The purpose of this project is to perform "Cutomer Analytics" of the behaviour of the different types of mall customers by dividing them into different groups and doing "Purchase Analytics" to predict the purchase behaviour of different segments of customers including models for purchase incidence, brand choice and purchase quantity.
- PCA
- Machine Learning
- Data Visualization
- Predictive Modeling
- Clustering
- Unsupervised Learning
- Python
- Pandas,Jupyter,Numpy,Sklearn
It is done in two parts:
- Segmenting the customers into different groups using KMeans clustering and PCA(Principle Component Analysis).
- Saving this model and applying the model in purchase data set.
- Gaining some important insights from the segmented data.
- Predicting the price elasticity of different features:
4.1 Price Elasticity wrt Purchase Probability (i.e if a customer will make purchase or not)
4.2 Price Elasticity wrt Brand Choice Probability (i.e which brand customer will purchase)
4.3 Price Elasticity wrt Purchase Quantity (i.e how many things a customer will purchase)