multi-factor
Multi-factor ranks stocks by computing and standardizing multiple factors—momentum, reversal, volatility, and volume—then combines them into a composite score to select top performers for equal-weight portfolios. Built-in support for value metrics like PE and ROE on supported markets. The newer ZooSignalEngine integrates 450+ pre-built alphas from the registry for flexible long-only, short-only, or long-short strategies.
Multi-factor provides cross-sectional stock ranking by combining standardized factors into composite scores for portfolio selection.
AI-generated summary based on this skill's SKILL.md
Install
HKUDS/Vibe-Trading/multi-factor · repository language: Python
git clone https://github.com/HKUDS/Vibe-Trading
cp -r Vibe-Trading/agent/src/skills/multi-factor ~/.claude/skills/multi-factorFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does multi-factor build a multi-factor stock ranking system?
Multi-factor ranks stocks by computing and standardizing multiple factors—momentum, reversal, volatility, and volume—then combines them into a composite score to select top performers for equal-weight portfolios. It standardizes each factor using z-score normalization across the stock universe, then weights and aggregates them to produce a single ranking that identifies the highest-quality candidates for portfolio construction.
What is cross sectional factor model methodology in multi-factor?
Multi-factor uses cross-sectional factor analysis to standardize and composite multiple factors across a stock universe at a single point in time. This approach normalizes each factor independently, allowing you to combine momentum, value, quality, and volatility metrics on equal footing. The cross-sectional design ensures fair comparison across all stocks regardless of their absolute values.
Can multi-factor combine value, momentum, and quality factors?
Yes. Multi-factor supports momentum, reversal, volatility, and volume factors natively, plus built-in value metrics like PE and ROE on supported markets. The ZooSignalEngine extension integrates 450+ pre-built alphas from the registry, enabling flexible composition of value, momentum, quality, and custom factors into long-only, short-only, or long-short strategies.
How does multi-factor implement factor standardization for ranking?
Multi-factor standardizes each factor using z-score normalization across your stock universe, converting raw values into comparable scores centered at zero. This standardization ensures that factors with different scales—like price momentum and earnings yield—can be fairly weighted and combined into a composite ranking score for portfolio selection.
What portfolio selection methods does multi-factor support?
Multi-factor selects top-ranked stocks using cross-sectional factor analysis and composite scoring. It supports equal-weight factor combination for straightforward multi-factor strategies, and IC-weighted factor scoring for backtesting scenarios where you want to weight factors by their information coefficient. Both methods feed into topN portfolio selection to build your final holdings.
How can I use multi-factor for multi-factor strategy backtesting?
Multi-factor enables backtesting via equal-weight or IC-weighted factor scoring. Compute and standardize your chosen factors, combine them into a composite score, select your topN stocks, and rebalance at your chosen frequency. The ZooSignalEngine also lets you compose alphas from the Alpha Zoo registry into multi-factor strategies for more sophisticated signal generation and long-short portfolio testing.
SKILL.md
rendered from the published skill — quoted content, verbatim
Multi-Factor Cross-Sectional Stock Ranking
Purpose
On the same time cross-section, compute multiple factor values for many stocks, standardize them, combine them into a composite score, and select the top-ranked stocks to build a portfolio.
Signal Logic
- Factor calculation: calculate N factors for each stock (such as momentum, value, and quality)
- Cross-sectional standardization: standardize each factor on the cross-section with Z-score normalization (subtract mean, divide by standard deviation)
- Composite scoring: sum the factors with equal weights (or custom weights) to obtain a composite score
- Rank and select: go long the TopN names, with weight = 1/N for each
Built-In Factors
| Factor Name | Calculation Method | Direction |
|---|---|---|
| momentum | Return over the past N days | Positive (higher is better) |
| reversal | Return over the past 5 days | Negative (lower |
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 3 files
agent/src/skills/multi-factor/SKILL.md
agent/src/skills/multi-factor/example_signal_engine.py
agent/src/skills/multi-factor/zoo_signal_engine.py