An Introduction to Artificial Intelligence assignment that uses a Deep Learning Multi-Layer Perceptron model to predict the churn rate of a company's customers by Naa Lamiorkor Boye
According to Mailchimp (n.d.), "Customer churn is the percentage of customers who stopped purchasing your business's products or services during a certain period of time. Your customer churn rate indicates how many of your existing customers are not likely to make another purchase from your business." It is an essential concern of a business as its customers determine its revenue and profit. When a company knows what would cause its customers to stop purchasing their products or services, it can make careful decisions to prevent that problem.
My project is composed of the following structure:
- Importing relevant libraries such as pandas, TensorFlow, LabelEncoder, GridSearchCV and joblib
- Importing and displaying the dataset
- Encoding categorical columns to type int or float
- Scaling the data
- Using feature importance through RandomForestClassifier to determine the relevance of the various features
- Implementing a Multi-Layer Perceptor model and passing it through GridSearchCV to optimise its training performance
- Selecting the best estimators and using them to test the model's performance
- Deploying the model using Streamlite and allowing users to input their own feature values
Find the link to my video utilising my deployed model here: https://youtu.be/TIzAEzuGpvY
Customer churn: definition and how to Reduce it | Mailchimp. (n.d.). Mailchimp. https://mailchimp.com/resources/customer-churn/#:~:text=Customer%20churn%20is%20the%20percentage,another%20purchase%20from%20your%20business.