Using Alphalens to Contrast Predictive and Non-Predictive Equity Factors
Notebook Alphalens
Summary
This notebook illustrates factor evaluation with Alphalens using a large-cap equity universe assigned to sectors. It compares a baseline factor based on each stock’s recent ten-day performance with a second factor constructed from future price changes. The latter intentionally looks ahead by several sessions, making it predictive by design. The notebook runs Alphalens tear sheets for both factors, including sector-level views and event-style returns, to show the difference between an ordinary signal and one contaminated with future information.
The example also explains how to align factor observations with pricing data: the price series should begin at the next available entry price, while subsequent prices provide exits for the chosen forward period. In this illustration, those are daily opening prices, so calculated returns are open-to-open. The key limitation is explicit: the predictive factor is an artificial demonstration that cannot be used as a live signal. The notebook shows analysis outputs but gives no independent test establishing real-world predictive value, and its small illustrative setup does not prove robustness.
Key ideas
- The notebook compares a recent-performance factor with a factor deliberately built from future prices.
- Alphalens tear sheets are used to inspect factor returns, sector differences, and event-style returns.
- Pricing should use the next available entry price and later prices for forward exits.
- The example calculates open-to-open returns using daily opening prices.
- The future-informed factor demonstrates lookahead bias rather than a deployable edge.
Tags
Full text
# Alphalens: predictive vs. non-predictive factor
# Alphalens: predictive vs. non-predictive factor
This is a very simply notebook in which we use Alphalens to analyse a predictive and a non-predictive factor. The goal is to have exemplifying output for both scenarios to make clear what to expect from Alphalens in the case of a predictive and a non-preditive factor.
```python
%pylab inline --no-import-all
import alphalens
import pandas as pd
import numpy as np
import datetime
```
```python
import warnings
warnings.filterwarnings('ignore')
```
Below is a simple mapping of tickers to sectors for a universe of 500 large cap stocks.
```python
sector_names = {
0 : "information_technology",
1 : "financials",
2 : "health_care",
3 : "industrials",
4 : "utilities",
5 : "real_estate",
6 : "materials",
7 : "telecommunication_services",
8 : "consumer_staples",
9 : "consumer_discretionary",
10 : "energy"
}
ticker_sector = {
"ACN" : 0, "ATVI" : 0, "ADBE" : 0, "AMD" : 0, "AKAM" : 0, "ADS" : 0, "GOOGL" : 0, "GOOG" : 0,
"APH" : 0, "ADI" : 0, "ANSS" : 0, "AAPL" : 0, "AMAT" : 0, "ADSK" : 0, "ADP" : 0, "AVGO" : 0,
"AMG" : 1, "AFL" : 1, "ALL" : 1, "AXP" : 1, "AIG" : 1, "AMP" : 1, "AON" : 1, "AJG" : 1, "AIZ" : 1, "BAC" : 1,
"BK" : 1, "BBT" : 1, "BRK.B" : 1, "BLK" : 1, "HRB" : 1, "BHF" : 1, "COF" : 1, "CBOE" : 1, "SCHW" : 1, "CB" : 1,
"ABT" : 2, "ABBV" : 2, "AET" : 2, "A" : 2, "ALXN" : 2, "ALGN" : 2, "AGN" : 2, "ABC" : 2, "AMGN" : 2, "ANTM" : 2,
"BCR" : 2, "BAX" : 2, "BDX" : 2, "BIIB" : 2, "BSX" : 2, "BMY" : 2, "CAH" : 2, "CELG" : 2, "CNC" : 2, "CERN" : 2,
"MMM" : 3, "AYI" : 3, "ALK" : 3, "ALLE" : 3, "AAL" : 3, "AME" : 3, "AOS" : 3, "ARNC" : 3, "BA" : 3, "CHRW" : 3,
"CAT" : 3, "CTAS" : 3, "CSX" : 3, "CMI" : 3, "DE" : 3, "DAL" : 3, "DOV" : 3, "ETN" : 3, "EMR" : 3, "EFX" : 3,
"AES" : 4, "LNT" : 4, "AEE" : 4, "AEP" : 4, "AWK" : 4, "CNP" : 4, "CMS" : 4, "ED" : 4, "D" : 4, "DTE" : 4,
"DUK" : 4, "EIX" : 4, "ETR" : 4, "ES" : 4, "EXC" : 4, "FE" : 4, "NEE" : 4, "NI" : 4, "NRG" : 4, "PCG" : 4,
"ARE" : 5, "AMT" : 5, "AIV" : 5, "AVB" : 5, "BXP" : 5, "CBG" : 5, "CCI" : 5, "DLR" : 5, "DRE" : 5,
"EQIX" : 5, "EQR" : 5, "ESS" : 5, "EXR" : 5, "FRT" : 5, "GGP" : 5, "HCP" : 5, "HST" : 5, "IRM" : 5, "KIM" : 5,
"APD" : 6, "ALB" : 6, "AVY" : 6, "BLL" : 6, "CF" : 6, "DWDP" : 6, "EMN" : 6, "ECL" : 6, "FMC" : 6, "FCX" : 6,
"IP" : 6, "IFF" : 6, "LYB" : 6, "MLM" : 6, "MON" : 6, "MOS" : 6, "NEM" : 6, "NUE" : 6, "PKG" : 6, "PPG" : 6,
"T" : 7, "CTL" : 7, "VZ" : 7,
"MO" : 8, "ADM" : 8, "BF.B" : 8, "CPB" : 8, "CHD" : 8, "CLX" : 8, "KO" : 8, "CL" : 8, "CAG" : 8,
"STZ" : 8, "COST" : 8, "COTY" : 8, "CVS" : 8, "DPS" : 8, "EL" : 8, "GIS" : 8, "HSY" : 8, "HRL" : 8,
"AAP" : 9, "AMZN" : 9, "APTV" : 9, "AZO" : 9, "BBY" : 9, "BWA" : 9, "KMX" : 9, "CCL" : 9,
"APC" : 10, "ANDV" : 10, "APA" : 10, "BHGE" : 10, "COG" : 10, "CHK" : 10, "CVX" : 10, "XEC" : 10, "CXO" : 10,
"COP" : 10, "DVN" : 10, "EOG" : 10, "EQT" : 10, "XOM" : 10, "HAL" : 10, "HP" : 10, "HES" : 10, "KMI" : 10
}
```
```python
import pandas_datareader.data as web
tickers = list(ticker_sector.keys())
pan = web.DataReader(tickers, "google", datetime.datetime(2017, 1, 1), datetime.datetime(2017, 6, 1))
```
The pricing data passed to alphalens should contain the entry price for the assets so it must reflect the next available price after a factor value was observed at a given timestamp. Those prices must not be used in the calculation of the factor values for that time. Always double check to ensure you are not introducing lookahead bias to your study.
The pricing data must also contain the exit price for the assets, for period 1 the price at the next timestamp will be used, for period 2 the price after 2 timestamps will be used and so on.
There are no restrinctions/assumptions on the time frequencies a factor should be computed at and neither on the specific time a factor should be traded (trading at the open vs trading at the close vs intraday trading), it is only required that factor and price DataFrames are properly aligned given the rules above.
In our example, before the trading starts every day, we observe yesterday factor values. The price we pass to alphalens is the next available price after that factor observation: the daily open price that will be used as assets entry price. Also, we are not adding additional prices so the assets exit price will be the following days open prices (how many days depends on 'periods' argument). The retuns computed by Alphalens will therefore based on assets open prices.
```python
pricing = pan['Open']
```
We'll use a naive factor as non-predictive factor, we'll rank stocks based on recent performance: stocks that performed well in the last 10 days will have high rank and vice versa.
```python
non_predictive_factor = pricing.pct_change(10)
non_predictive_factor = non_predictive_factor.stack()
non_predictive_factor.index = non_predictive_factor.index.set_names(['date', 'asset'])
```
To create a predictive factor we'll cheat: we will look at future prices to make sure we'll rank high stoks that will perform well and vice versa.
```python
lookahead_bias_days = 5
predictive_factor = pricing.pct_change(lookahead_bias_days)
# introduce look-ahead bias and make the factor predictive
predictive_factor = predictive_factor.shift(-lookahead_bias_days)
predictive_factor = predictive_factor.stack()
predictive_factor.index = predictive_factor.index.set_names(['date', 'asset'])
```
# Run Alphalens on the non-predictive factor
```python
non_predictive_factor_data = alphalens.utils.get_clean_factor_and_forward_returns(non_predictive_factor,
pricing,
quantiles=5,
bins=None,
groupby=ticker_sector,
groupby_labels=sector_names)
```
```python
alphalens.tears.create_full_tear_sheet(non_predictive_factor_data, by_group=True)
```
# Run Alphalens on the predictive factor
```python
predictive_factor_data = alphalens.utils.get_clean_factor_and_forward_returns(predictive_factor,
pricing,
quantiles=5,
bins=None,
groupby=ticker_sector,
groupby_labels=sector_names)
```
```python
alphalens.tears.create_full_tear_sheet(predictive_factor_data, by_group=True)
```
# Run Event Style Returns Analysis
## Non-predictive factor
```python
alphalens.tears.create_event_returns_tear_sheet(non_predictive_factor_data, pricing)
```
## Predictive factor
```python
alphalens.tears.create_event_returns_tear_sheet(predictive_factor_data, pricing)
```
Shown in full with attribution under the source's licence. Licence: Apache-2.0
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.