Machine Learning Model to Predict CTR with Python
Ademola Ibitayo
Data Scientist
Marketing Analytics Specialist
Data Analyst
Jupyter Notebook
Python
scikit-learn
Machine-Learning-Model-to-Predict-CTR-with-Python
This project is aimed at building machine learning models to predict click-through rates (CTR) based on historical marketing data. The model performances are measured using statistical metrics such as MSE, RMSE, MAE and R-squared.
The problem was approached from a regression standpoint due to the CTR feature being a continuous variable. The machine learning algorithms implemented include:
Linear Regression
Decision Tree Regressor
Random Forest Regressor
XGBoost Regressor
The impact of the model features on prediction values was analysed using SHAP values and visualisation (beeswarm, waterfall)
View the full project on GitHub - https://github.com/AdemolaI/Machine-Learning-Model-to-Predict-CTR-with-Python
Data Information.
SHAP beeswarm plot of top ten features from XGBoost regressor model.
