quantmodel — Improve Aspect RMM corr vs AS

Objective

Improve Aspect RMM corr vs AS.

Notes: Aspect RMM corr 0.896→0.933 via DBC→PDBC stitch + require_positive_defensive. Official verify PASS CAGRΔ +1.49%. Hist-alloc 10/10. Residual 2017/2021 AS-flat months. Findings: aspect-rmm-corr-t121.md

Approach

Reuses existing report research/findings/aspect-rmm-corr-t121.md — tables/metrics preserved verbatim via source_report pointer. Body below summarizes grounded evidence from that report and adjacent artifacts.

Files / code / data changed

Associated commits (inferred from log grep t121):

75424585 research: t121 Aspect RMM corr 0.896→0.933 (DBC stitch + abs-pos) (#105)
75424585 research: t121 Aspect RMM corr 0.896→0.933 (DBC stitch + abs-pos) (#105)
Source report: research/findings/aspect-rmm-corr-t121.md
Task-history entry: research/findings/task-history.json#t121

Results

Key table from source report (preserved):

variant	monthly corr	hist-alloc match	notes
t105 PDBC-only panel (IPO 2014-11)	0.896	10/10 recent	baseline
DBC→PDBC stitch only	0.921	10/10	early-2015 signals restored
stitch + require_positive_defensive	0.933	10/10	shipped
EFA/EEM/DBC traded (not live labels)	0.930	breaks IEMG/PDBC	rejected
proxy signals→live holds + abs-pos	0.934	recent OK	tiny lift; skipped for complexity
VAA/half CBF blends	≤0.86	fails snap months	rejected
alt lookbacks / SMA canaries / thr≠0	≤0.922	—	no lift over stitch

Conclusions and metrics are in research/findings/aspect-rmm-corr-t121.md; see detail page for preserved tables/metrics.

Conclusions

Aspect RMM corr 0.896→0.933 via DBC→PDBC stitch + require_positive_defensive. Official verify PASS CAGRΔ +1.49%. Hist-alloc 10/10. Residual 2017/2021 AS-flat months. Findings: aspect-rmm-corr-t121.md

Problems / follow-ups

See source report or PR discussion for follow-ups. No unsupported follow-ups fabricated.