capstone_projects

Kaggle Competition - Google Analytics Customer Revenue Prediction

overview

The 80/20 rule has proven true for many businesses–only a small percentage of customers produce most of the revenue. As such, marketing teams are challenged to make appropriate investments in promotional strategies.

In this competition, you’re challenged to analyze a Google Merchandise Store (also known as GStore, where Google swag is sold) customer dataset to predict revenue per customer. Hopefully, the outcome will be more actionable operational changes and a better use of marketing budgets for those companies who choose to use data analysis on top of GA data.

---

Data:

provided by google. available at :https://www.kaggle.com/c/ga-customer-revenue-prediction/data

Prerequisites:

• python libraries(numpy,pands,matplotlib.,etc)
• machine learning algorithms.
• Data pre-processing techniques.

Regarding files:

• case_study.ipynb : This file contains everything from data collection, preprocessing, EDA, features building, Model building
• PipeLine.ipynb : In this file we implemented final pipe-line from scratch(with out using sklearn pipe-line)., So here we are taking raw data-point/querypoint from this function "final_fun_1(data_point)"., so internally this function featurize the raw data point and loads all our pretrained models finally it will return revenue for the given data point.

Authors:

• kireeti kunam

Blog:

• In this blog I explanied in detailed about this project. Please visit for more details: https://medium.com/analytics-vidhya/google-analytics-customer-revenue-prediction-e41da071d942

Acknowledgments:

Thanks to winners solution. We referred that to implement it in python - https://www.kaggle.com/c/ga-customer-revenue-prediction/discussion/82614