Better valuation is better investing.
The FFER is a comprehensive valuation ratio powered by machine learning.
Scroll down for the FFER table...

FFER basics

• Like P/E... but better
The FFER utilizes XGBoost to fit a curve to actual stock prices.
• 16 dimensions
Instead of just earnings or sales, the FFER is derived from 16 different company financial figures.
• Updated daily
The stock market moves and so do intrinsic valuations. Come back every day to see the current FFERs.

What does the FFER look like?

The "Fundamental Fitted Estimate Ratio" (FFER) is the ratio between the actual market price and the "Fundamental Fitted Estimate" (FFE) price. The FFE is the estimate generated by the machine learning model and is conceptually represented by the green line in the diagram above.

Example FFERs from large-cap stocks. Updated daily after market close.
Ticker ⇕Name ⇕Price ⇕FFE Price ⇕FFER ⇕
PYPLPayPal HoldingsPayPal Holdings$247.25$58.594.220
CHTRCharter CommunicationsCharter Communications$633.27$175.803.602
AMTAmerican Tower Corporation (REIT)American Tower Corporation (REIT)$216.88$105.532.055
DISThe Walt Disney CompanyThe Walt Disney Company$172.26$95.891.796
SPGIS&P GlobalS&P Global$313.14$175.911.780
JNJJohnson & JohnsonJohnson & Johnson$162.78$91.691.775
UNHUnitedHealth GroupUnitedHealth Group$352.19$201.871.745
LLYEli Lilly and CompanyEli Lilly and Company$198.48$116.181.708
NEENextEra EnergyNextEra Energy$82.81$55.711.486
LOWLowe's CompaniesLowe's Companies$170.76$115.441.479
PGThe Procter & Gamble CompanyThe Procter & Gamble Company$133.60$101.241.320
MSMorgan StanleyMorgan Stanley$74.99$60.351.243
ABTAbbott LaboratoriesAbbott Laboratories$112.57$92.371.219
KOThe Coca-Cola CompanyThe Coca-Cola Company$48.51$41.081.181
TMOThermo Fisher ScientificThermo Fisher Scientific$507.38$442.181.147
BAThe Boeing CompanyThe Boeing Company$210.71$187.801.122
FISFidelity National Information ServicesFidelity National Information Services$128.06$115.511.109
XOMExxon MobilExxon Mobil$48.84$45.871.065
COSTCostco WholesaleCostco Wholesale$354.47$335.731.056
MRKMerck & Co.Merck & Co.$83.19$79.621.045
UPSUnited Parcel ServiceUnited Parcel Service$156.28$152.771.023
UNPUnion PacificUnion Pacific$215.28$210.851.021
HONHoneywell InternationalHoneywell International$206.76$213.160.970
LMTLockheed MartinLockheed Martin$341.50$424.400.805
VZVerizon CommunicationsVerizon Communications$57.05$73.060.781
CSCOCisco SystemsCisco Systems$45.19$57.950.780
MMM3M Company3M Company$169.12$217.310.778
TXNTexas InstrumentsTexas Instruments$174.19$267.540.651
BACBank of AmericaBank of America$32.77$50.710.646
BMYBristol-Myers Squibb CompanyBristol-Myers Squibb Company$66.74$113.440.588
IBMInternational Business MachinesInternational Business Machines$129.02$270.800.476
CVSCVS HealthCVS Health$75.40$162.940.463
GILDGilead SciencesGilead Sciences$67.07$248.260.270
Show all 100Last updated EOD Tuesday January 19, 2021

Why is the FFER useful?

You can use the FFER as a valuation metric similar to the Price/Earnings, Price/Book, or EV/EBITDA ratios. The difference is that the FFER is comprehensive. Each FFER is calculated using 16 dimensions, including income, revenue, assets, liabilities, and dividends.

Like other valuation metrics, the FFER tells us the intrinsic value of the stock and whether it is cheap or expensive. If the actual price is lower than the fundamental price, it implies that it is cheap relative to the market. Likewise, if the actual price is higher than the fundamental price, it implies that it is expensive relative to the market.

How does the FFER work?

The FFER is the ratio between the actual price and the fundamental price. The fundamental price is the output of a machine learning model trained with 16 fundamental dimensions as independent (X) variables and the actual price as the dependent (Y) variable. For those unfamiliar with machine learning, you can think of it as "curve fitting." So for FFER, we are "fitting" an equation to predict any stock price given the fundamentals of a public company.

Since real-world data tends to be messy, even the best machine learning models are subject to error. Few points actually fall on the curve. For most machine learning applications, this error is treated as regrettable. For the FFER, retrieving the magnitude of the error is the goal.

The "fitted curve" represents the best-guess valuation function of the market. If the actual price is significantly above or below the curve, either the stock is incorrectly valued, or there is some other significant information impacting the price.

A more detailed technical explanation is available here.

Is a low FFER generally a good buy?

Not exactly. Because the FFER is derived from only basic financial statements, it is missing a lot of information. It does not capture consumer sentiment, economic conditions, price momentum, etc. Indeed, stocks with high or low FFERs tend to have justifications for their ratios. This might be an exciting product, a bankruptcy proceeding, or some recent economic trend. Additionally, because the model is trained daily with EOD prices, it only signals the stock's value relative to the market on a single day. It cannot predict broader market movements.

How is the FFER useful to me?

Given that the FFER is just a better valuation metric, you can substitute it wherever you would use the P/E or any other metric. If you are a value investor, you can utilize the FFER as a stock screener to find cheap stocks worthy of closer investigation. If you do algorithmic trading, you can use the FFER as an input to your model.

Is the FFER correlated with other valuation metrics?

Yes. Being derived from the same data, the FFER is correlated with other valuation metrics.

MetricCorrelation (Pearson's)
Price/Earnings (MRQ)0.074
Price/Sales (TTM)0.46
Price/Book (MRQ)0.054

How do I get this data?

The FFER model is re-built and prices are updated on trading days one hour after US markets close (5:30PM Eastern Time). The 100 largest stocks by market cap will remain free on this page indefinitely.

The FFERs for every US company listed on NYSE and Nasdaq will soon be available by subscription. Until then, leave your email to:

Join the mailing list

Your inbox will be respected. You will get no more than two emails per month - if that.
Your privacy is important to us. We'll never share your email with any third parties.