Skip to content

It is just a fun project i did to start learning Machine Learning.

Notifications You must be signed in to change notification settings

Pragyanand/divorce-prediction

Repository files navigation

About The Project

This 'DIVORCE PREDICTOR ' project is based off of a paper published by the title of 'DIVORCE PREDICTION USING CORRELATION BASED FEATURE SELECTION AND ARTIFICIAL NEURAL NETWORKS' in June of 2019 by Mustafa Kemal YÖNTEM et al. in which the data from a survey report was used to predict the divorce in couples on the basis of Gottman couples therapy. Of the participants, 84 (49%) were divorced and 86 (51%) were married couples. In the scope of this research, it was also discovered which factors affected the divorce the most.

Here, I have take the same Dataset from the UCI Machine Learning Repository (not complete) and tried to analyse and see which factors affected the target variable (Marital Status) in my case, the most.

I have deployed it on herou. Click here to try.

Built With

  • Python
  • Flask

Description

The Dataset was obtained from UCI Machine Learning Repository and contained 170 Rows and 54 columns (Reponses of Different Questions) and another column containing the target variable , which was marital status.

The responses were recorded using a google form or a similar technique, which allowed the user to answer by selecting one of the five options which ranged from

Strongly Agree to Strongly Disagree , each of which corresponded to number ranging from 0 to 4 and marital status of every user was also recorded in the same manner 1 = Divorced & 0 = Married.

For more details, please checkout the Jupyter Notebook included. I have explained every step of the process and if that doesn't make it clear, please feel free to connect on the links mentioned below.

License

Open Sorce ? ( I don't really know, what to write here! :)

Connect

Twitter : @pragyanand
Facebook : @pragyanand
Instagram : @little.tiwari

About

It is just a fun project i did to start learning Machine Learning.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published