ml4t-evaluate-factor skillA
ml4t-evaluate-factor is agent-read markdown (skill) from ml4t/skills: Evaluate alpha factor quality with IC analysis, quantile spreads, turnover, and decay. Use when deciding whether a signal has enough predictive power to trade..
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 Evaluation
A factor that looks predictive may be untradeable due to high turnover, rapid decay, or non-monotonic quantile spreads. Comprehensive evaluation before portfolio integration prevents costly live failures.
## The Problem
Reporting a single backtest Sharpe ratio conflates signal quality with portfolio construction. A factor with IC 0.03 and low turnover can be more valuable than one with IC 0.05 and 80% daily turnover - whether IC is sufficient depends on breadth, turnover costs, and regime stability. Without decomposing signal quality into IC, quantile monotonicity, turnover, and decay, you cannot diagnose why a strategy fails or how to improve it.
## The Pattern
### WRONG
```python
# Evaluate only via backtest Sharpe - hides factor-level issues
returns = run_backtest(signal)
sharpe = returns.mean() / returns.std() * np.sqrt(252)
print(f"Sharpe: {sharpe:.2f}") # No idea why it works or doesn't
```
### CORRECT
```python
import numpy as np
from scipy import stats
# 1. Information Coefficient: rank correlation with forward returns
def compute_ic_series(signal, forward_returns, timestamps):
"""Per-period rank IC between signal and forward returns."""
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-evaluate-factor@git:20260901.c415df0mdr add ml4t/skills/ml4t-evaluate-factor@sha256:2919eb8dc6215dc8Pin 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_useqyvaln4mih7v7)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 4,748 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,758 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 (4748 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_useqyvaln4mih7v7 GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-evaluate-factor GET https://markdownregistry.com/api/v1/blob/2919eb8dc6215dc8681d84d3a25ba671f78d54d537271863838164fa5f63cbbe
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.