This contains data science applications in the retail industry projects
- Customer Churn Prediction
- Product Recommendation for Customers
- Demand Forecasting for retail products
Churn prediction is identifying customers that are most likely to live a service. This is important for most companies as acquiring new customers is more costlier than retaining old ones, So the results of Churn prediction help companies focus on customers that are likely to churn and develop strategies for retaining those customers.
Here I worked with E Commerce Customer Dataset gotten from Kaggle.
- I explored the data by creating visualizations, calculating statistical summaries.
- After exploration, I preprocessed the data which involved
- Encoding Categorical variables
- Imputing missing values
- Finally, I built the model using Logistic Regression, KNN, Random Forest, Naive Bayes, and XGBoost
Recommender systems in a very general way operate by suggesting the most likely thing a user want to receive next to a user. By looking at users history on your platform, you are able to profile them and give them recommendations based on that profile
Two datasets were used for this project:
- Movie Recommendation Dataset gotten from kaggle
- Yelp Dataset gotten from kaggle
I built the recommender system using matrix factorization on the first Dataset, and I used Apache Spark Alternating Least Square for the second dataset, because it has more ratings
... More projects will be added as time goes on
Pls Star if you find this repo helpful