Figuring out customer's behaviour in order to identify the key indicators of customer's churn status, Moreover, Build a classification model that predicts whether the customer would churn or otherwise.
- Python
- Pandas (Library)
- Numpy (Library)
- Matplotlib.pyplot (Library)
- Seaborn (Library)
- Sklearn (Library)
- Excel (Dashboard and Analysis)
- PowerBI (Dashboard and Analysis)
- Decision Tree
- Random Forest Classifier
You can download the dataset from the repo files or by clicking Here
| Column | Description |
|---|---|
| CustomerID | Unique customer ID |
| Churn | Churn Flag |
| Tenure | Tenure of customer in organization |
| PreferredLoginDevice | Preferred login device of customer |
| CityTier | City tier |
| WarehouseToHome | Distance in between warehouse to home of customer |
| PreferredPaymentMode | Preferred payment method of customer |
| Gender | Gender of customer |
| HourSpendOnApp | Number of hours spend on mobile application or website |
| NumberOfDeviceRegistered | Total number of deceives is registered on particular customer |
| PreferedOrderCat | Preferred order category of customer in last month |
| SatisfactionScore | Satisfactory score of customer on service |
| MaritalStatus | Marital status of customer |
| NumberOfAddress | Total number of added added on particular customer |
| Complain | Any complaint has been raised in last month |
| OrderAmountHikeFromlastYear | OrderAmountHikeFromlastYear |
| CouponUsed | Total number of coupon has been used in last month |
| OrderCount | Total number of orders has been places in last month |
| DaySinceLastOrder | Day Since last order by customer |
| CashbackAmount | Average cashback in last month |