Retail Product Category Classification Based on Features
The main objective of this model is to build a predictive model which is able to distinguish between main retail product categories.
Data:
The data is collected from Otto Group which contains a dataset with 93 features for more than 200,000 products. It has a training dataset which has ID, Features and Target Class and a testing dataset which has ID and Features.
Model:
Initially we are doing some preprocessing such as cleaning data and removing NAs like that.
Then we are using Random Forest Classification Algorithm for classifying the products. There we used R Scripts for the Random Forest. We set the ntree as 100 for better classfication
Output:
The output will be the products with the classes which has to be there. The accuracy is 80%.