How to Measure Your Portfolio's Factor Exposure
Regress daily returns on the Fama-French market, size and value factors, then read the loadings, standard errors and R². Real regression outputs for seven funds show how.
To measure your portfolio's factor exposure, regress its daily excess returns on the daily returns of the Fama-French market, size and value factors. The coefficients, called loadings, say how strongly the portfolio tilts toward each one, and R² says how much of its movement the three explain at all. Factors are the shared characteristics that make stocks move together whatever they sell.
Every loading in this article is a real regression output, not an illustration, fitted on 1,206 daily observations from August 10, 2021 to May 29, 2026. Factor data is from the Ken French Data Library (daily file re-downloaded October 28, 2026; definitions checked September 14, 2026); prices are the daily closes retained for this calculation. These historical outputs use the stated window, and a new regression may produce different loadings. All investing involves risk, including possible loss of principal, and past performance does not guarantee future results. The methodology explains the calculation.
What are investment factors?
Eugene Fama and Kenneth French set size and value beside the market in a 1993 paper in the Journal of Financial Economics; their April 2015 five-factor model added profitability and investment. French's Data Library publishes every row below as a return series:
| Factor | What it captures | Classic measure |
|---|---|---|
| Market | Broad equity risk | Beta vs. the market |
| Size (SMB) | Small caps vs. large caps | "Small minus big" returns |
| Value (HML) | Cheap vs. expensive stocks | "High minus low" book-to-market |
| Momentum | Recent winners vs. losers | Returns over the prior 2 to 12 months |
| Profitability (RMW) | More vs. less profitable firms | "Robust minus weak" operating profitability |
The first three (market, size, value) form the Fama-French three-factor model. In the regressions below, those three explain between 88.3% and 99.5% of the daily movement of six US stock funds over August 2021 to May 2026, and no sector weight enters the model.
How do I measure my portfolio's factor exposure?
With a time-series regression of your portfolio's returns on the factors' returns, in five steps:
- Compute the portfolio's daily returns from the daily closes of what you hold, weighted by position size.
- Download the daily factor series. The Ken French Data Library linked above publishes the market, size and value factors alongside a daily risk-free rate.
- Subtract the risk-free rate from each day's portfolio return, which turns returns into excess returns.
- Match the two series by calendar date, dropping any day missing from either (more on why below).
- Fit an ordinary least squares regression of the excess returns on the three factors.
The fitted coefficients, the loadings, tell you how much of your movement each factor explains:
- A market loading of 1.2 → amplified equity exposure.
- A positive size loading → behaves like small caps; negative → mega-cap tilted.
- A negative value loading → growth-tilted; positive → value-tilted.
- The regression's R² is the share of return variation explained over the fitted window. Residuals are the individual daily differences between observed and fitted returns.
A meaningful regression needs 60 or more overlapping trading days. PortLens's Fama-French return projection, a hypothetical one-year estimate with a 95% band, uses the same regression and floor, but it is planned for Pro and available on no tier yet, so nothing in PortLens runs it on your portfolio today; our methodology documents its recipe.
Two practical details decide whether the output means anything.
Returns must be aligned by calendar date and never by row. US, London and crypto calendars differ, and matching the 200th observation of one series to the 200th of another compares different days. That biases every covariance toward zero, which makes a concentrated portfolio look diversified.
Recent dates simply drop. The published factor series runs a month or more behind the market (the October 28, 2026 file ends September 30), so the most recent weeks of your own price history have nothing to regress against. That is why the window here, set when these regressions were first run in August 2026, ends in May.
What do real factor loadings look like?
Below, each fund is regressed on its own, and the ± figure is the coefficient's standard error: how precisely the window pins the loading down.
| Fund | Market | Size (SMB) | Value (HML) | R² |
|---|---|---|---|---|
| VOO (S&P 500) | +0.98 ±0.00 | −0.11 ±0.00 | +0.01 ±0.00 | 99.5% |
| VUG (growth) | +1.14 ±0.01 | −0.14 ±0.01 | −0.35 ±0.01 | 97.2% |
| VTV (value) | +0.79 ±0.01 | −0.02 ±0.01 | +0.39 ±0.01 | 88.3% |
| VYM (dividend) | +0.80 ±0.01 | −0.01 ±0.01 | +0.42 ±0.01 | 88.6% |
| VB (small-cap) | +1.02 ±0.01 | +0.64 ±0.01 | +0.28 ±0.01 | 96.2% |
| VGT (technology) | +1.25 ±0.01 | −0.10 ±0.02 | −0.37 ±0.02 | 91.4% |
| VXUS (ex-US) | +0.75 ±0.02 | +0.09 ±0.03 | +0.12 ±0.02 | 66.8% |
The fund labels and the loadings agree, which is the first useful thing to establish: the model recovers what the fund names claim. A growth fund loads negatively on value; a value fund and a dividend fund load positively on it, at +0.39 and +0.42, nearly the same exposure bought under two different labels. VB has the largest size loading in this sample, at +0.64. Most other funds have negative size loadings; VXUS is a small positive exception at +0.09. A loading describes behavior relative to the chosen factors; it says nothing about a fund's complete holdings composition.
R² is the second thing worth reading. It says how much of the holding's daily movement the three factors explain at all: 99.5% for a broad index fund, 66.8% for an international one. The unexplained variation in VXUS can include currency effects, local-market conditions and other influences. R² alone cannot identify those causes or assign a share to each.
What does a factor tilt look like across a few holdings?
It can be larger than the tilt of the fund it resembles. Microsoft, Amazon and Alphabet share one factor profile, mega-cap growth, so a portfolio holding all three plus a growth ETF is exposed four times to the same driver: the stacking problem behind ETF overlap, one level deeper. The reason a sector chart misses it gets its own treatment in Diversification Beyond Sector Splits.
That trio is measurable as a portfolio. Equally weighted, Microsoft, Amazon and Alphabet regress to a market loading of +1.17 ±0.02, a size loading of −0.31 ±0.04 and a value loading of −0.50 ±0.03. Three tickers, and a growth tilt larger than the dedicated growth fund's. Add VUG and the tilt does not dilute: a 50/50 mix of VUG and VGT still computes to −0.36 on value, because both funds sit on the same side of it.
The contrast is what a real spread looks like. A 50/50 mix of VUG and VTV, a growth fund and a value fund, lands at +0.02 ±0.00 on value. Their estimated value loadings nearly offset in this window. That does not remove market risk or establish how many companies the funds share; the dated VTV vs VUG holdings comparison measures that separately.
The danger is regime risk: factors rotate. In Kenneth French's annual series, HML (value minus growth) fell in every year from 2017 to 2020, by 46.94% in 2020, then gained 25.60% in 2021 and 25.70% in 2022, and its sign has flipped twice more through 2025 (Data Library annual file, downloaded October 28, 2026). A single-factor portfolio doesn't just underperform when its factor rotates out; it does so all at once, across every holding, precisely because the holdings were never really different bets.
How do I read a loading I've just computed?
Four questions, in order:
- Is the loading distinguishable from zero? Compare it to its standard error. VTV's +0.39 ±0.01 is a real tilt. An estimate of +0.03 with a standard error of 0.04 is not clearly distinguishable from zero; the positive sign alone is weak evidence of a tilt.
- Is it large relative to the market loading? Every long equity portfolio loads near +1 on the market. That is not a finding. The size and value loadings are where portfolios actually differ from one another.
- What does R² leave out? A single stock is mostly not a factor story. Coca-Cola's daily returns over this window regress to a market loading of +0.38 ±0.03 with an R² of 14.9%: the three factors explain about a seventh of what it does. NVIDIA's R² is 58.6%, Apple's 57.0%. Diversified portfolios sit far higher: VOO at 99.5%. The more concentrated the portfolio, the more of its risk lives outside the model.
- Would a different window change the answer? It will. These loadings describe August 2021 to May 2026, a period with one particular rate cycle and one particular growth regime in it. A loading is a measurement, not a constant.
Can factor concentration be diversified away by adding holdings?
Not by adding more, only by adding different. Adding a fourth mega-cap growth stock to Microsoft, Amazon and Alphabet raises the position count by a third and moves the value loading further negative. Adding VTV, whose loading has the opposite sign, moves it toward zero. Both are "adding a holding". Only one is adding a bet. The same arithmetic applied to volatility is what the minimum variance frontier formalizes: a mix cancels risk only where its parts don't move together.
Is a factor tilt a problem?
Not by itself. Finance theory's nearest reference point is the market portfolio, which every investor's risky holdings match in William Sharpe's 1964 capital asset pricing model. Run through this regression, the US market factor loads exactly 1 on the market and 0 on size and value; VOO, the nearest of the seven funds above, sits at −0.11 and +0.01.
PortLens doesn't publish a target loading; a loading describes exposure. What it can't tell you is whether you meant it, and that takes questions only you can answer:
- Did you choose this tilt, or did it arrive with funds bought for other reasons?
- Has a factor that did well grown its own weight since you last measured, with no trade on your part?
- Do funds you hold for different jobs load on the same side of value?
A free portfolio scan shows company exposure, overlap and portfolio beta. Factor loadings need a separate regression: PortLens's Fama-French analysis is planned for Pro, and the free scan does not calculate them.
None of that says which tilt to hold: a negative value loading is not a flaw, a positive one is not a virtue, and the regression knows nothing about what you were trying to build.
What are the limits of factor models?
Three limits bound every loading here:
- It is descriptive and never predictive. A loading measured over one window says what a portfolio did and nothing about what it will do. Nothing here supports a return forecast, and the factor premia that appear in academic work are long-run historical averages with wide dispersion around them.
- The factors are a choice. Three factors is a convention; it is no fact about markets. Adding momentum or profitability changes every other loading, because factors are correlated with each other.
- Concentrated portfolios sit largely outside it. At an R² of 14.9%, a factor model is not describing Coca-Cola. Single-stock risk is the residual, and the residual is where a −60% company-specific move lives.
Key takeaways
- Measuring factor exposure takes one regression: daily excess returns on the market, size and value factors, matched by calendar date, read with each loading's standard error.
- Real loadings recover real labels: growth funds compute to −0.35 on value, value and dividend funds to +0.39 and +0.42, and only a small-cap fund carries a meaningful size loading at +0.64.
- Three mega-cap stocks held equally reached a −0.50 value loading, a bigger growth bet than the dedicated growth fund it resembles.
- Diversifying factors means opposite signs, not more line items: 50/50 growth and value computes to +0.02 on value; 50/50 growth and technology computes to −0.36.
- Read R² alongside the loadings. It tells you how much of the portfolio the model is entitled to speak about.
This article is for information and education only and is not investment advice. See our methodology and disclosures.
