rllm.datasets.ChurnModelling

class rllm.datasets.ChurnModelling(cached_dir: str, forced_reload: bool | None = False)

Bases: Dataset

The Churn Modelling dataset is used to predict which customers are likely to churn from the organization by analyzing various attributes and applying machine learning and deep learning techniques.

Customer churn refers to when a customer (player, subscriber, user, etc.) ceases their relationship with a company. Online businesses typically treat a customer as churned once a particular amount of time has elapsed since the customer’s last interaction with the site or service.

Customer churn occurs when customers or subscribers stop doing business with a company or service, also known as customer attrition. It is also referred to as loss of clients or customers. Similar to predicting employee turnover, we are going to predict customer churn using this dataset.

The dataset encompasses a variety of features pertaining to customers and their interactions with the company. The primary objective is to predict whether a customer will churn.

Parameters:

• cached_dir (str) – Root directory where dataset should be saved.

• forced_reload (bool) – If set to True, this dataset will be re-processed again.

Statics:
Name   Customers   Features
Size   10000       14

download()

download the datasets to self.raw_dir

process()

process data and save to ‘./cached_dir/{dataset}/processed/’.

property processed_filenames

file names in the self.processed_dir

property raw_filenames

file names in the self.raw_dir