This is part-2 of the case study on Boost Collections and Recoveries using Machine Learning (MLBR).
Disclaimer: This case study is solely an educational exercise and information contained in this case study is to be used only as a case study example for guideline purposes. This hypothetical case study is provided for illustrative purposes only and do not represent an actual client or an actual client’s experience. All of the data, contents and information presented here have been altered and edited to protect the confidentiality and privacy of the company.
In response to readers' interest and demand, we've published a thorough and insightful case study on Gumroad. This is a real-world end-to-end machine learning case study that will assist you in increasing debt recovery by improving the traditional debt collection system of your crediting company.
This document will provide you everything you need to build a successful machine learning model, i.e. data collection (variables) and preparation, feature engineering and attribute importance, model development and evaluation, cross validation and production deployment.
Here is the high level content that you will get:
- Understanding the Recovery System
- Goals and objectives
3.1 Optimum Cost
3.2 Improved Collector Efficiency
3.4 Up-to-date information at one place
3.5 Regular Monitoring
3.6 Dynamic Communication
3.7 Interactive Dashboard for Recoveries
- Overview of the Solution
4.1 Machine Learning and Predictive Modeling
4.2 High Level Design
4.3 Data Collection
4.4 Data Preparation
- Exploratory Data Analysis
- Feature Engineering
6.1 Collection Score
6.2 Repayment Score
6.3 Expert Score
- Attribute Importance and Feature Selection
- Labeling of Historical Data
- Creation of the Training, Testing and Cross Validation Datasets
- Choosing a model for Classification
- Testing and Cross Validation
- Results Analysis and Evaluation
14.1 Cross Validation-1 results (CV1)
14.2 Cross Validation-2 results (CV2)
- Tools and Technologies