ml4t-factor-research skillA
ml4t-factor-research is agent-read markdown (skill) from ml4t/skills: Systematic factor research from hypothesis through IC analysis, decay profiling, and capacity assessment. Use when developing a new alpha factor end-to-end..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Factor Research Workflow
Testing one factor on one period and deploying is data mining. Systematic factor research requires IC significance, stability across subperiods, decay profiling, and capacity estimation before any factor enters a model.
## The Problem
A researcher computes 12-month momentum, sees rank IC of 0.04, and adds it to
the model. Six months later the factor collapses because the original test
never checked significance, stability, decay, or capacity.
## The Pattern
### WRONG
```python
# Test one factor, one period, deploy on a single positive number
from scipy.stats import spearmanr
factor = prices.pct_change(252) # 12-month momentum
fwd_ret = prices.pct_change(21).shift(-21) # 1-month forward return
ic, _ = spearmanr(factor.dropna(), fwd_ret.dropna())
print(f"IC: {ic:.3f}") # 0.04 - looks good, ship it
```
### CORRECT
```python
import numpy as np
import polars as pl
from scipy.stats import spearmanr
ic_series = []
for date in rebalance_dates:
cross_section = data.filter(pl.col("timestamp") == date)
ic, _ = spearmanr(cross_section["factor"], cross_section["fwd_ret"])
ic_series.append({"timestamp": date, "ic": ic})
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-factor-research@git:20260901.297789fmdr add ml4t/skills/ml4t-factor-research@sha256:cd93000c5430f613Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ls3grwymzeznixcx)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.297789f latest | 2026-09-01 | 297789f | 4,747 B | A | view · diff |
| git:20260901.c415df0 | 2026-09-01 | c415df0 | 4,518 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,524 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4747 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ml4t/skills · 19 stars · license Apache-2.0 · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ls3grwymzeznixcx GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-factor-research GET https://markdownregistry.com/api/v1/blob/cd93000c5430f613644c1a5089f731f55514bc3edae721468d3c0ca94a6bb2bf
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.