Methodology

How the Farlens composite score is built, how it is tested, and what the tests actually said — published in full, because a score you can't interrogate is an opinion with a number attached.

Why publish this at all? The method is not the moat — the accumulated event history and the execution are. Publishing it, including the unflattering grade, is what separates an analytical tool from an unfalsifiable claim. If a claim on this page can't be checked, tell us.

The composite score

Every name Farlens covers — equity or crypto — gets a composite score built from twelve weighted measurements across three families. Every individual weight is published on the analytical indicator page; the summary is:

Price and money flow (54%) — trend, money flow index, on-balance volume, momentum, accumulation/distribution and volume surge. Deliberately weighted toward measurements that track money rather than price alone.
Positioning and flow (34%) — crypto derivatives positioning (open interest, funding rates, liquidations), premium or discount to the 200-week moving average, sector rotation against the sector ETF, and FINRA off-exchange short volume.
The world outside the chart (12%) — geopolitical event exposure mapped to affected sectors, and an engagement-weighted social narrative measurement scored against each name's own trailing baseline.

Two facts worth stating plainly, because they cut against how this kind of product is usually marketed. The geopolitical overlay carries 6.9% of the composite — it is the most distinctive thing we measure, and it was never the whole score. And crypto is not a bolt-on: the two crypto-specific components together carry 19%, nearly three times the geopolitical weight.

Credit conditions are tracked as a separate market-wide backdrop rather than a per-name component — see credit spreads, explained. Components are weighted and combined into a single bounded score, and two design rules matter more than the weights themselves:

A missing measurement is missing, not neutral. When a component can't be computed, it is excluded from the composite rather than entered as zero — a zero would silently dilute every other measurement and read as "neutral" when the truth is "no data".
At launch, scores are designed to be computed fresh at read time, rather than presenting a cached prior-day score with a current timestamp.

How it was tested

The current internal assessment uses walk-forward validation: the score is fitted on an earlier span of history and judged only on a later span it has not seen, then the process rolls forward. Both the in-sample and out-of-sample legs are annualised before comparison so window length does not distort the comparison. Dataset size, fold count and numerical ratios are not published while the reproducibility file and evidence review remain incomplete.

Walk-forward matters because a single train/test split can flatter. The current internal assessment is WEAK and not robust. It is published as a limitation, not as a verified performance claim.

Historical-results limitation. The composite grades WEAK on the current walk-forward test and is not robust. Historical, backtested and walk-forward results do not guarantee future results; in-sample and walk-forward results differ, and the absolute magnitudes were small. Numerical result claims are withheld pending a complete reproducibility file and evidence review. Nothing here implies a forward return.

At launch, each reading is designed to be point-in-time, with no look-ahead. A reading will be recorded from the data available at the measurement time rather than reconstructed later with hindsight. Backfilled history will be labelled and kept separate from any presentation that could otherwise imply a live track record.

What the score is not

It is not a recommendation. Farlens publishes no buy/sell calls, no price targets, no entry or exit levels — on any surface, ever.
It is not a prediction of any single outcome. It is a summary of present conditions across twelve measured inputs, with the components visible so you can disagree with any of them.
It is never presented one-sided. Every read carries the bull case and the bear case together.

Historical analogues

Historical analogues are planned as descriptive context with sample sizes and limitations displayed. They are not currently available, and no forward-return-by-band figures are published or implied.

Data sources and boundaries

Farlens is designed to use public data and third-party data licensed where applicable. The analysis layer — scoring, exposure mapping and planned analogues — is Farlens's own. Features that depend on unresolved third-party rights remain planned and will not be activated until the required licence and technical evidence is verified. Live daily readings are not yet available; public educational material and methodology are available now. Farlens does not republish upstream raw feeds.