Interview Prep
Career
GenAI
Prompt Engg
ChatGPT
LLM
Langchain
RAG
AI Agents
Machine Learning
Deep Learning
GenAI Tools
LLMOps
Python
NLP
SQL
AIML Projects

Reading list

Machine Learning Basics for a Newbie
6 Steps of Machine learning Lifecycle Introduction to Predictive Modeling
Introduction to Exploratory Data Analysis & Data Insights Descriptive Statistics Inferential Statistics How to Understand Population Distributions?
Reading Data Files into Python Different Variable Datatypes
Probability for Data Science Basic Concepts of Probability Axioms of Probability Conditional Probability
Central Tendencies for Continuous Variables Spread of Data KDE plots for Continuous Variable Overview of Distribution for Continuous variables Normal Distribution Skewed Distribution Skeweness and Kurtosis Distribution for Continuous Variable
Central Tendencies for Categorical Variables Understanding Discrete Distributions Performing EDA on Categorical Variables
Dealing with Missing Values Understanding Outliers Identifying Outliers in Data Outlier Detection in Python Outliers Detection Using IQR, Z-score, LOF and DBSCAN
Sample and Population Central Limit Theorem Confidence Interval and Margin of Error
Bivariate Analysis Introduction
Covariance Pearson Correlation Spearman's Correlation & Kendall's Tau Correlation versus Causation Tabular and Graphical methods for Bivariate Analysis Performing Bivariate Analysis on Continuous-Continuous Variables
Tabular and Graphical methods for Continuous-Categorical Variables Introduction to Hypothesis Testing P-value Two sample Z-test T-test T-test vs Z-test Performing Bivariate Analysis on Continuous-Catagorical variables
Chi-Squares Test Bivariate Analysis on Categorical Categorical Variables
Multivariate Analysis A Comprehensive Guide to Data Exploration The Data Science behind IPL
Supervised Learning vs Unsupervised Learning Reinforcement Learning Generative and Descriminative Models Parametric and Non Parametric model
Machine Learning Pipeline Preparing Dataset Build a Benchmark Model: Regression Build a Benchmark Model: Classification
Evaluation Metrics for Machine Learning Everyone should know Confusion Matrix Accuracy Precision and Recall AUC-ROC Log Loss R2 and Adjusted R2
Dealing with Missing Values Replacing Missing Values Imputing Missing Values in Data Working with Categorical Variables Working with Outliers Preprocessing Data for Model Building
Understanding Cost Function Understanding Gradient Descent Math Behind Gradient Descent Assumptions of Linear Regression Implement Linear Regression from Scratch Train Linear Regression in Python Implementing Linear Regression in R Diagnosing Residual Plots in Linear Regression Models Generalized Linear Models Introduction to Logistic Regression Odds Ratio Implementing Logistic Regression from Scratch Introduction to Scikit-learn in Python Train Logistic Regression in python Multiclass using Logistic Regression How to use Multinomial and Ordinal Logistic Regression in R ? Challenges with Linear Regression Introduction to Regularisation Implementing Regularisation Ridge Regression Lasso Regression
Introduction to K Nearest Neighbours Determining the Right Value of K in KNN Implement KNN from Scratch Implement KNN in Python
Bias Variance Tradeoff Introduction to Overfitting and Underfitting Visualizing Overfitting and Underfitting Selecting the Right Model What is Validation? Hold-Out Validation Understanding K Fold Cross Validation
Introduction to Feature Selection Feature Selection Algorithms Missing Value Ratio Low Variance Filter High Correlation Filter Backward Feature Elimination Forward Feature Selection Implement Feature Selection in Python Implement Feature Selection in R
Introduction to Decision Tree Purity in Decision Tree Terminologies Related to Decision Tree How to Select Best Split Point in Decision Tree? Chi-Squares Information Gain Reduction in Variance Optimizing Performance of Decision Tree Train Decision Tree using Scikit Learn Pruning of Decision Trees
Introduction to Feature Engineering Feature Transformation Feature Scaling Feature Engineering Frequency Encoding Automated Feature Engineering: Feature Tools
Introduction to Naive Bayes Conditional Probability and Bayes Theorem Introduction to Bayesian Adjustment Rating: The Incredible Concept Behind Online Ratings! Working of Naive Bayes Math behind Naive Bayes Types of Naive Bayes Implementation of Naive Bayes
Understanding how to solve Multiclass and Multilabled Classification Problem Evaluation Metrics: Multi Class Classification
Introduction to Ensemble Techniques Basic Ensemble Techniques Implementing Basic Ensemble Techniques Finding Optimal Weights of Ensemble Learner using Neural Network Why Ensemble Models Work well?
Introduction to Stacking Implementing Stacking Variants of Stacking Implementing Variants of Stacking Introduction to Blending Bootstrap Sampling Introduction to Random Sampling Hyper-parameters of Random Forest Implementing Random Forest Out-of-Bag (OOB) Score in the Random Forest IPL Team Win Prediction Project Using Machine Learning Introduction to Boosting Gradient Boosting Algorithm Math behind GBM Implementing GBM in python Regularized Greedy Forests Extreme Gradient Boosting Implementing XGBM in python Tuning Hyperparameters of XGBoost in Python Implement XGBM in R/H2O Adaptive Boosting Implementing Adaptive Boosing LightGBM Implementing LightGBM in Python Catboost Implementing Catboost in Python
Different Hyperparameter Tuning methods Implementing Different Hyperparameter Tuning methods GridsearchCV RandomizedsearchCV Bayesian Optimization for Hyperparameter Tuning Hyperopt
Understanding SVM Algorithm SVM Kernels In-depth Intuition and Practical Implementation SVM Kernel Tricks Kernels and Hyperparameters in SVM Implementing SVM from Scratch in Python and R
Introduction to Principal Component Analysis Steps to Perform Principal Compound Analysis Computation of Covariance Matrix Finding Eigenvectors and Eigenvalues Implementing PCA in python Visualizing PCA A Brief Introduction to Linear Discriminant Analysis Introduction to Factor Analysis
Introduction to Clustering Applications of Clustering Evaluation Metrics for Clustering Understanding K-Means Implementation of K-Means in Python Implementation of K-Means in R Choosing Right Value for K Profiling Market Segments using K-Means Clustering Hierarchical Clustering Implementation of Hierarchial Clustering DBSCAN Defining Similarity between clusters Build Better and Accurate Clusters with Gaussian Mixture Models
Understand Basics of Recommendation Engine with Case Study
8 Ways to Improve Accuracy of Machine Learning Models
Introduction to Dask Working with CuML
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to Machine Learning Interpretability Framework and Interpretable Models model Agnostic Methods for Interpretability Implementing Interpretable Model Understanding SHAP Out-of-Core ML Introduction to Interpretable Machine Learning Models Model Agnostic Methods for Interpretability Game Theory & Shapley Values
Introduction to AutoML Implementation of MLBox Introduction to PyCaret TPOT Auto-Sklearn EvalML
Pickle and Joblib Introduction to Model Deployment
Deploying Machine Learning Model using Streamlit Deploying ML Models in Docker Deploy Using Streamlit Deploy on Heroku Deploy Using Netlify Introduction to Amazon Sagemaker Setting up Amazon SageMaker Using SageMaker Endpoint to Generate Inference Deploy on Microsoft Azure Cloud Introduction to Flask for Model Deploying ML model using Flask
Model Deployment in Android Model Deployment in Iphone

Getting your clustering right (Part II)

Tavish Srivastava
Tavish Srivastava Last Updated : 25 Jun, 2020
5 min read

I was starring at the computer screen for the final clustering result. Finally, I opened the output file and found the first cluster with more than 90% of the data-points. 6 other clusters composed the 10% of the remaining data-points. I packed up my bag and thought over the possible reasons of this dramatic failure of the technique on the way home.

This article will illustrate how to tackle such problems in a systematic manner by exploring the possible reasons of such failure. As this is the second part of the concept (please read basics of clustering here), we assume the reader is comfortable with the two clustering techniques widely used in the industry and their mechanisms.

[stextbox id=”section”]Definition of a good cluster analysis :[/stextbox]

There are two basic requirements of a good cluster analysis :

1. Data-points within same cluster share similar profile : Statistical method to judge this criterion is simply checking the standard deviation for each input variable in each cluster. A perfect separation in case of cluster analysis is rarely achieved. Hence,even one standard deviation distance between two cluster means is considered to be a good separation.

2. Well spread proportion of data-points among clusters : There are no industry standards for this requirement. But a minimum of 5% and maximum of 35% of the total population can be assumed as a safe range for each cluster.

[stextbox id=”section”]A hard nut to crack:[/stextbox]

This illustrative example is very similar to the problem I faced recently while doing a cluster analysis. Following is what I did to build clusters :

1. Identifying all possible variables which can be used for clustering technique

2. Outlier treatment and missing value fixation

3. Identifying most significant variables to be considered for final clustering analysis using VARCLUS, one of the technique to find independent variables

4. Finding final clusters using FASTCLUS, fastest technique to do a k-means clustering

Following is a graphical representation of the clusters I get:

Uneven clusters

Cluster 1   :            90%

Cluster 2     :            5%

Cluster 3     :            5%

This does not qualify as a good cluster analysis.

[stextbox id=”section”]What could have gone wrong?[/stextbox]

Whenever stuck with bad results for any modelling technique, the best way to solve it is not trying different solution but to explore what could have gone wrong. Let’s try to do the same in this case.  Following are some of the hypothesis around what could have gone wrong :

1. Outliers still present : Try making outlier definition stricter. This has been a savior for me in most of the cases. Try capping and flouring instead of removing the outlier.

Demo2

2. Presence of overshadowing variable : This kind of variable generally become visible in the FASTCLUS output, in the significance table. If the significance index of a particular variable is exceptionally high, try replacing it with the next best variable. This next best variable can be found at the VARCLUS step.

What if the problem still remains? What does this indicate?

It indicates that the population is too homogeneous to be segmented. This problem is the hardest nut to crack. Try incorporating more data points to start with. If the problem still remains we need to do clustering at a finer level. We will now discuss this method in detail.

Possible Clustering Technique and their advantages

1. Hierarchical Clustering : The advantage of this technique is that it becomes very handy to club different data-points. In other words, the output of the model is a tree and we can choose any combination from the tree to build clusters for different number of clusters. The disadvantage of technique is that it can handle only few data-points and takes exponential time for the high number of observations. If this were not a constraint for the technique, no cluster analysis would have failed.

2. k-means Clustering : The advantage of this technique is that it can handle huge number of observations and takes very less time compared to all other available techniques. The disadvantage of the technique is that changing the process in between to club data-points to the second best cluster is not possible. Hence, the method is much more rigid when compared to  Hierarchical Clustering.

The two techniques have opposite pros and cons and hence can be used together to compliment each other.

[stextbox id=”section”]What if we combine the two methods?[/stextbox]

Following is the technique I finally used to get reasonable and actionable clusters :

1. Use outlier removal and overshadowing variable removal technique

2. Use k-means method to get many granular cluster : Build number of granular clusters. For n number of final cluster required, I put k=3 to 4 times n. Following is an illustrative figure to demonstrate this step :

Granular clusters

We get 10 smaller clusters with size ranging from 2-25% of the same population.

3. Use Hierarchical Clustering to club these granular clusters : Plug the mean values of the granular clusters as individual data-points to hierarchical clustering. This will give a line diagram as output. Choose the combinations which will not lead a cluster to go above 35% and make sure all the clusters come above 5%. Following is an illustrative figure of this step :

Clubbing

The output of this step is a set of clusters complying to both the constraints of a good clustering analysis.

[stextbox id=”section”]End Notes :[/stextbox]

As the method demonstrated above uses finer differences between observation, which were not differentiated by simply using k-means, the technique needs to be verified for the separation test.  In such cases, when strong separation is not possible between observations, vastly different actionable should not be taken for each cluster.

What do think of this technique? Do you think this provides a solution to any problem you face? Are there any other techniques you use to improve separation of your clustering models ? Do let us know your thoughts in the comments below.

If you like what you just read & want to continue your analytics learning, subscribe to our emails or like our facebook page.

 

 

AnalyticsBusiness AnalyticsclusteringSegmentationuniform population
Tavish Srivastava
Tavish Srivastava

Tavish Srivastava, co-founder and Chief Strategy Officer of Analytics Vidhya, is an IIT Madras graduate and a passionate data-science professional with 8+ years of diverse experience in markets including the US, India and Singapore, domains including Digital Acquisitions, Customer Servicing and Customer Management, and industry including Retail Banking, Credit Cards and Insurance. He is fascinated by the idea of artificial intelligence inspired by human intelligence and enjoys every discussion, theory or even movie related to this idea.

Free Courses

Generative AI 4.7

Generative AI - A Way of Life

Explore Generative AI for beginners: create text and images, use top AI tools, learn practical skills, and ethics.
Large Language Models 4.5

Getting Started with Large Language Models

Master Large Language Models (LLMs) with this course, offering clear guidance in NLP and model training made simple.
Prompt Engineering 4.6

Building LLM Applications using Prompt Engineering

This free course guides you on building LLM apps, mastering prompt engineering, and developing chatbots with enterprise data.
LlamaIndex 4.8

Improving Real World RAG Systems: Key Challenges & Practical Solutions

Explore practical solutions, advanced retrieval strategies, and agentic RAG systems to improve context, relevance, and accuracy in AI-driven applications.
RAG systems using LlamaIndex 4.7

Microsoft Excel: Formulas & Functions

Master MS Excel for data analysis with key formulas, functions, and LookUp tools in this comprehensive course.

Recommended Articles

Responses From Readers

Clear

Rashmi
Rashmi

Hi Tavish, Can you throw some light on the output results that come out of running PROC VARCLUS and FASTCLUS and explain the interpretations and industry standards? For example things like "cubic clustering criterion". If you can take the output and provide some examples that would be great!

123

Newbie analytics
Newbie analytics

Hi Tavish Can you please answer few questions for me : 1. I have a dataset of ~5 lakhs records and a system of high computation. I am able to perform both k means and heirarchical in R successfully. Which method should I prefer? 2. I have a dataset of 5 lakh rows and 50 variables. There are categorical variables with multiple categories (~Eg. State) and there are nominal categories (~Eg. loan issuance year). How do I handle such categorical and nominal categories? I am using R and am not aware of the any procedure which might replicate VARCLUS procedure in R. Any suggestions?

123

fateme
fateme

i want to use this article in definition of my thesis. could you plz send me the references of this article?

123

Write for us

Write, captivate, and earn accolades and rewards for your work
  • Reach a Global Audience
  • Get Expert Feedback
  • Build Your Brand & Audience
  • Cash In on Your Knowledge
  • Join a Thriving Community
  • Level Up Your Data Science Game
imag
Congratulations, You Did It!
Well Done on Completing Your Learning Journey. Stay curious and keep exploring!
Clustering | Different Methods, and Applications (Updated 2024)
Clustering | Different Methods, and Applications (Updated 2024)
Getting your clustering right (Part I)
Getting your clustering right (Part I)

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details