Customer Personality analysis is the process of analyzing the customers of a company through their purchases. In this day and age of digital marketing, it has become very common for companies to send personalized ads and promotions for better customer sales and support. Customer personality analysis helps this process by providing necessary information to the companies to better understand their customers. In this project, we collected a dataset and performed necessary operations like data cleaning, data analysis, feature transformation, and modeling experiments.
The raw dataset was collected from Kaggle. The organized version of this dataset can be found in this GitHub repository. This is a structured dataset that contains information about customers' personal details and their purchases of various types of products along with their medium of purchase. Our goal is to segment customers into different groups based on these data. The dataset contains 2240 samples and 29 columns
- Data Analysis
- Null Value Imputation
- Outlier Detection
- Feature Creation
- Scaling
- Feature Selection
- Feature Encoding
- Feature Reduction using PCA
- Implementation of
KMeans
Clustering algorithm from Scratch - Validation using Silhouette Coefficient and Elbow Method
- Hyperparameter Tuning
- DBSCAN algorithm using Scikit-learn
- Cluster visualization