Scribd
Upload
108 views8 pages

Market Mix Modelling

This document discusses market mix modeling and segmentation analysis. It explains that market mix modeling is used to understand how marketing activities drive business metrics and is a decision-making tool used to estimate the effectiveness of initiatives. It then describes performing hierarchical and k-means clustering on customer data to identify four segments based on similarities in age, income, and other features. Principal component analysis was used to reduce the data dimensions while preserving variance, identifying three key components explaining 80% of variance for further k-means clustering. Purchase data and charts are then discussed to analyze purchase occasions, incidence, and revenue by segment and brand.

Uploaded by

Srivatsan Sabarish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
108 views8 pages

Market Mix Modelling

This document discusses market mix modeling and segmentation analysis. It explains that market mix modeling is used to understand how marketing activities drive business metrics and is a decision-making tool used to estimate the effectiveness of initiatives. It then describes performing hierarchical and k-means clustering on customer data to identify four segments based on similarities in age, income, and other features. Principal component analysis was used to reduce the data dimensions while preserving variance, identifying three key components explaining 80% of variance for further k-means clustering. Purchase data and charts are then discussed to analyze purchase occasions, incidence, and revenue by segment and brand.

Uploaded by

Srivatsan Sabarish
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

Market mix modelling

Develop the best product or service and offer it at the right price through the right channels.

The key purpose of a Marketing Mix Model is to understand how various marketing activities are driving
the business metrics of a product. It is used as a decision-making tool by brands to estimate the
effectiveness of various marketing initiatives.
Our segmentation is based on similarities and differences between individual consumers and features
that characterise them …age 20 and 70,income 100000-150000,

age diff 50 ,income diff 50000 much weight for income.The numbers from 20-70 will be insignificant
when compared to income . In general we want to treat all our variables equally.
So we did standardizing.

HIERARCHIAL CLUSTERING

Found out there are 4 clusters

And we did the same using kmeans clustering

Segementation:
PCA :

These components are arranged in order of importance in this case how much the variance of
the data is explained by each component

PCA applies linear transformation of data which creates 7 new variables while some of them large
proportion of variance while others almost none. Together 7 components explains 100% variability of
the data

1st component explians 35%....our task is to preserve subset of components while preserving variance

array([0.35696328, 0.26250923, 0.18821114, 0.0755775 , 0.05716512,


0.03954794, 0.02002579])

At the 3 componenst it covers 80% of variance . Rule of thumb is to keep data above 80%. So we
choose 3.

After that we did kmean using this pca.


Purchase data:
Purchase occasion and purchase incidence

The average number of store visits for each of the four segments using a bar chart.

The
average
number of
purchases
by
segments
Each brand

Revenue from
Each brand

You might also like