Skip to content

The primary goal of this project is to convert free users of a financial tracking app into paid members. This conversion will be achieved by building a model that identifies users who are unlikely to enroll in the paid version of the app.

License

Notifications You must be signed in to change notification settings

REAtes/Directing-App-Customers-to-Subscription

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Directing Customers to Subscription through App Behavior Analysis

Overview

The primary goal of this project is to convert free users of a financial tracking app into paid members. This conversion will be achieved by building a model that identifies users who are unlikely to enroll in the paid version of the app.

Problem Statement

The project centers around a fintech enterprise that provides a financial tracking app in both free and paid versions. The objective is to create a model that can accurately identify users who are less likely to upgrade to the paid version. By doing so, the company can optimize its resources by focusing its marketing efforts on users who are more likely to convert to paid membership.

Project Workflow

1. Dataset Exploration:

  • Explore the provided dataset to understand its structure and characteristics.
  • Identify key features and gain insights into the nature of the data.

2. Data Visualization:

  • Visualize relevant data patterns and distributions.
  • Gain a deeper understanding of the relationships between different variables.

3. Feature Engineering:

  • Manipulate and transform data to create meaningful features.
  • Enhance the dataset to improve model performance.

4. Label Encoding - Binary Encoding & One-Hot Encoding:

  • Encode categorical variables using both binary encoding and one-hot encoding techniques.
  • Prepare the data for model training by converting categorical features into a suitable format.

5. Base Models:

  • Develop initial machine learning models to establish a baseline performance.
  • Evaluate the models to understand their predictive capabilities.

6. Hyperparameter Optimization:

  • Fine-tune model hyperparameters to improve overall performance.
  • Use optimization techniques to enhance model accuracy and efficiency.

7. SHAP Summary Plot:

  • Utilize SHAP (Shapley Additive exPlanations) to interpret and explain model predictions.
  • Generate summary plots to understand the impact of different features on the model's decision-making.

Conclusion

The objective of this project is to tackle the problem of converting users who use the app for free to paid members, using behavior analysis. The project will follow a structured workflow, including exploring the dataset, visualizing the data, engineering the features, and building the model. The aim is to create an efficient predictive model. The README provides an overview of each step in the project, highlighting the main tasks and methodologies used to achieve the intended outcome.

About

The primary goal of this project is to convert free users of a financial tracking app into paid members. This conversion will be achieved by building a model that identifies users who are unlikely to enroll in the paid version of the app.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages