canli-mcp / Quant finance
Factor model regression (alpha and betas)
Regress a strategy's excess returns on factor returns (e.g. Fama-French market, size, value, momentum) with Newey-West errors: annualized alpha, its t-stat, factor betas and R-squared.
The tool is factor_regression in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It comes from canli-quant-mcp, which canli-mcp includes, and it is also its own server.
Arguments
| Argument | Required | Type |
|---|---|---|
returns | yes | number[] |
factors | yes | number[][] |
factor_names | no | string[] |
periods_per_year | no | number |
lags | no | integer |
How a model reaches it
Ask in plain words. The model finds factor_regression with canli-mcp's find_tool, reads its arguments with describe_tool if it needs to, and runs it with run_tool. The call has this shape, with your values in place of the angle brackets:
{
"name": "factor_regression",
"arguments": {
"returns": "<number[]>",
"factors": "<number[][]>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to factor_regression on these words: factor, model, fama, french, carhart, alpha, betas, exposures, attribution, newey, west, market, smb, hml, momentum.
More
Nothing here is investment advice.