Skip to content

SwagatDas/Tensors-Analytics2.0

 
 

Repository files navigation

Tensors-Analytics2.0

This project was a part of the work done in a Hackathon conducted by Orient Bell Tiles. This was a team project done collaboratively with - Sandeep Pattanayak and Supriya

This is the interactive portal designed for real world problems which corporates face like -

1. Identification of appropriate target audience for a new product.

The proper identification of target audience facilitates targeted advertising, thus, maximising the effectiveness and impact of the advertising expenditures. This has an added cost cutting benefit as with a list of targeted audience, the advertising can be much more personalised.

A glimpse at the functioning Top Customer Prediction portal - The customisable slider on the top allows the user to adjust size of the target audience.

Image

2. Clustering of customers into similar groups

This helps in identifying the customers behaviour pattern and their taste which then facilitates the personalisation of products specific to certain clusters.

Various behavioural patterns like buying frequency, similarity between items bought, quantity of items bought etc were considered to segregate the entire customer base into clusters.

A glimpse of the Clustering Application -

Image

3. An interactive visualisation portal which can be used at wide ranging granularity level of product specific analysis to city specific to region specific.

The interactive portal also supports multi-feature analysis along with unary features.

Step 1 - Select the necessary features

Image

Step 2 - Click on Generate to get the plots

Image

Another glimpse

Image

PS: The portal for Feature 1 and 2 is in this repository - https://github.com/PSandeepSandy/Tensors-Analytics2.0

PS: The portal for Feature 3 is in this repository - https://github.com/PSandeepSandy/Tensors-Analytics

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • JavaScript 41.5%
  • HTML 40.0%
  • Python 18.1%
  • CSS 0.4%