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 is better) |
| volatility |
Standard deviation of returns over the past N days |
Negative (lower is better) |
| volume_ratio |
Today's volume / N-day average volume |
Positive |
If extra_fields are available (China A-shares), you can also add:
pe_factor: 1/PE (the larger, the cheaper)pb_factor: 1/PBroe_factor: ROE (the larger, the better)
Parameters
| Parameter |
Default |
Description |
| momentum_window |
20 |
Momentum lookback window |
| vol_window |
20 |
Volatility lookback window |
| top_n |
3 |
Number of selected stocks |
| rebalance_freq |
20 |
Rebalancing frequency (trading days) |
Common Pitfalls
- Cross-sectional standardization requires at least 3 stocks, otherwise Z-scores are meaningless
- Keep the previous signal unchanged between rebalance dates (do not rerank every day)
- Factors have different directions: momentum is positively sorted, volatility is negatively sorted, so directions must be aligned before standardization
- Portfolio weights must be normalized: each TopN stock gets 1/N, all others get 0
Dependencies
pip install pandas numpy
Signal Convention
1/N = selected into TopN (equal-weight long), 0 = not selected
Zoo Signal Engine (new in 0.1.8)
When the user wants to compose 1-N alphas drawn from the Alpha Zoo (450+ pre-built factors) into a multi-factor strategy, use ZooSignalEngine.from_zoo(...) from zoo_signal_engine.py instead of the old per-symbol example_signal_engine.py. The new engine operates on wide-panel dict[str, pd.DataFrame] inputs (the same shape the registry's Alpha.compute(panel) contract uses), redistributes weights when any alpha fails or is skipped, and supports long-only (top_n), short-only (bottom_n), and long-short (top_n + bottom_n) signal modes. It also exposes a generate(data_map) adapter so it drops straight into the existing run_backtest pipelines.
from src.factors.registry import Registry
from zoo_signal_engine import ZooSignalEngine
registry = Registry()
# Browse candidates with registry.list(theme="momentum") -- see the alpha-zoo skill.
alpha_ids = ["alpha101_001", "alpha101_012", "guotai_191_003"]
engine = ZooSignalEngine.from_zoo(alpha_ids, top_n=10, bottom_n=10, standardize=True)
# Feed into a panel-aware backtest, or via .generate(data_map) into the bundled engines.
signal_panel = engine.compute_signal(panel) # DataFrame, same shape as panel["close"]
Cross-references:
- See the
alpha-zoo skill for browsing the alpha catalogue, filtering by theme/universe, and inspecting __alpha_meta__ records.
example_signal_engine.py is kept for legacy per-symbol workflows that compute factors directly from raw OHLCV; new code should prefer zoo_signal_engine.py so it benefits from the 450+ zoo alphas, registry-level NaN/inf guardrails, and per-alpha skip isolation.
1---
2name: multi-factor
3description: Multi-factor cross-sectional stock ranking. Combines factor standardization, equal-weight or IC-weighted scoring, and TopN portfolio construction. Suitable for multi-instrument portfolio strategies.
4category: strategy
5---
6
7# Multi-Factor Cross-Sectional Stock Ranking
8
9## Purpose
10
11On 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.
12
13## Signal Logic
14
151. **Factor calculation**: calculate N factors for each stock (such as momentum, value, and quality)
162. **Cross-sectional standardization**: standardize each factor on the cross-section with Z-score normalization (subtract mean, divide by standard deviation)
173. **Composite scoring**: sum the factors with equal weights (or custom weights) to obtain a composite score
184. **Rank and select**: go long the TopN names, with weight = 1/N for each
19
20## Built-In Factors
21
22| Factor Name | Calculation Method | Direction |
23|--------|---------|------|
24| momentum | Return over the past N days | Positive (higher is better) |
25| reversal | Return over the past 5 days | Negative (lower is better) |
26| volatility | Standard deviation of returns over the past N days | Negative (lower is better) |
27| volume_ratio | Today's volume / N-day average volume | Positive |
28
29If `extra_fields` are available (China A-shares), you can also add:
30- `pe_factor`: 1/PE (the larger, the cheaper)
31- `pb_factor`: 1/PB
32- `roe_factor`: ROE (the larger, the better)
33
34## Parameters
35
36| Parameter | Default | Description |
37|------|--------|------|
38| momentum_window | 20 | Momentum lookback window |
39| vol_window | 20 | Volatility lookback window |
40| top_n | 3 | Number of selected stocks |
41| rebalance_freq | 20 | Rebalancing frequency (trading days) |
42
43## Common Pitfalls
44
45- Cross-sectional standardization requires at least 3 stocks, otherwise Z-scores are meaningless
46- Keep the previous signal unchanged between rebalance dates (do not rerank every day)
47- Factors have different directions: momentum is positively sorted, volatility is negatively sorted, so directions must be aligned before standardization
48- Portfolio weights must be normalized: each TopN stock gets 1/N, all others get 0
49
50## Dependencies
51
52```bash
53pip install pandas numpy
54```
55
56## Signal Convention
57
58- `1/N` = selected into TopN (equal-weight long), `0` = not selected
59
60## Zoo Signal Engine (new in 0.1.8)
61
62When the user wants to compose 1-N alphas drawn from the Alpha Zoo (450+ pre-built factors) into a multi-factor strategy, use `ZooSignalEngine.from_zoo(...)` from `zoo_signal_engine.py` instead of the old per-symbol `example_signal_engine.py`. The new engine operates on wide-panel `dict[str, pd.DataFrame]` inputs (the same shape the registry's `Alpha.compute(panel)` contract uses), redistributes weights when any alpha fails or is skipped, and supports long-only (`top_n`), short-only (`bottom_n`), and long-short (`top_n` + `bottom_n`) signal modes. It also exposes a `generate(data_map)` adapter so it drops straight into the existing `run_backtest` pipelines.
63
64```python
65from src.factors.registry import Registry
66from zoo_signal_engine import ZooSignalEngine
67
68registry = Registry()
69# Browse candidates with registry.list(theme="momentum") -- see the alpha-zoo skill.
70alpha_ids = ["alpha101_001", "alpha101_012", "guotai_191_003"]
71engine = ZooSignalEngine.from_zoo(alpha_ids, top_n=10, bottom_n=10, standardize=True)
72# Feed into a panel-aware backtest, or via .generate(data_map) into the bundled engines.
73signal_panel = engine.compute_signal(panel) # DataFrame, same shape as panel["close"]
74```
75
76Cross-references:
77- See the `alpha-zoo` skill for browsing the alpha catalogue, filtering by `theme`/`universe`, and inspecting `__alpha_meta__` records.
78- `example_signal_engine.py` is kept for legacy per-symbol workflows that compute factors directly from raw OHLCV; **new code should prefer `zoo_signal_engine.py`** so it benefits from the 450+ zoo alphas, registry-level NaN/inf guardrails, and per-alpha skip isolation.
79
HKUDS