In this project based the dataset used is of an electricity power company that supplies electricity utility to coorporates, SME and residential customers. A significant amount of churn in customers is happening in the SME customer segments which is decreasing the revenue of the company. At a high level research the customer churn among SME segment is driven by price sensitivity.
The motive of this project is to develop a predictive model that will predict the customers likely to churn and form a strategic perspective to decrease the churn rate of customers, some monetary benefits may be provided to the predicted customers.
Datasets used:
- Customer data - which should include characteristics of each client, for example, industry, historical electricity consumption, date joined as customer etc
- Churn data - which should indicate if customer has churned
- Historical price data – which should indicate the prices the client charges to each customer for both electricity and gas at granular time intervals
From the XGBoost model it was observed that other factors apart from price sensitivity like Yearly consumption, Forecasted Consumption and net margin were drivers of customer churn.
Recommendations : The strategy of monetary benefits is effective. However it should be appropiately targeted to high-valued customers with high churn probability. If not administered properly then the company may face a hard impact on their revenue
In case of failure of loading Jupyter Notebooks on Github, the following notebooks can be found in nbviewer. Click on the respective hyperlinks to view::