We Used 5 Outlier Detection Strategies on a Actual Dataset: They Disagreed on 96% of Flagged Samples

Picture by Writer

# Introduction

All tutorials on knowledge science make detecting outliers look like fairly simple. Take away all values larger than three commonplace deviations; that is all there’s to it. However when you begin working with an precise dataset the place the distribution is skewed and a stakeholder asks, “Why did you take away that knowledge level?” you all of a sudden notice you do not have a very good reply.

So we ran an experiment. We examined 5 of essentially the most generally used outlier detection strategies on an actual dataset (6,497 Portuguese wines) to search out out: do these strategies produce constant outcomes?

They did not. What we realized from the disagreement turned out to be extra beneficial than something we might have picked up from a textbook.

Picture by Writer

We constructed this evaluation as an interactive Strata pocket book, a format you should utilize in your personal experiments utilizing the Knowledge Challenge on StrataScratch. You’ll be able to view and run the total code right here.

# Setting Up

 
Our knowledge comes from the Wine High quality Dataset, publicly out there by way of UCI’s Machine Studying Repository. It accommodates physicochemical measurements from 6,497 Portuguese “Vinho Verde” wines (1,599 purple, 4,898 white), together with high quality scores from skilled tasters.

We chosen it for a number of causes. It is manufacturing knowledge, not one thing generated artificially. The distributions are skewed (6 of 11 options have skewness ( > 1 )), so the info don’t meet textbook assumptions. And the standard scores allow us to examine if the detected “outliers” present up extra amongst wines with uncommon scores.

Under are the 5 strategies we examined:

# Discovering the First Shock: Inflated Outcomes From A number of Testing

 
Earlier than we might examine strategies, we hit a wall. With 11 options, the naive strategy (flagging a pattern primarily based on an excessive worth in no less than one function) produced extraordinarily inflated outcomes.

IQR flagged about 23% of wines as outliers. Z-Rating flagged about 26%.

When almost 1 in 4 wines get flagged as outliers, one thing is off. Actual datasets don’t have 25% outliers. The issue was that we had been testing 11 options independently, and that inflates the outcomes.

The maths is easy. If every function has lower than a 5% likelihood of getting a “random” excessive worth, then with 11 impartial options:
[ P(text{at least one extreme}) = 1 – (0.95)^{11} approx 43% ]

In plain phrases: even when each function is completely regular, you’d count on almost half your samples to have no less than one excessive worth someplace simply by random likelihood.

To repair this, we modified the requirement: flag a pattern solely when no less than 2 options are concurrently excessive.

 

 
Altering min_features from 1 to 2 modified the definition from “any function of the pattern is excessive” to “the pattern is excessive throughout a couple of function.”

This is the repair in code:

# Depend excessive options per pattern
outlier_counts = (np.abs(z_scores) > 3.5).sum(axis=1)
outliers = outlier_counts >= 2

# Evaluating 5 Strategies on 1 Dataset

 
As soon as the multiple-testing repair was in place, we counted what number of samples every methodology flagged:

 

 
This is how we arrange the ML strategies:

from sklearn.ensemble import IsolationForest
from sklearn.neighbors import LocalOutlierFactor
 
iforest = IsolationForest(contamination=0.05, random_state=42)
lof = LocalOutlierFactor(n_neighbors=20, contamination=0.05)

Why do the ML strategies all present precisely 5%? Due to the contamination parameter. It requires them to flag precisely that share. It is a quota, not a threshold. In different phrases, Isolation Forest will flag 5% no matter whether or not your knowledge accommodates 1% true outliers or 20%.

# Discovering the Actual Distinction: They Determine Completely different Issues

 
This is what stunned us most. Once we examined how a lot the strategies agreed, the Jaccard similarity ranged from 0.10 to 0.30. That is poor settlement.

Out of 6,497 wines:

• Solely 32 samples (0.5%) had been flagged by all 4 major strategies
• 143 samples (2.2%) had been flagged by 3+ strategies
• The remaining “outliers” had been flagged by only one or 2 strategies

You may suppose it is a bug, however it’s the purpose. Every methodology has its personal definition of “uncommon”:

 

 
If a wine has residual sugar ranges considerably greater than common, it is a univariate outlier (Z-Rating/IQR will catch it). But when it is surrounded by different wines with related sugar ranges, LOF will not flag it. It is regular throughout the native context.

So the true query is not “which methodology is finest?” It is “what sort of uncommon am I looking for?”

# Checking Sanity: Do Outliers Correlate With Wine High quality?

 
The dataset consists of skilled high quality scores (3-9). We wished to know: do detected outliers seem extra continuously amongst wines with excessive high quality scores?

 

 
Excessive-quality wines had been twice as prone to be consensus outliers. That is a very good sanity examine. In some instances, the connection is evident: a wine with approach an excessive amount of risky acidity tastes vinegary, will get rated poorly, and will get flagged as an outlier. The chemistry drives each outcomes. However we will not assume this explains each case. There may be patterns we’re not seeing, or confounding components we have not accounted for.

# Making Three Selections That Formed Our Outcomes

// 1. Utilizing Strong Z-Rating Moderately Than Normal Z-Rating

A Normal Z-Rating makes use of the imply and commonplace deviation of the info, each of that are affected by the outliers current in our dataset. A Strong Z-Rating as an alternative makes use of the median and Median Absolute Deviation (MAD), neither of which is affected by outliers.

In consequence, the Normal Z-Rating recognized 0.8% of the info as outliers, whereas the Strong Z-Rating recognized 3.5%.

# Strong Z-Rating utilizing median and MAD
median = np.median(knowledge, axis=0)
mad = np.median(np.abs(knowledge - median), axis=0)
robust_z = 0.6745 * (knowledge - median) / mad

// 2. Scaling Pink And White Wines Individually

Pink and white wines have completely different baseline ranges of chemical substances. For instance, when combining purple and white wines right into a single dataset, a purple wine that has completely common chemistry relative to different purple wines could also be recognized as an outlier primarily based solely on its sulfur content material in comparison with the mixed imply of purple and white wines. Due to this fact, we scaled every wine sort individually utilizing the median and Interquartile Vary (IQR) of every wine sort, after which mixed the 2.

# Scale every wine sort individually
from sklearn.preprocessing import RobustScaler
scaled_parts = []
for wine_type in ['red', 'white']:
    subset = df[df['type'] == wine_type][features]
    scaled_parts.append(RobustScaler().fit_transform(subset))

// 3. Figuring out When To Exclude A Technique

Elliptic Envelope assumes your knowledge follows a multivariate regular distribution. Ours did not. Six of 11 options had skewness above 1, and one function hit 5.4. We stored the Elliptic Envelope within the comparability for completeness, however left it out of the consensus vote.

# Figuring out Which Technique Performs Finest For This Wine Dataset

Picture by Writer

Can we decide a “winner” given the traits of our knowledge (heavy skewness, combined inhabitants, no identified floor reality)?

Strong Z-Rating, IQR, Isolation Forest, and LOF all deal with skewed knowledge moderately nicely. If pressured to select one, we might go along with Isolation Forest: no distribution assumptions, considers all options directly, and offers with combined populations gracefully.

However no single methodology does every part:

• Isolation Forest can miss outliers which are solely excessive on one function (Z-Rating/IQR catches these)
• Z-Rating/IQR can miss outliers which are uncommon throughout a number of options (multidimensional outliers)

The higher strategy: use a number of strategies and belief the consensus. The 143 wines flagged by 3 or extra strategies are way more dependable than something flagged by a single methodology alone.

This is how we calculated consensus:

# Depend what number of strategies flagged every pattern
consensus = zscore_out + iqr_out + iforest_out + lof_out
high_confidence = df[consensus >= 3]  # Recognized by 3+ strategies

With out floor reality (as in most real-world tasks), methodology settlement is the closest measure of confidence.

# Understanding What All This Means For Your Personal Tasks

 
Outline your downside earlier than selecting your methodology. What sort of “uncommon” are you really on the lookout for? Knowledge entry errors look completely different from measurement anomalies, and each look completely different from real uncommon instances. The kind of downside factors to completely different strategies.

Verify your assumptions. In case your knowledge is closely skewed, the Normal Z-Rating and Elliptic Envelope will steer you unsuitable. Have a look at your distributions earlier than committing to a technique.

Use a number of strategies. Samples flagged by three or extra strategies with completely different definitions of “outlier” are extra reliable than samples flagged by only one.

Do not assume all outliers ought to be eliminated. An outlier could possibly be an error. It may be your most attention-grabbing knowledge level. Area information makes that decision, not algorithms.

# Concluding Remarks

 
The purpose right here is not that outlier detection is damaged. It is that “outlier” means various things relying on who’s asking. Z-Rating and IQR catch values which are excessive on a single dimension. Isolation Forest and LOF discover samples that stand out of their general sample. Elliptic Envelope works nicely when your knowledge is definitely Gaussian (ours wasn’t).

Work out what you are actually on the lookout for earlier than you decide a technique. And should you’re undecided? Run a number of strategies and go along with the consensus.

# FAQs

// 1. Figuring out Which Approach I Ought to Begin With

A very good place to start is with the Isolation Forest approach. It doesn’t assume how your knowledge is distributed and makes use of all your options on the similar time. Nevertheless, if you wish to determine excessive values for a selected measurement (comparable to very hypertension readings), then Z-Rating or IQR could also be extra appropriate for that.

// 2. Selecting a Contamination Price For Scikit-learn Strategies

It is dependent upon the issue you are attempting to resolve. A generally used worth is 5% (or 0.05). However remember the fact that contamination is a quota. Because of this 5% of your samples will probably be categorised as outliers, no matter whether or not there really are 1% or 20% true outliers in your knowledge. Use a contamination charge primarily based in your information of the proportion of outliers in your knowledge.

// 3. Eradicating Outliers Earlier than Splitting Prepare/take a look at Knowledge

No. It’s best to match an outlier-detection mannequin to your coaching dataset, after which apply the skilled mannequin to your testing dataset. Should you do in any other case, your take a look at knowledge is influencing your preprocessing, which introduces leakage.

// 4. Dealing with Categorical Options

The strategies lined right here work on numerical knowledge. There are three potential alternate options for categorical options:

• encode your categorical variables and proceed;
• use a way designed for mixed-type knowledge (e.g. HBOS);
• run outlier detection on numeric columns individually and use frequency-based strategies for categorical ones.

// 5. Figuring out If A Flagged Outlier Is An Error Or Simply Uncommon

You can’t decide from the algorithm alone when an recognized outlier represents an error versus when it’s merely uncommon. It flags what’s uncommon, not what’s unsuitable. For instance, a wine that has a particularly excessive residual sugar content material may be a knowledge entry error, or it may be a dessert wine that’s meant to be that candy. Finally, solely your area experience can present a solution. Should you’re uncertain, mark it for overview relatively than eradicating it robotically.
 
 

Nate Rosidi is a knowledge scientist and in product technique. He is additionally an adjunct professor instructing analytics, and is the founding father of StrataScratch, a platform serving to knowledge scientists put together for his or her interviews with actual interview questions from prime firms. Nate writes on the most recent traits within the profession market, offers interview recommendation, shares knowledge science tasks, and covers every part SQL.