely match the index, making sure we generate alpha purely from stock selection, not from sector allocation. Quant Picks are the very best in every sector based on an aggregate score considering the five core factors (Growth, Valuation, Quality, Revisions, Momentum) and six complementary factors (Capital return, Sentiment, EPS surprises, Analysts opinion, Other Quantitative data, Qualitative data via content-analytic).
Machine learning
The metrics we consider in our ratings and their relative importance are different from one sector to another, based on their historical relation to stock returns in that sector. As these relations change over time, our scoring algorithm adapts to focus on the most meaningful indicators. Every month, our scoring algorithm is refined by expanding its dataset. Machine learning enables us to adapt to a changing world where investment styles and criteria evolve over time. By constantly optimizing our scoring algorithm based on data available at the decision date, our machine learning process eliminates the typical biases in factor investing and improves the probability of continued alpha generation.
Content analytic
Using Python, we read thousands of press releases every day and convert words into quantitative data. For instance, a press release stating "announces stock split" or "announces share repurchase" becomes quantitative data in our dataset. This expands our dataset with data unavailable to most. Financial databases like Bloomberg tell you the date a stock splited and the amount of shares repurchased in a quarter, but by analyzing the content of press releases, we capture the announcement, which is the most important input for a trading strategy. With over 500 qualitative signals translated into quantitative variables, we use a much wider range of data than most investors.
Sector neutral
Many competing quantitative services show off great historical returns, but they have been overweight in tech for years. Is it skill, or is it luck? At QDD, we believe there are great opportunities in every sector. We think sector picking is hazardous and believe the best long-term approach to keep a reasonable level of active risk is to stay sector neutral and generate alpha across all sectors. That's why our Quant Picks always cover every sector, with weightings closely matching the index.
Sampling and universe
For U.S. and Canadian equities, our stock sample consists of the S&P 500 Index and the S&P/TSX Composite Index. As a result of sampling in these large cap indexes, our Quant Picks are mostly focused on large cap stocks. However, our equal-weighting strategy creates a (small) size bias compared to the market weighted indexes.
Longer term backtest performance
For investors looking for data prior to the launch of Quant Picks in 2023, we present below the simulated backtest performance of a portfolio applying the same methodology and machine learning process since 2008.
Backtesting inherently comes with limitations and biases. Although we take great care to minimize potential biases, backtest returns may still contain biases and are not indicative of future performance.
Bias Risk Mitigation
By sampling the S&P 500 Index and the S&P/TSX Composite Index every month since 2008, we avoid one of the most common biases in backtesting: survivorship bias.
By applying our machine learning process starting in 2008—using only the historical data available at that time—we significantly mitigate another major source of error in backtesting: lookahead bias. Our stock selection methodology is not based on current knowledge of which factors performed well in subsequent years. Instead, factor selection and weightings are determined exclusively using data available as of each decision date since 2008.
With the amount of data available today, it is easy, in hindsight, to design a strategy that would have performed well over the past decade. Our machine learning process is fundamentally different. Each month, our algorithm recalculates the historical relationships between stock fundamentals and future excess returns. The process continuously evolves and refines itself, always using only the information available at that specific point in time. Our backtest replicates the same process beginning in 2008.
Backtest performance
U.S. equities
Cumulative annual returns
Historical ratings and returns :
Risk metrics (10 years)
Civil year returns
Backtest returns as of March 31, 2026
DISCLAIMER: The returns shown above are the result of a backtest simulation implementing our quant-based strategy. Although we take great care to minimize potential biases, backtest returns may present some biases and may not be indicative of future performance.
Canadian equities
Cumulative annual returns
Historical ratings and returns :
Risk metrics (10 years)
Civil year returns
Backtest returns as of March 31, 2026
DISCLAIMER: The returns shown above are the result of a backtest simulation implementing our quant-based strategy. Although we take great care to minimize potential biases, backtest returns may present some biases and may not be indicative of future performance.
Frequently Asked Questions
What is the trade frequency and turnover rate of the Quant Picks?
If you apply our Quant Picks following our monthly email alerts, you should expect an average of 3 trades per month for Candian stocks and 5 trades per month for US stocks, based on historical averages. Many subscribers use these recommendations systematically as a portfolio model, while others use them as stock ideas.
To reduce the noise caused by daily data changes and keep a reasonable portfolio turnover, our Quant Picks are updated monthly. We send the new additions and deletions to our subscribers monthly.
How to use your email alerts?
Our Quant Picks identify the top-ranked stocks in every sector. For instance, in the financials sector in the U.S., our Quant Picks identify the stocks ranked #1 to #4. If a stock drops from rank #4 to rank #5, it will be removed from our Quant Picks and replaced by the new #4. It does not mean that the stock ranked #5 is a bad investment. It is still one of the best. If you don't systematically follow the Quant Picks as a portfolio model, our advice is to consider every new addition to the Quant Picks as a very serious buy candidate, but not necessarily to interpret every deletion as sell signals.
What is the portfolio performance for international stocks?
At this time, QDD Research covers equities listed on North American exchanges. While our primary focus is on U.S. and Canadian securities, we also assign Quant Ratings to internationally domiciled companies that are listed in the U.S. These ratings are calculated using the same quantitative methodology applied for U.S. stocks.
However, because our international coverage is limited to securities listed on North American exchanges — and does not represent the full global opportunity set — we do not maintain or publish an official model portfolio performance for the international segment. That said, given the consistency of our quant-based framework, we would expect a similar potential for alpha generation over time. Investors should nevertheless anticipate a higher level of active risk relative to broad international benchmarks such as the MSCI EAFE Index, due to the narrower investable universe and listing constraints.
How are factor scores calculated?
Within each sector and geography, stocks are evaluated using a broad set of quantitative inputs. Each metric is ranked on a sector-relative basis, ensuring that companies are always compared against their direct peers.
For example, in the U.S. Technology sector, the Quality factor incorporates more than 80 quantitative data points. For each metric (such as Return on Equity), companies are ranked from best to worst within the sector. The highest-ranked company receives a score of 100 for that metric, while the lowest-ranked receives a score of 0. These percentile ranks are then aggregated across all metrics within the factor to produce a sector-relative factor score for each stock. The same methodology is applied consistently across all factors, as well as our proprietary qualitative signals derived from content analytics. As a result, each stock receives standardized, sector-adjusted scores across all factors.
How are factor weightings determined?
Factor weightings vary by sector and geography. Our algorithm continuously evaluates the historical relationship between each factor and subsequent stock returns within a specific sector and region. Factors that have historically demonstrated stronger explanatory power are assigned higher weights in the overall Quant Score.
Because factor-return relationships evolve over time, weightings are dynamic. The model regularly recalibrates factor importance based on updated historical correlations, allowing it to adapt to changing market regimes, style rotations, and sector-specific conditions. Importantly, this same dynamic framework was applied throughout the historical backtest simulation. Factor weights were recalculated using only information available at each point in time, therefore preserving the integrity of the historical results.
Factor weighting matrix for US Equities as of January 31st, 2026
Factor weighting matrix for Canadian Equities as of January 31st, 2026
