Research campaign · Iteration 1 · unassessed
Berg turning-point families — public-proxy campaign
Which public-proxy interpretations of Berg price, volume, breadth, and composite families remain useful research even though exact proprietary rules are untestable?
- Expressions
- 4
- Logged trials
- Not recorded
- Independent events
- Not assessed
- Evidence
- unassessed
What the research found
Exact Berg rules are untestable; public proxies failed subperiod and overlay gates.
Negative results stay in the Research Library; they are not official admissions.
Mechanism and falsifiers
Not recorded in this iteration.
Not recorded in this iteration.
Confidence and limitations
Proxy-only. Proprietary Berg series not in market.sqlite.
Do not invent __BERG_*__ history.
Not recorded in this iteration.
Compare expressions
Download evidenceExploratory results. Check each period, proxy and cost assumption before comparing. — means not recorded.
| Expression / family | CAGR | Sharpe | Max drawdown | Test period | Assessment |
|---|---|---|---|---|---|
| berg-f1.percentile20.threshold0.05.hold20berg-f1-price | — | — | — | Not recorded |
exploratory |
| berg-f2.dvol-uvol.threshold1.5.hold20berg-f2-volume | — | — | — | Not recorded |
exploratory |
| berg-f3.hl-thrust.threshold0.615.hold20berg-f3-breadth | — | — | — | Not recorded |
exploratory |
| berg-f4.count.threshold1.5.hold20berg-f4-composite | — | — | — | Not recorded |
exploratory |
Open an expression to inspect its rules and request confirmation. The request must be submitted by a trusted repository collaborator.
berg-f1.percentile20.threshold0.05.hold20
- variant id
berg-f1.percentile20.threshold0.05.hold20
- family id
berg-f1-price
- parameters
- threshold
0.05
- holding period
20
- created by
public_proxy
- reason tested
price-extreme proxy; not Berg-verbatim
- status
exploratory
- tags
interesting_negative_result
data_limited
berg-f2.dvol-uvol.threshold1.5.hold20
- variant id
berg-f2.dvol-uvol.threshold1.5.hold20
- family id
berg-f2-volume
- parameters
- threshold
1.5
- holding period
20
- created by
public_proxy
- reason tested
down-volume dominance proxy; TRIN history unavailable
- status
exploratory
- tags
interesting_negative_result
data_limited
berg-f3.hl-thrust.threshold0.615.hold20
- variant id
berg-f3.hl-thrust.threshold0.615.hold20
- family id
berg-f3-breadth
- parameters
- threshold
0.615
- holding period
20
- created by
public_proxy
- reason tested
Zweig-style HIGN/(HIGN+LOWN) proxy
- status
exploratory
- tags
interesting_negative_result
regime_dependent
berg-f4.count.threshold1.5.hold20
- variant id
berg-f4.count.threshold1.5.hold20
- family id
berg-f4-composite
- parameters
- threshold
1.5
- holding period
20
- created by
public_proxy
- reason tested
count of public extremes; not proprietary composite
- status
exploratory
- tags
interesting_negative_result
uninvestable
Interactive lab
Interactive history unavailableLoading available evidence…
Research record
Source claims, inferred rules, experiments and the evidence behind the assessment.
Source
- kind
whitepaper
- links
- https://miltonberg.com/research-process
research/findings/berg-coverage-ledger-qm-tykd.5.md
- prior experiments
qm-tykd.1
qm-tykd.2
qm-tykd.3
qm-tykd.4
What the source claims
Berg discloses four families: price/boundary, volume/TRIN, breadth/thrust, composite synthesis.
No numeric thresholds, lookbacks, or composite weights are disclosed.
Public proxies: SPY percentile, UVOL/DVOL, HIGN/LOWN thrust, count>=2 composite.
Native 30k daily Berg feeds are not redistributable; no synthetic Berg history.
Rules actually disclosed
Berg discloses four families: price/boundary, volume/TRIN, breadth/thrust, composite synthesis.
No numeric thresholds, lookbacks, or composite weights are disclosed.
What had to be inferred
Public proxies: SPY percentile, UVOL/DVOL, HIGN/LOWN thrust, count>=2 composite.
Research questions
Which public-proxy interpretations of Berg price, volume, breadth, and composite families remain useful research even though exact proprietary rules are untestable?
Data
- inputs
SPY
INDEX:HIGN
INDEX:LOWN
USI:UVOL
USI:DVOL
- native berg
False
Baseline implementation
- variant id
berg-f1.percentile20.threshold0.05.hold20
- family id
berg-f1-price
- parameters
- threshold
0.05
- holding period
20
- created by
public_proxy
- reason tested
price-extreme proxy; not Berg-verbatim
- status
exploratory
- metrics
- label
exploratory
- tags
interesting_negative_result
data_limited
What to try interactively
- name
threshold
- type
float
- default
0.05
Suggested next research
Keep F2–F4 as documented negative families; do not promote.
Trial ledger
- iteration number
1
- objective
preserve rejected Berg proxies as playable research
Next questions
Keep F2–F4 as documented negative families; do not promote.
Review status
awaiting research feedback. Research publication does not imply official admission.
Return to pending research