Boost Debt Collection and Recovery using Machine Learning

$49
$49
Umer Mirza
2 ratings

This is a real-world data science case study that used predictive modeling and machine learning to assist credit lending firms improve their debt collection rates. This case study discusses a machine learning model created in R to help lending businesses improve their debt collection processes.

This case study will assist you in increasing debt recovery by improving the traditional debt collection system of your crediting company. The machine learning model implemented in this case study enhances an existing recovery system by creating focus groups for businesses to boost debt collection.


Contents

1. Introduction

2. Understanding the Recovery System

3. Goals and objectives

3.1 Optimum Cost

3.2 Improved Collector Efficiency

3.3 Prioritization

3.4 Up-to-date information at one place

3.5 Regular Monitoring

3.6 Dynamic Communication

3.7 Interactive Dashboard for Recoveries

4. Overview of the Solution

4.1 Machine Learning and Predictive Modeling

4.2 High Level Design

4.3 Data Collection

4.4 Data Preparation

4.5 Exploratory Data Analysis

4.6 Feature Engineering

4.6.1 Collection Score

4.6.2 Repayment Score

4.6.3 Expert Score

4.7 Attribute Importance and Feature Selection

4.8 Modeling

4.8.1 Training

4.8.2 Labeling of Historical Data

4.8.3 Creation of the Training, Testing and Cross Validation Datasets

4.8.4 Choosing a model for Classification

4.8.5 Testing and Cross Validation

4.9 Results Analysis and Evaluation

4.9.1 Cross Validation-1 results (CV1)

4.9.2 Cross Validation-2 results (CV2)

5. Tools and Technologies Used

2 ratings
  • An in-depth and insightful case study

  • Size
    2.6 MB
  • Length
    38 pages
  • An in-depth and insightful case study
  • Size2.6 MB
  • Length38 pages

Ratings

3.0
(2 ratings)
5 stars
50%
4 stars
0%
3 stars
0%
2 stars
0%
1 star
50%
Powered by

Checkout

Boost Debt Collection and Recovery using Machine Learning

Enter your info to complete your purchase

Card

or pay with
You'll be charged US$49.